CN104462262B - A kind of method for realizing phonetic search, device and browser client - Google Patents

Abstract

The invention discloses a kind of method and apparatus for realizing phonetic search, this method includes：Obtain the voice signal of voice search user input；The voice signal is sent to voice conversion services device；Receive the corresponding character information returned after the voice signal is identified voice conversion services device；Using the character information as search term, searching request is sent to search server；Receive the search result returned with search server described in loaded and displayed.The technical scheme that the present invention is provided with voice conversion services devices by interacting and by being interacted with search server, complete and the corresponding character information of voice signal that user inputs is scanned for, and the process of search result is shown to user, form complete, effective phonetic search scheme, compared with traditional manual text search, operating process is simplified, search efficiency is improved, more convenient, perfect experience is provide the user.

Description

A method, device and browser client for realizing voice search

technical field

The invention relates to the technical field of the Internet, in particular to a method, device and browser client for realizing voice search.

Background technique

With the rapid development of mobile Internet technology, users' search behavior can occur in various environments and places, and users will have different search needs in different environments and places.

The traditional search method is based on the search process of users manually inputting text. The human-computer interaction method is often keyboard input or handwriting input. The operation process is cumbersome and the user's input experience is poor; and there are great limitations in the implementation process. In scenarios where the user cannot perform manual input, the search solution is completely ineffective. For example, the user cannot search while driving, and blind users cannot perform search. Therefore, traditional search methods cannot meet the needs of current users who want to search in various scenarios.

Contents of the invention

In view of the above problems, the present invention is proposed to provide a method, device and browser client for implementing voice search that overcome the above problems or at least partially solve the above problems.

According to one aspect of the present invention, a method for implementing voice search is provided, the method comprising:

Obtain the voice signal input by the voice search user;

sending the voice signal to a voice conversion server;

Receiving the corresponding character information returned by the speech conversion server after recognizing the speech signal;

Using the character information as a search word, send a search request to the search server;

Receiving and loading displaying the search results returned by the search server.

Optionally, the method further includes:

Obtain tag information of the voice search user;

Acquiring from the voice conversion server according to the tag information one or more keywords after speech recognition shared by friends of the voice search user and matched with the tag information;

When it is a keyword, the keyword is used as the search term; when there are multiple keywords, one keyword is selected as the search term, and a search request is sent to the search server;

Receiving and loading displaying the search results returned by the search server.

Optionally, the method further includes:

Acquiring a voice signal input by the voice search user according to an instruction triggered by the voice search user;

The voice signal is uploaded to the voice conversion server together with the tag information of the voice search user, and after the voice conversion server recognizes the voice signal into a keyword in text form, the voice signal, the recognized keyword and The tag information of the voice search user is correspondingly stored as a shared information item.

Optionally, the method further includes:

The shared information item matching the tag information of the voice search user is downloaded from the voice conversion server and stored locally.

Optionally, the method further includes:

When the character information is identified as number data conforming to a specific format, the loading entry of the corresponding operation of the number data is displayed.

Optionally,

When the character information is identified as number data conforming to a specific format, the e-commerce web page information corresponding to the number data returned by the search server is also loaded, and an entry for interactive operation with the e-commerce web page is provided.

Optionally, the method further includes:

The call recording data of the mobile terminal is obtained, and the call recording data is edited to obtain a voice signal for voice search.

Optionally, the method further includes:

Add a voice recognition module to recognize and record the voice search user's own voice, and mark it as the voice data of the voice search user, and perform manual recognition or machine learning recognition on the voice data shared or sent by friends After recording, mark it as the voice data of the corresponding friend;

Edit the voice data of the voice search user or the voice data of his friend to obtain a voice signal for voice search.

Optionally, the method further includes: performing semantic recognition on the character information, and determining the classification of the character information as a search term;

The sending the search request to the search server includes: sending the search request to the search server of the corresponding category.

Optionally, said acquiring the input voice signal includes:

Display the voice search icon on the home page of the browser client; when the voice search icon is clicked, jump to the voice search page containing the voice search control;

In response to the event that the voice search control is started, utilize the microphone of the mobile device where the browser client is located to start capturing voice signals;

In response to the event that the voice search control is turned off, stop capturing voice signals and obtain input voice signals.

Optionally,

Displaying the voice search icon on the home page of the browser client includes: displaying a microphone icon at the end of the address bar of the browser client;

The event that the voice search control is started is: the voice search control starts to be touched;

The event that the voice search control is turned off is: the voice search control ends being touched.

Optionally, the method further includes:

N hot search words are displayed on the voice search page; wherein, the N hot search words are the top N search words obtained by statistics within a statistical period, and N is a natural number;

Alternatively, search prompt information is displayed on the voice search page to prompt the user how to perform voice search.

Optionally, the method further includes:

A page close control is displayed on the voice search page, and when the page close control is triggered, the voice search page is closed and the home page of the browser client is returned.

Optionally, the method further includes:

In response to an event that a hot search word on the voice search page is clicked, jump to a search result page corresponding to the hot search word.

Optionally, the corresponding character information returned by the receiving speech conversion server after recognizing the speech signal includes: a plurality of corresponding character information returned by the receiving speech conversion server after recognizing the speech signal;

Then the method further includes: displaying the plurality of character information for selection by the user;

The using the character information as the search term is to use the character information selected by the user as the search term.

Optionally, before sending the voice signal to the voice conversion server, the method further includes:

Obtain the network connection status of the mobile device;

If the mobile device is not connected to the network, or the mobile device is connected to a problematic network, display information indicating that the network connection status of the mobile device is abnormal;

If the mobile device is connected to a normal network, the step of sending the voice signal to the voice conversion server is performed.

Optionally, the method further includes:

When receiving the information indicating the recognition error returned by the speech conversion server after recognizing the voice signal, the information indicating the recognition error is displayed.

Optionally, the method further includes:

receiving the voice conversion server performing semantic recognition on the character information and returning instruction information according to the recognized semantics;

Perform corresponding operations according to the instruction information.

According to another aspect of the present invention, a device for implementing voice search is provided, the device comprising:

A signal acquisition unit adapted to acquire a voice signal input by a voice search user;

The voice conversion interaction unit is adapted to send the voice signal to the voice conversion server; and is adapted to receive the corresponding character information returned by the voice conversion server after recognizing the voice signal;

The search interaction unit is adapted to use the character information as a search word to send a search request to a search server; and is adapted to receive search results returned by the search server;

The display unit is adapted to load and display the search results returned by the search server.

Optionally, the signal acquisition unit is further adapted to acquire tag information of the voice search user;

The voice conversion interaction unit is further adapted to obtain from the voice conversion server according to the tag information one or more speech-recognized keywords shared by friends of the voice search user and matched with the tag information;

The search interaction unit is adapted to use a keyword as a search word when the speech conversion interaction unit obtains a keyword, and selects a keyword as a search word when the speech conversion interaction unit obtains multiple keywords. word, send a search request to the search server; and be adapted to receive the search result returned by the search server;

The display unit is adapted to load and display the search results returned by the search server.

Optionally, the signal acquisition unit is further adapted to acquire a voice signal input by the voice search user according to an instruction triggered by the voice search user;

The voice conversion interaction unit is further adapted to upload the voice signal and the tag information of the voice search user to the voice conversion server, so that after the voice conversion server recognizes the voice signal into a keyword in text form, the The voice information, the recognized keyword and the tag information of the voice search user are correspondingly stored as a shared information item.

Optionally, the voice conversion interaction unit is further adapted to download the shared information item matching the voice search user's tag information from the voice conversion server, and save it locally.

Optionally, the display unit is further adapted to display a corresponding operation loading entry for the number data when the search interaction unit recognizes that the character information is number data conforming to a specific format.

Optionally, the display unit is further adapted to load the e-commerce webpage information corresponding to the number data returned by the search server when the search interaction unit recognizes that the character information is number data conforming to a specific format, and provide information corresponding to the number data. The portal for interactive operation of the e-commerce webpage.

Optionally, the signal acquisition unit is further adapted to acquire call recording data of the mobile terminal, and edit the call recording data to obtain a voice signal for voice search.

Optionally, the signal acquisition unit is further adapted to add a voice recognition module to recognize and record the voice search user's own voice, and mark it as the voice data of the voice search user, and share it with friends or The sent voice data is recorded after manual recognition or machine learning recognition, and marked as the voice data of the corresponding friend; and it is suitable for editing the voice data of the voice search user or the voice data of his friend to obtain the Voice signal for voice search.

Optionally, the search interaction unit is further adapted to perform semantic recognition on the character information, to determine the classification of the character information as a search term; and to send a search request to a search server of a corresponding classification.

Optionally, the signal acquisition unit includes: a voice search jump unit and a voice acquisition control unit;

The voice search jump unit is suitable for displaying a voice search icon on the homepage of the browser client; when the voice search icon is clicked, it jumps to a voice search page containing a voice search control;

The voice acquisition control unit is adapted to respond to the event that the voice search control is started, using the microphone of the mobile device where the browser client is located to start capturing voice signals; and is adapted to respond to the event that the voice search control is turned off , stop capturing the voice signal and get the input voice signal.

Optionally, the voice search jump unit is adapted to display a microphone icon at the end of the address bar of the browser client;

The voice acquisition control unit is adapted to start capturing voice signals with the microphone of the mobile device where the browser client is located in response to the voice search control being touched; and is adapted to stop being touched in response to the voice search control ending. Capture the speech signal to obtain the input speech signal.

Optionally, the signal acquisition unit further includes: a voice search prompt unit;

The voice search prompt unit is adapted to display N hot search words on the voice search page; wherein, the N hot search words are the top N search terms obtained from statistics within a statistical period words, N is a natural number; or, it is suitable for displaying search prompt information on the voice search page to prompt the user how to perform voice search.

Optionally, the voice search jump unit is further adapted to display a page closing control on the voice search page, and when the page closing control is triggered, close the voice search page and return to the home page of the browser client .

Optionally, the search interaction unit is further adapted to jump to the search result page corresponding to the hot search word in response to the event that the hot search word on the voice search page is clicked;

The display unit is further adapted to load and display a search result page corresponding to the hot search word.

Optionally, the voice conversion interaction unit is adapted to receive the corresponding multiple character information returned by the voice conversion server after recognizing the voice signal;

The display unit is further adapted to display the plurality of character information for selection by the user;

The search interaction unit is adapted to send a search request to a search server using character information selected by a user as a search word.

Optionally, the device further includes: a network detection unit;

The network detection unit is adapted to obtain the network connection status of the mobile device before the voice conversion interaction unit sends the voice signal to the voice conversion server;

The voice conversion interaction unit is further adapted to send the voice signal to a voice conversion server when the network detection unit detects that the mobile device is connected to a normal network;

The display unit is further adapted to display a message indicating that the network connection status of the mobile device is abnormal when the network detection unit detects that the mobile device has access to a problematic network.

Optionally, the presentation unit is further adapted to display the information indicating a recognition error when the voice conversion interaction unit receives information indicating a recognition error returned by a voice conversion server after recognizing the voice signal.

Optionally, the device further includes: an instruction execution unit;

The voice conversion interaction unit is further adapted to receive the voice conversion server performing semantic recognition on the character information and returning instruction information according to the recognized semantics;

The instruction executing unit is adapted to execute corresponding operations according to the instruction information.

According to yet another aspect of the present invention, a browser client for implementing voice search is provided, including the device for implementing voice search as described in any one of the above items.

As can be seen from the above, the technical solution provided by the present invention completes the process of searching the character information corresponding to the voice signal input by the user and presenting the search results to the user through the interaction with the voice conversion server and the search server, realizing A complete and effective voice search solution using voice signals as the carrier, compared with the traditional manual text search, simplifies the operation process, improves the search efficiency, makes the search more scene-oriented and personalized, and provides users with more Convenient and perfect experience.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same parts. In the attached picture:

FIG. 1 shows a flowchart of a method for voice search according to an embodiment of the present invention;

FIG. 2 shows a flow chart of a method for voice search according to another embodiment of the present invention;

Fig. 3 shows a schematic diagram of a device for implementing voice search according to an embodiment of the present invention;

FIG. 4 shows a schematic diagram of a signal acquisition unit of a device for realizing voice search according to an embodiment of the present invention;

FIG. 5 shows a schematic diagram of a signal acquisition unit of a device for realizing voice search according to another embodiment of the present invention;

Fig. 6 shows a schematic diagram of a device for implementing voice search according to another embodiment of the present invention;

Fig. 7 shows a schematic diagram of a device for implementing voice search according to yet another embodiment of the present invention;

FIG. 8A shows a schematic interface diagram of a home page of a browser client according to an embodiment of the present invention;

Fig. 8B shows a schematic interface of a voice search page according to an embodiment of the present invention.

detailed description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

Fig. 1 shows a flowchart of a method for voice search according to an embodiment of the present invention. As shown in Figure 1, the method includes:

Step S110, acquiring a voice signal input by a voice search user.

Step S120, sending the voice signal to the voice conversion server.

Step S130, receiving the corresponding character information returned by the speech conversion server after recognizing the speech signal.

The above step S120 and step S130 complete the interaction process between the local and the voice conversion server.

Step S140, sending a search request to the search server with the character information as the search word.

Step S150, receiving and loading and displaying the search results returned by the search server.

The above step S140 and step S150 complete the interaction process between the local and the search server.

It can be seen that the method shown in FIG. 1 completes the process of searching for the character information corresponding to the voice signal input by the user and displaying the search results to the user through the interaction with the voice conversion server and the search server. The voice signal is a complete and effective voice search solution. Compared with the traditional manual text search, it simplifies the operation process, improves the search efficiency, and provides users with a more convenient and perfect experience.

Fig. 2 shows a flowchart of a method for voice search according to another embodiment of the present invention. As shown in Figure 2, the method includes:

Step S210, acquiring tag information of voice search users.

The tag information obtained in this step can reflect the interest, hobbies, personality and needs of the voice search user. For example, the user's historical browsing data can be statistically analyzed to determine the user's label information, for example, the label can be a sports fan, an online shopper or an English lover, etc.

In step S220, according to the tag information, one or more speech-recognized keywords shared by friends of the voice search user and matched with the tag information are obtained from the voice conversion server.

The keyword in this step means that when each voice search user conducts a voice search, the voice signal input by him can be recognized by the voice conversion server to extract keywords from the character information. In the browser system, registered users can add friends to each other as in social networking sites, so as to share some browsing information.

Step S230, if there is one keyword, the keyword is used as the search word; when there are multiple keywords, one keyword is selected as the search word, and a search request is sent to the search server.

In this step, if what obtain in step 220 is a keyword, then directly take this keyword as search term, if what obtain in step 220 is a plurality of keywords, select a keyword as search term according to user's selection instruction .

Step S240, receiving and loading and displaying the search results returned by the search server.

The method shown in Figure 2 matches the tag information of the voice search user with the voice search information shared by other voice search users to obtain a voice search solution that meets the voice search user's needs, interests and personality. Further, the voice search user can Share your own voice search information so that other friend users can match, so as to realize the sharing of voice search information between friends; wherein, the voice search information shared by voice search users is based on the method shown in Figure 1, through This is achieved by the following steps:

Step S221, according to the instruction triggered by the voice search user, the voice signal input by the voice search user is acquired.

Step S222, upload the voice signal and the tag information of the voice search user to the voice conversion server, for the voice conversion server to recognize the voice signal into a keyword in text form, and then use the voice signal, the recognized keyword and the voice The search user's tag information is correspondingly saved as a shared information item.

In this step, each shared information directory stored on the voice conversion server side is shown in Table 1, including one-to-one corresponding voice signals, recognized keywords, and tag information of voice search users, used to identify each Every voice search by a voice search user.

Table 1

voice signal Key words Label Information

For example, the tag information of user A is: "novel lover", the voice signal input by user A is: "recommend a martial arts novel by Jin Yong", the tag information and voice signal of user A are uploaded to the voice conversion server, And the voice conversion server recognizes the keyword of the voice signal "recommend a Jin Yong's martial arts novel" as: "Jin Yong, martial arts novel". At this time, the shared information items saved on the voice conversion server side are shown in Table 2:

Table 2

voice signal Key words Label Information "Recommend a martial arts novel by Jin Yong" Jin Yong, martial arts novel fiction lover

User B, a friend of user A, likes literature, and its tag information is "literature". The word "martial arts novel" is used as a search term, and the search results returned by the search for "martial arts novel" are displayed to user B.

In addition, in some embodiments of the present invention, voice search users wish to download shared information items that match their own label information to the local, so that they can be viewed, searched and shared in the future. Therefore, the method shown in FIG. 2 can further Including: downloading the shared information items matching the tag information of the voice search user from the voice conversion server, and saving them locally. Using the above example, user B can also download the shared information items shown in Table 2 from the voice conversion server and store them locally.

In one embodiment of the present invention, the method shown in FIG. 1 and FIG. 2 further includes: when recognizing that the character information returned by the speech conversion server is number data conforming to a specific format, displaying the loading entry of the corresponding operation of the number data. Among them, the number data in a specific format can be: data such as phone numbers, WeChat public numbers, QQ numbers, etc. Or the loading entry for sending information; or, identifying the character information as a WeChat public account, indicating that the user may have a need to follow the public account, and then showing the user the loading entry for following the public account; or, identifying the character information as a QQ account, indicating that the user If there is a need to add the QQ number, the loading entry for adding the QQ number will be displayed to the user; and so on, they will not be listed one by one. This solution further optimizes the voice search process, making the voice search more in line with the user's search habits.

In some embodiments of the present invention, the user performs a voice search on the number data in a specific format because he wants to access the webpage information related to the number data. In this case, the method shown in FIG. 1 further includes: when recognizing the character When the information is number data conforming to a specific format, the e-commerce web page information corresponding to the number data returned by the search server can also be loaded, and an entry for interactive operation with the e-commerce web page can be provided. For example, when it is the hotline number of a courier company, provide the website entrance of the courier company so that users can perform operations such as courier inquiries.

In an embodiment of the present invention, the voice signal acquisition process of the methods shown in FIG. 1 and FIG. 2 may be: acquire call recording data of the mobile terminal, and edit the call recording data to obtain a voice signal for voice search.

In one embodiment of the present invention, the voice signal acquisition process of step S110 of the method shown in FIG. 1 may also be: add a voice recognition module to recognize and record the voice of the voice search user, and mark it as a voice search user , and record the voice data shared or sent by friends manually or after machine learning recognition, and mark it as the voice data of corresponding friends; edit the voice data of voice search users or their friends, A voice signal for voice search is obtained.

In the above two embodiments, it is not necessary to input voice through the microphone on site, but to edit the original saved voice data to obtain the voice signal for searching. The originally saved voice data may be the call recording data of the mobile terminal, or the voice data of a certain user who has been identified and identified.

In one embodiment of the present invention, when the method shown in Fig. 1 and Fig. 2 searches the returned character information, it may further include: performing semantic recognition on the returned character information, and determining the classification of the character information as the search term; Then send a search request to the search server of the corresponding category. For example, the character information returned by the speech conversion server is "News of the APEC meeting", and semantic recognition is performed on it, and it is determined that the character information is classified as news as a search term, and "APEC meeting" is used as the search term to search for the news category. The search server sends a search request. It can be seen that when the recognized character information belongs to categories such as pictures, music, videos, and maps as search words, search requests are sent to the picture search server, music search server, video search server, and map search server respectively. The search process is the same as above. This will not be repeated here. This solution makes the voice search more directional, the search result is more accurate, and meets the needs of users.

In one embodiment of the present invention, the process of obtaining the voice signal input by the voice search user in the method shown in Fig. 1 and Fig. 2 is to obtain the user's voice signal through a microphone on the spot, which specifically includes:

Step S111 , displaying a voice search icon on the home page of the browser client; when the voice search icon is clicked, jump to a voice search page including a voice search control.

The voice search page in this step is an interactive interface when the user conducts voice search.

Step S112, in response to the event that the voice search control is activated, start capturing voice signals with the microphone of the mobile device where the browser client is located.

Step S113, in response to the event that the voice search control is turned off, stop capturing the voice signal, and obtain the input voice signal.

Displaying the voice search icon on the homepage of the browser client in this embodiment may be: displaying a microphone icon at the end of the address bar of the browser client; the event that the voice search control in step S112 is activated may be: the voice search control starts to be Touch; the event that the voice search control is turned off in step S113 is: the voice search control ends being touched.

FIG. 8A shows a schematic interface of a home page of a browser client according to an embodiment of the present invention, and FIG. 8B shows a schematic interface of a voice search page according to an embodiment of the present invention. Step S111 displays a microphone icon at the end of the address bar as shown in FIG. 8A. When the microphone icon is clicked, it jumps to a voice search page containing a voice search control as shown in FIG. 8B. In this embodiment, the voice The search control is also a microphone icon. In response to the start of the voice search control being touched, the microphone of the mobile device where the browser client is located begins to capture voice signals; in response to the end of the voice search control being touched, stop capturing voice signals and obtain input voice signal.

In an embodiment of the present invention, the above step S111 may further include: displaying N hot search words on the voice search page; wherein, the N hot search words are the top search words obtained from statistics within a statistical period N search terms, where N is a natural number; or, display search prompt information on the voice search page to prompt users how to perform voice search. As shown in Figure 8B, the voice search prompt unit 530 displays seven hot search terms such as "how is the weather tomorrow" and "how to make braised pork" on the voice search page, and distinguishes the search terms of each search term by font size ranking.

On the premise of displaying N hot search words on the voice search page as described in the above embodiment, in one embodiment of the present invention, in response to the event that the hot search words on the voice search page are clicked, jump to the The search result page corresponding to the hot search term. For example, in the voice search page shown in Figure 8B, in response to the event that the hot search word "what's the weather tomorrow" is clicked, jump to the search result page of the weather forecast corresponding to the hot search word; and load the display to the user The search results page. This solution recommends the recent hot search words to the user, and jumps to the corresponding search page when the user clicks the hot search word, which is in line with the user's search habits.

In an embodiment of the present invention, the above step S111 may further include: displaying a page closing control on the voice search page, and when the page closing control is triggered, closing the voice search page and returning to the homepage of the browser client. As shown in FIG. 8B , a page closing control is displayed in the lower right corner of the voice search page. When the page closing control is triggered, the voice search page is closed and the browser client homepage as shown in FIG. 8A is returned.

In one embodiment of the present invention, due to the influence of the external environment or other factors, the speech signal is unclear or has multiple meanings, and the following two situations may occur:

In the first case, the voice conversion server recognizes the voice signal to obtain a plurality of character information, that is, the corresponding character information returned by the receiving voice conversion server of the method shown in Fig. 1 and Fig. 2 after recognizing the voice signal can be: the receiving voice conversion server The corresponding multiple character information returned after the voice signal is recognized; in this case, in order to continue the search process, the method further includes: displaying the multiple character information for the user to choose; The character information is used as a search word, and a search request is sent to the search server.

In the second case, the voice conversion server cannot recognize the voice signal, and will return information indicating that the recognition is wrong. information, informing the user that an error occurred in the voice signal recognition of this voice search.

In one embodiment of the present invention, after the method shown in Figure 1 and Figure 2 acquires the voice signal input by the voice search user, before sending the voice signal to the voice conversion server, it further includes: acquiring the network connection status of the mobile device ; If the mobile device is not connected to the network, or if the mobile device is connected to a problematic network, the information indicating that the network connection status of the mobile device is abnormal will be displayed to inform the user that the current network connection is abnormal and voice search cannot be performed; If the access is a normal network, then perform the step of sending the voice signal to the voice conversion server.

In one embodiment of the present invention, in order to better realize the human-computer interaction in the voice search process, after the voice conversion server recognizes the voice signal to obtain the corresponding character information, it can further perform semantic recognition on the character information, and Return corresponding instruction information according to the semantics after recognition; correspondingly, the method shown in Figure 1 and Figure 2 further includes: receiving the instruction information that the voice conversion server performs semantic recognition on the character information, and returns according to the semantics after recognition; according to the instruction information to perform the appropriate action. For example, the voice signal input by the user is: "I want to watch a movie". After the voice conversion server recognizes the character information corresponding to the voice signal, it returns instruction information according to the semantics of the character information: "Search for popular movies" or "Find nearby movie theaters" ", after receiving the instruction information, use "popular movies" as the search term to initiate a search to a video-type search server, or use "movie theater" as a search term to initiate a search to a map-type search server, and display the search results to the user.

Fig. 3 shows a schematic diagram of an apparatus for implementing voice search according to an embodiment of the present invention. As shown in Figure 3, the device 300 for implementing voice search includes:

The signal obtaining unit 310 is adapted to obtain a voice signal input by a voice search user.

The signal acquisition unit 310, in an embodiment of the present invention, may be the signal acquisition unit 400 shown in FIG. 4 or the signal acquisition unit 500 shown in FIG. 5, which will be described in detail below.

The voice conversion interaction unit 320 is adapted to send the voice signal to the voice conversion server; and is adapted to receive corresponding character information returned by the voice conversion server after recognizing the voice signal.

This unit is used to interact with the speech conversion server.

The search interaction unit 330 is adapted to send a search request to the search server using character information as a search word; and is adapted to receive the search result returned by the search server.

This unit is used to interact with the search server.

The display unit 340 is adapted to load and display the search results returned by the search server.

It can be seen that the device 300 for implementing voice search shown in FIG. 3 realizes the interaction with the voice conversion server and the search server through the mutual cooperation of each unit, completes the search for the character information corresponding to the voice signal input by the user, and displays to the user The process of searching results realizes a complete and effective voice search solution based on voice signals. Compared with traditional manual text search, it simplifies the operation process, improves search efficiency, and provides users with more convenient and perfect search results. experience.

In one embodiment of the present invention, the signal acquisition unit 310 of the device shown in Figure 3 is further adapted to acquire tag information of voice search users; the tag information acquired by this unit can reflect the voice search user's interest, hobbies, personality and needs . The voice conversion interaction unit 320 is further adapted to obtain from the voice conversion server according to the label information one or more keywords after speech recognition that are shared by friends of the voice search user and matched with the label information; the search interaction unit 330 is further adapted to When the voice conversion and interaction unit 320 acquires a keyword, use the keyword as a search word; when the voice conversion interaction unit 320 acquires multiple keywords, select a keyword as the search term, and send a search request to the search server and adapted to receive the search results returned by the search server; the display unit 340 is adapted to load and display the search results returned by the search server.

In this embodiment, the voice conversion and interaction unit 320 matches the tag information of the voice search user with the voice search information shared by other voice search users to obtain a voice search solution that meets the voice search user's needs, interests and personality, and further , voice search users can share their own voice search information so that other friend users can match, so that voice search information can be shared between friends; wherein, the voice search information shared by voice search users can be passed through the device shown in Figure 3 The signal acquisition unit 310 and the voice conversion interaction unit 320 cooperate to realize:

The signal acquisition unit 310 is further adapted to acquire a voice signal input by the voice search user according to an instruction triggered by the voice search user.

The voice conversion interaction unit 320 is further adapted to upload the voice signal and the label information of the voice search user to the voice conversion server, so that the voice conversion server recognizes the voice signal into a keyword in text form, and then the voice signal, recognition The generated keywords and tag information of voice search users are correspondingly saved as a shared information item.

Each shared information directory saved by this unit on the voice conversion server side is shown in Table 1, including one-to-one corresponding voice signals, recognized keywords, and tag information of voice search users, used to identify each voice search user Every voice search.

For example, user A likes food, and its label information is: "food", the voice signal input by user A is: "recommend a martial arts novel by Jin Yong", the label information and voice signal of user A are uploaded to the voice conversion server, And the voice conversion server recognizes the key word of the voice signal "recommend a martial arts novel by Jin Yong" as: "Jin Yong, martial arts novel". At this time, the shared information items saved on the voice conversion server side are shown in Table 2.

User B, a friend of user A, likes literature, and its tag information is "literature". The word "martial arts novel" is used as a search term, and the search results returned by the search for "martial arts novel" are displayed to user B.

In addition, in some embodiments of the present invention, voice search users wish to download shared information items matching their own label information to the local, which is convenient for viewing, searching and sharing in the future. Therefore, the voice conversion of the device shown in FIG. 3 The interaction unit 320 may be further adapted to download the shared information item matching the tag information of the voice search user from the voice conversion server, and save it locally. That is, using the above example, user B can also download the shared information items shown in Table 2 from the voice conversion server and store them locally.

In one embodiment of the present invention, the display unit 340 of the device shown in FIG. 3 is further adapted to display the loading entry of the corresponding operation of the number data when the search interaction unit 330 recognizes that the character information is number data conforming to a specific format. Among them, the number data in a specific format can be: phone number, WeChat public number, QQ number and other data. For example, the search interaction unit 330 recognizes the character information as a phone number, indicating that the user may have a need to make a call or send a message, then the display unit 340 shows the user the loading entry for making a call or sending information; or, the search interaction unit 330 identifies the character information as a WeChat public number, indicating that the user may have a need to pay attention to the public number, and then the display unit 340 shows the user the loading of the concerned public number. Entrance; or, the search interaction unit 330 identifies the character information as a QQ number, indicating that the user may have a need to add the QQ number, and then the display unit 340 shows the user the loading entry for adding the QQ number; and so on, no longer list them one by one, further optimization voice search solution.

In some embodiments of the present invention, the user performs a voice search on the number data in a specific format because he wants to access the web page information corresponding to the number data. In this case, when the search interaction unit 330 recognizes that the character information is the above-mentioned number data conforming to a specific format, the display unit 340 is further adapted to load the e-commerce webpage information corresponding to the number data returned by the search server, and provide information corresponding to the number data. The portal for interactive operations on e-commerce web pages.

In an embodiment of the present invention, the signal acquisition unit 310 of the device shown in FIG. 3 is further adapted to acquire call recording data of the mobile terminal, and edit the call recording data to obtain a voice signal for voice search.

In one embodiment of the present invention, the signal acquisition unit 310 of the device shown in FIG. 3 is further adapted to add a voice recognition module to recognize and record the voice search user's own voice, and mark it as the voice data of the voice search user , and record the voice data shared or sent by friends manually or after machine learning recognition, and mark it as the voice data of corresponding friends; and it is suitable for editing the voice data of voice search users or their friends, A voice signal for voice search is obtained.

In one embodiment of the present invention, the search interaction unit 330 of the device shown in FIG. 3 is further adapted to perform semantic recognition on the character information returned by the speech conversion interaction unit 320, and determine the character information as the classification of the search term; The search server for the corresponding category sends a search request. For example, the character information returned by the speech conversion server is "News of the APEC meeting", and the search interaction unit 330 performs semantic recognition on it, and determines that the search term is classified as news, and the search interaction unit 330 uses "APEC meeting" as the search term to search for the news. class of search servers to send search requests. It can be seen that when the recognized character information belongs to categories such as pictures, music, videos, maps, etc., the search process of the search interaction unit 330 is the same as above, and will not be repeated here. This solution makes the voice search more directional, the search result is more accurate, and meets the needs of users.

In one embodiment of the present invention, due to the influence of the external environment or other factors, the speech signal is unclear or has multiple meanings, and the following two situations may occur:

In the first case, the voice conversion server recognizes the voice signal to obtain a plurality of character information, that is, the voice conversion interaction unit 320 of the device shown in Figure 3 is adapted to receive the corresponding multiple character information returned by the voice conversion server after recognizing the voice signal ; In this case, in order to continue to perform the search process, the display unit 340 is further adapted to display a plurality of character information for the user to select; the search interaction unit 330 is adapted to use the character information selected by the user as the search term, Send a search request to the search server.

In the second case, the voice conversion server cannot recognize the voice signal, and will return information indicating that the recognition is wrong. The display unit 340 of the device shown in Figure 3 is further suitable for recognizing the voice signal when the voice conversion interaction unit 320 receives the voice conversion server. When the information indicating the recognition error is returned later, the information indicating the recognition error is displayed to inform the user that an error occurred in the voice signal recognition of this voice search.

Fig. 4 shows a schematic diagram of a signal acquisition unit of a device for realizing voice search according to an embodiment of the present invention. As shown in Figure 4, the signal acquisition unit 400 includes:

The voice search jumping unit 410 is adapted to display a voice search icon on the home page of the browser client; and is adapted to jump to a voice search page containing a voice search control when the voice search icon is clicked.

The voice acquisition control unit 420 is adapted to start capturing voice signals with the microphone of the mobile device where the browser client is located in response to the event that the voice search control is activated; and is adapted to stop capturing voice signals in response to the event that the voice search control is turned off , to obtain the input speech signal.

In one embodiment of the present invention, the voice search jump unit 410 of the signal acquisition unit 400 shown in FIG. 4 is suitable for displaying a microphone icon at the end of the address bar of the browser client; The acquisition control unit 420 is adapted to start capturing voice signals with the microphone of the mobile device where the browser client is located in response to the voice search control being touched; voice signal.

In one embodiment of the present invention, the voice search jump unit 410 displays a microphone icon at the end of the address bar as shown in FIG. 8A . In this embodiment, the voice search control is also a microphone icon. In response to the voice search control starting to be touched, the voice acquisition control unit 420 uses the microphone of the mobile device where the browser client is located to start capturing voice signals ; In response to the voice search control being touched, the voice acquisition control unit 420 stops capturing voice signals and obtains input voice signals.

In one embodiment of the present invention, the voice search jump unit 410 shown in FIG. 4 is further adapted to display a page close control on the voice search page, and when the page close control is triggered, close the voice search page and return to The home page of the browser client. As shown in Figure 8B, the voice search jump unit 410 displays a page close control in the lower right corner of the voice search page, when the page close control is triggered, close the voice search page and return to the browser as shown in Figure 8A The client's home page.

Fig. 5 shows a schematic diagram of a signal acquisition unit of an apparatus for realizing voice search according to another embodiment of the present invention. As shown in Figure 5, the signal acquisition unit 500 includes: a voice search jump unit 510, a voice acquisition control unit 520, and a voice search prompt unit 530; The voice search jumping unit 410 shown is the same as the voice acquisition control unit 420 , and will not be repeated here.

The voice search prompt unit 530 is suitable for displaying N hot search words on the voice search page; wherein, the N hot search words are the top N search words obtained from statistics within a statistical period, and N is a natural number ; Or, it is suitable for displaying search prompt information on the voice search page, which is used to prompt the user how to perform voice search. As shown in Figure 8B, the voice search prompt unit 530 displays seven hot search terms such as "how is the weather tomorrow" and "how to make braised pork" on the voice search page, and distinguishes the search terms of each search term by font size ranking.

On the premise that the signal acquisition unit 500 shown in FIG. 5 displays N hot search words on the voice search page, in one embodiment of the present invention, the search interaction unit 330 of the device shown in FIG. 3 is further adapted to respond to When a hot search word on the voice search page is clicked, jump to the search result page corresponding to the hot search word; the display unit 340 is further adapted to load and display the search result page corresponding to the hot search word. For example, in the voice search page shown in FIG. 8B , in response to the event that the hot search word "what's the weather tomorrow" is clicked, the search interaction unit 330 jumps to the search result page of the weather forecast corresponding to the hot search word; the display unit 340 loads and displays the search result page to the user. This solution recommends the recent hot search words to the user, and jumps to the corresponding search page when the user clicks the hot search word, which is in line with the user's search habits.

Fig. 6 shows a schematic diagram of an apparatus for implementing voice search according to another embodiment of the present invention. As shown in Figure 6, the device 600 for implementing voice search includes: a signal acquisition unit 610, a network detection unit 620, a voice conversion interaction unit 630, a search interaction unit 640, and a display unit 650; wherein, the signal acquisition unit 610, the search interaction unit 640 are respectively the same as the signal acquisition unit 310 and the search interaction unit 330 of the device shown in FIG. 3; and in one embodiment of the present invention, the signal acquisition unit 610 may be the signal acquisition unit 400 as shown in FIG. The signal acquisition unit 500 shown will not be described in detail here.

The network detection unit 620 is adapted to acquire the network connection status of the mobile device before the voice conversion interaction unit 630 sends the voice signal to the voice conversion server.

The voice conversion interaction unit 630 is further adapted to send a voice signal to the voice conversion server when the network detection unit 620 detects that the mobile device is connected to a normal network.

The display unit 650 is further adapted to display a message indicating that the network connection status of the mobile device is abnormal when the network detection unit 620 detects that the mobile device has access to a problematic network.

Fig. 7 shows a schematic diagram of an apparatus for implementing voice search according to yet another embodiment of the present invention. As shown in Figure 7, the device 700 for implementing voice search includes: a signal acquisition unit 710, a voice conversion interaction unit 720, a search interaction unit 730, a presentation unit 740, and an instruction execution unit 750; wherein, the signal acquisition unit 710, the search interaction unit 730 and the display unit 740 are respectively the same as the signal acquisition unit 310, the search interaction unit 330, and the display unit 340 of the device shown in Figure 3; and in one embodiment of the present invention, the signal acquisition unit 710 may be as shown in Figure 4 The signal acquisition unit 400 or the signal acquisition unit 500 shown in FIG. 5 will not be described in detail here.

The voice conversion interaction unit 720 is further adapted to receive instruction information that the voice conversion server performs semantic recognition on the character information and returns according to the recognized semantics;

The instruction executing unit 750 is adapted to execute corresponding operations according to the instruction information.

According to the instruction information returned by the voice conversion server, this unit can invoke the relevant service components or third-party application programs in the terminal, and execute the corresponding operation of the instruction information. For example, the signal acquisition unit 710 acquires the voice signal input by the user as: "I want to watch a movie". After the voice conversion interaction unit 720 sends the voice signal to the voice conversion server, it receives the character information corresponding to the voice signal from the voice conversion server. The instruction information returned by semantics is: "search for popular movies" or "find nearby movie theaters", and the instruction execution unit 750 can invoke the search interaction unit 730 to initiate a search to a video-type search server with "hot movies" as the search term; or , the instruction execution unit 750 may also invoke the positioning component in the terminal to search for nearby "movie theaters" and display the search results to the user.

An embodiment of the present invention also discloses a browser client for implementing voice search, which includes the device for implementing voice search as described in any of the above-mentioned embodiments.

In summary, the technical solution provided by the present invention completes the process of searching the character information corresponding to the voice signal input by the user and displaying the search results to the user through the interaction with the voice conversion server and the search server. A complete and effective voice search solution has been formed. Compared with the traditional manual search, it simplifies the operation process and improves the search efficiency. Further, through the matching of the voice search user's label information, the recommended display of hot search words, and the The semantic recognition of voice signals and the detection of the current network of voice search expand the interactive boundary of voice search, optimize the process of voice search, make the voice search of this solution more in line with the user's search habits, and provide users with more convenient , perfect experience.

It should be noted:

The algorithms and displays presented herein are not inherently related to any particular computer, virtual appliance, or other device. Various general purpose devices can also be used with the teachings based on this. The structure required to construct such an apparatus will be apparent from the foregoing description. Furthermore, the present invention is not specific to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in a device for implementing voice search according to an embodiment of the present invention . The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

The invention discloses A1. A method for implementing voice search, the method comprising: acquiring a voice signal input by a voice search user; sending the voice signal to a voice conversion server; receiving the voice conversion server after recognizing the voice signal Returning the corresponding character information; using the character information as a search term, sending a search request to the search server; receiving, loading and displaying the search result returned by the search server.

A2. The method as described in A1, wherein, the method further includes: obtaining the tag information of the voice search user; obtaining from the voice conversion server according to the tag information the voice search user’s friends who match the tag information One or more keywords after speech recognition; when it is a keyword, use this keyword as a search term, when it is multiple keywords, select a keyword as a search term, and send a search request to the search server; receive and loading displays the search results returned by the search server.

A3. The method according to A2, wherein the method further includes: acquiring a voice signal input by the voice search user according to an instruction triggered by the voice search user; combining the voice signal with the tag information of the voice search user Upload to the voice conversion server together, after the voice conversion server recognizes the voice signal into a keyword in text form, the voice signal, the recognized keyword and the label information of the voice search user are correspondingly stored as a share information entry.

A4. The method as described in A3, wherein the method further includes: downloading from the voice conversion server the shared information item matching the tag information of the voice search user, and saving it locally.

A5. The method as described in A1, which further includes: when the character information is identified as number data conforming to a specific format, displaying the loading entry of the corresponding operation of the number data.

A6, the method as described in A5, when identifying the character information as number data conforming to a specific format, also load the e-commerce web page information corresponding to the number data returned by the search server, and provide interactive operation with the e-commerce web page entrance.

A7. The method as described in A1, further comprising: acquiring call recording data of the mobile terminal, and editing the call recording data to obtain a voice signal for voice search.

A8, the method as described in A7, the method further includes: adding a voice recognition module, recording the voice of the voice search user after recognition, and marking it as the voice data of the voice search user, and sharing it with friends Or the voice data sent is manually recognized or recorded after machine learning recognition, and marked as the voice data of the corresponding friend; the voice data of the voice search user or the voice data of the friend is edited to obtain the voice data used for voice search. voice signal.

A9, the method as described in A1, the method further includes: performing semantic recognition on the character information, and determining the classification of the character information as a search word;

The sending the search request to the search server includes: sending the search request to the search server of the corresponding category.

A10, the method as described in A1, said acquiring the input voice signal comprises: displaying a voice search icon on the home page of the browser client; when the voice search icon is clicked, jumping to a voice search page containing a voice search control ; In response to the event that the voice search control is started, use the microphone of the mobile device where the browser client is located to start capturing the voice signal; in response to the event that the voice search control is closed, stop capturing the voice signal and obtain the input voice signal .

A11, the method described in A10, displaying the voice search icon in the home page of the browser client includes: displaying the microphone icon at the end of the address bar of the browser client;

The event that the voice search control is started is: the voice search control starts to be touched;

The event that the voice search control is turned off is: the voice search control ends being touched.

A12, the method as described in A10, the method further includes: displaying N hot search words on the voice search page; wherein, the N hot search words are search rankings obtained by statistics within a statistical period The first N search terms, where N is a natural number; or, displaying search prompt information on the voice search page to prompt the user how to conduct a voice search.

A13, the method as described in A10, wherein, the method further comprises:

A page close control is displayed on the voice search page, and when the page close control is triggered, the voice search page is closed and the home page of the browser client is returned.

A14. The method according to A12, further comprising: jumping to a search result page corresponding to the hot search word in response to the event that the hot search word on the voice search page is clicked.

A15. The method according to any one of A1-A14, wherein the corresponding character information returned by the receiving speech conversion server after recognizing the speech signal includes: receiving the speech conversion server recognizing the speech signal The corresponding multiple character information returned after;

Then the method further includes: displaying the plurality of character information for selection by the user;

The using the character information as the search term is to use the character information selected by the user as the search term.

A16. The method according to any one of A1-A14, wherein, before sending the voice signal to the voice conversion server, the method further includes: acquiring the network connection status of the mobile device;

If the mobile device is not connected to the network, or the mobile device is connected to a problematic network, display information indicating that the network connection status of the mobile device is abnormal;

If the mobile device is connected to a normal network, the step of sending the voice signal to the voice conversion server is performed.

A17. The method according to any one of A1-A14, wherein the method further comprises:

When receiving the information indicating the recognition error returned by the speech conversion server after recognizing the voice signal, the information indicating the recognition error is displayed.

A18. The method according to any one of A1-A14, wherein the method further comprises:

receiving the voice conversion server performing semantic recognition on the character information and returning instruction information according to the recognized semantics;

Perform corresponding operations according to the instruction information.

The present invention also discloses B19, a device for realizing voice search, wherein the device includes:

A signal acquisition unit adapted to acquire a voice signal input by a voice search user;

The voice conversion interaction unit is adapted to send the voice signal to the voice conversion server; and is adapted to receive the corresponding character information returned by the voice conversion server after recognizing the voice signal;

The search interaction unit is adapted to use the character information as a search word to send a search request to a search server; and is adapted to receive search results returned by the search server;

The display unit is adapted to load and display the search results returned by the search server.

B20. The device according to B19, wherein the signal acquisition unit is further adapted to acquire tag information of the voice search user;

The voice conversion interaction unit is further adapted to obtain from the voice conversion server according to the tag information one or more speech-recognized keywords shared by friends of the voice search user and matched with the tag information;

The search interaction unit is adapted to use a keyword as a search word when the speech conversion interaction unit obtains a keyword, and selects a keyword as a search word when the speech conversion interaction unit obtains multiple keywords. word, send a search request to the search server; and be adapted to receive the search result returned by the search server;

The display unit is adapted to load and display the search results returned by the search server.

B21. The device of B20, wherein,

The signal acquisition unit is further adapted to acquire a voice signal input by the voice search user according to an instruction triggered by the voice search user;

The voice conversion interaction unit is further adapted to upload the voice signal and the tag information of the voice search user to the voice conversion server, so that after the voice conversion server recognizes the voice signal into a keyword in text form, the The voice signal, the recognized keyword, and the tag information of the voice search user are correspondingly stored as a shared information item.

B22. The device of B21, wherein,

The voice conversion interaction unit is further adapted to download the shared information items matching the voice search user's tag information from the voice conversion server, and store them locally.

B23. The device of B19, wherein,

The display unit is further adapted to display the loading entry of the corresponding operation of the number data when the search interaction unit recognizes that the character information is number data conforming to a specific format.

B24. The device of B23, wherein,

The display unit is also adapted to load the e-commerce web page information corresponding to the number data returned by the search server when the search interaction unit recognizes that the character information is number data conforming to a specific format, and provide information related to the e-commerce web page The entry point for interactive operations.

B25. The device of B19, wherein,

The signal acquisition unit is further adapted to acquire call recording data of the mobile terminal, and edit the call recording data to obtain a voice signal for voice search.

B26. The device of B25, wherein,

The signal acquisition unit is further adapted to add a voice recognition module to recognize and record the voice search user's own voice, and mark it as the voice data of the voice search user, as well as the voice shared or sent by friends The data is recorded after manual recognition or machine learning recognition, and marked as the voice data of the corresponding friend; and it is suitable for editing the voice data of the voice search user or the voice data of his friend to obtain the voice used for voice search Signal.

B27. The device of B19, wherein,

The search interaction unit is further adapted to perform semantic recognition on the character information, to determine the classification of the character information as a search term; and to send a search request to a search server of a corresponding classification.

B28. The device as described in B19, wherein the signal acquisition unit includes: a voice search jump unit and a voice acquisition control unit;

The voice search jump unit is suitable for displaying a voice search icon on the homepage of the browser client; when the voice search icon is clicked, it jumps to a voice search page containing a voice search control;

The voice acquisition control unit is adapted to respond to the event that the voice search control is started, using the microphone of the mobile device where the browser client is located to start capturing voice signals; and is adapted to respond to the event that the voice search control is turned off , stop capturing the voice signal and get the input voice signal.

B29. The device of B28, wherein,

The voice search jump unit is adapted to display a microphone icon at the end of the address bar of the browser client;

The voice acquisition control unit is adapted to start capturing voice signals with the microphone of the mobile device where the browser client is located in response to the voice search control being touched; and is adapted to stop being touched in response to the voice search control ending. Capture the speech signal to obtain the input speech signal.

B30. The device according to B28, wherein the voice signal acquisition unit further includes: a voice search prompt unit;

The voice search prompt unit is adapted to display N hot search words on the voice search page; wherein, the N hot search words are the top N search terms obtained from statistics within a statistical period words, N is a natural number; or, it is suitable for displaying search prompt information on the voice search page to prompt the user how to perform voice search.

B31. The device of B28, wherein,

The voice search jump unit is further adapted to display a page closing control on the voice search page, and when the page closing control is triggered, close the voice search page and return to the home page of the browser client.

B32. The device of B30, wherein,

The search interaction unit is further adapted to jump to the search result page corresponding to the hot search word in response to the event that the hot search word on the voice search page is clicked;

The display unit is further adapted to load and display a search result page corresponding to the hot search word.

B33. The device of any one of B19-B32, wherein,

The voice conversion interaction unit is adapted to receive corresponding multiple character information returned after the voice conversion server recognizes the voice signal;

The display unit is further adapted to display the plurality of character information for selection by the user;

The search interaction unit is adapted to send a search request to a search server using character information selected by a user as a search term.

B34. The device according to any one of B19-B32, wherein the device further includes: a network detection unit;

The network detection unit is adapted to obtain the network connection status of the mobile device before the voice conversion interaction unit sends the voice signal to the voice conversion server;

The voice conversion interaction unit is further adapted to send the voice signal to a voice conversion server when the network detection unit detects that the mobile device is connected to a normal network;

The display unit is further adapted to display a message indicating that the network connection status of the mobile device is abnormal when the network detection unit detects that the mobile device has access to a problematic network.

B35. The device of any one of B19-B32, wherein,

The presentation unit is further adapted to display the information indicating an error in recognition when the voice conversion interaction unit receives information indicating an error in recognition returned by the voice conversion server after recognizing the voice signal.

B36. The device according to any one of B19-B32, wherein the device further comprises: an instruction execution unit;

The voice conversion interaction unit is further adapted to receive the voice conversion server performing semantic recognition on the character information and returning instruction information according to the recognized semantics;

The instruction executing unit is adapted to execute corresponding operations according to the instruction information.

The present invention also discloses C37, a browser client for realizing voice search, including the device for realizing voice search according to any one of the above items.

Claims (35)

1. A method for realizing voice search, wherein the method comprises: Obtain the voice signal input by the voice search user; sending the voice signal to a voice conversion server; Receiving the corresponding character information returned by the speech conversion server after recognizing the speech signal; Using the character information as a search word, send a search request to the search server; receiving and loading and displaying the search results returned by the search server; The method further includes: Obtain tag information of the voice search user; Acquiring from the voice conversion server according to the tag information one or more keywords after speech recognition shared by friends of the voice search user and matched with the tag information; When it is a keyword, the keyword is used as the search term; when there are multiple keywords, one keyword is selected as the search term, and a search request is sent to the search server; Receiving and loading displaying the search results returned by the search server. 2. The method of claim 1, wherein the method further comprises: Acquiring a voice signal input by the voice search user according to an instruction triggered by the voice search user; The voice signal is uploaded to the voice conversion server together with the tag information of the voice search user, and after the voice conversion server recognizes the voice signal into a keyword in text form, the voice signal, the recognized keyword and The tag information of the voice search user is correspondingly stored as a shared information item. 3. The method of claim 2, wherein the method further comprises: The shared information item matching the tag information of the voice search user is downloaded from the voice conversion server and stored locally. 4. The method of claim 1, wherein the method further comprises: When the character information is identified as number data conforming to a specific format, the loading entry of the corresponding operation of the number data is displayed. 5. The method of claim 4, wherein, When the character information is identified as number data conforming to a specific format, the e-commerce web page information corresponding to the number data returned by the search server is also loaded, and an entry for interactive operation with the e-commerce web page is provided. 6. The method of claim 1, wherein the method further comprises: The call recording data of the mobile terminal is obtained, and the call recording data is edited to obtain a voice signal for voice search. 7. The method of claim 6, wherein the method further comprises: Add a voice recognition module to recognize and record the voice search user's own voice, and mark it as the voice data of the voice search user, and perform manual recognition or machine learning recognition on the voice data shared or sent by friends After recording, mark it as the voice data of the corresponding friend; Edit the voice data of the voice search user or the voice data of his friend to obtain a voice signal for voice search. 8. The method according to claim 1, wherein the method further comprises: performing semantic recognition on the character information, and determining the classification of the character information as a search word; The sending the search request to the search server includes: sending the search request to the search server of the corresponding category. 9. The method according to claim 1, wherein said obtaining the voice signal input by the voice search user comprises: Display the voice search icon on the home page of the browser client; when the voice search icon is clicked, jump to the voice search page containing the voice search control; In response to the event that the voice search control is started, utilize the microphone of the mobile device where the browser client is located to start capturing voice signals; In response to the event that the voice search control is turned off, stop capturing voice signals and obtain input voice signals. 10. The method of claim 9, wherein, Displaying the voice search icon on the home page of the browser client includes: displaying a microphone icon at the end of the address bar of the browser client; The event that the voice search control is started is: the voice search control starts to be touched; The event that the voice search control is turned off is: the voice search control ends being touched. 11. The method of claim 9, wherein the method further comprises: N hot search words are displayed on the voice search page; wherein, the N hot search words are the top N search words obtained by statistics within a statistical period, and N is a natural number; or, Displaying search prompt information on the voice search page for prompting the user how to conduct a voice search. 12. The method of claim 9, wherein the method further comprises: A page close control is displayed on the voice search page, and when the page close control is triggered, the voice search page is closed and the home page of the browser client is returned. 13. The method of claim 11, wherein the method further comprises: In response to an event that a hot search word on the voice search page is clicked, jump to a search result page corresponding to the hot search word. 14. The method according to any one of claims 1-13, wherein, receiving the corresponding character information returned by the voice conversion server after recognizing the voice signal comprises: receiving the voice conversion server from the voice signal Corresponding multiple character information returned after recognition; Then the method further includes: displaying the plurality of character information for selection by the user; The using the character information as the search term is to use the character information selected by the user as the search term. 15. The method according to any one of claims 1-13, wherein, before sending the voice signal to the voice conversion server, the method further comprises: Obtain the network connection status of the mobile device; If the mobile device is not connected to the network, or the mobile device is connected to a problematic network, display information indicating that the network connection status of the mobile device is abnormal; If the mobile device is connected to a normal network, the step of sending the voice signal to the voice conversion server is performed. 16. The method of any one of claims 1-13, wherein the method further comprises: When receiving the information indicating the recognition error returned by the speech conversion server after recognizing the voice signal, the information indicating the recognition error is displayed. 17. The method of any one of claims 1-13, wherein the method further comprises: receiving the voice conversion server performing semantic recognition on the character information and returning instruction information according to the recognized semantics; Perform corresponding operations according to the instruction information. 18. A device for voice search, wherein the device comprises: A signal acquisition unit adapted to acquire a voice signal input by a voice search user; The voice conversion interaction unit is adapted to send the voice signal to the voice conversion server; and is adapted to receive the corresponding character information returned by the voice conversion server after recognizing the voice signal; The search interaction unit is adapted to use the character information as a search word to send a search request to a search server; and is adapted to receive search results returned by the search server; a display unit adapted to load and display the search results returned by the search server; The signal acquisition unit is further adapted to acquire tag information of the voice search user; The voice conversion interaction unit is further adapted to obtain from the voice conversion server according to the tag information one or more speech-recognized keywords shared by friends of the voice search user and matched with the tag information; The search interaction unit is adapted to use a keyword as a search word when the speech conversion interaction unit obtains a keyword, and selects a keyword as a search word when the speech conversion interaction unit obtains multiple keywords. word, send a search request to the search server; and be adapted to receive the search result returned by the search server; The display unit is adapted to load and display the search results returned by the search server. 19. The apparatus of claim 18, wherein, The signal acquisition unit is further adapted to acquire a voice signal input by the voice search user according to an instruction triggered by the voice search user; The voice conversion interaction unit is further adapted to upload the voice signal and the tag information of the voice search user to the voice conversion server, so that after the voice conversion server recognizes the voice signal into a keyword in text form, the The voice signal, the recognized keyword, and the tag information of the voice search user are correspondingly stored as a shared information item. 20. The apparatus of claim 19, wherein, The voice conversion interaction unit is further adapted to download the shared information items matching the voice search user's tag information from the voice conversion server, and store them locally. 21. The apparatus of claim 18, wherein, The display unit is further adapted to display the loading entry of the corresponding operation of the number data when the search interaction unit recognizes that the character information is number data conforming to a specific format. 22. The apparatus of claim 21, wherein, The display unit is also adapted to load the e-commerce web page information corresponding to the number data returned by the search server when the search interaction unit recognizes that the character information is number data conforming to a specific format, and provide information related to the e-commerce web page The entry point for interactive operations. 23. The apparatus of claim 18, wherein, The signal acquisition unit is further adapted to acquire call recording data of the mobile terminal, and edit the call recording data to obtain a voice signal for voice search. 24. The apparatus of claim 23, wherein, The signal acquisition unit is further adapted to add a voice recognition module to recognize and record the voice search user's own voice, and mark it as the voice data of the voice search user, as well as the voice shared or sent by friends The data is recorded after manual recognition or machine learning recognition, and marked as the voice data of the corresponding friend; and it is suitable for editing the voice data of the voice search user or the voice data of his friend to obtain the voice used for voice search Signal. 25. The apparatus of claim 18, wherein, The search interaction unit is further adapted to perform semantic recognition on the character information, to determine the classification of the character information as a search term; and to send a search request to a search server of a corresponding classification. 26. The device according to claim 18, wherein the signal acquisition unit comprises: a voice search jump unit and a voice acquisition control unit; The voice search jump unit is suitable for displaying a voice search icon on the homepage of the browser client; when the voice search icon is clicked, it jumps to a voice search page containing a voice search control; The voice acquisition control unit is adapted to respond to the event that the voice search control is started, using the microphone of the mobile device where the browser client is located to start capturing voice signals; and is adapted to respond to the event that the voice search control is turned off , stop capturing the voice signal and get the input voice signal. 27. The apparatus of claim 26, wherein, The voice search jump unit is adapted to display a microphone icon at the end of the address bar of the browser client; The voice acquisition control unit is adapted to start capturing voice signals with the microphone of the mobile device where the browser client is located in response to the voice search control being touched; and is adapted to stop being touched in response to the voice search control ending. Capture the speech signal to obtain the input speech signal. 28. The device according to claim 26, wherein the voice signal acquisition unit further comprises: a voice search prompt unit; The voice search prompt unit is adapted to display N hot search words on the voice search page; wherein, the N hot search words are the top N search terms obtained from statistics within a statistical period words, N is a natural number; or, it is suitable for displaying search prompt information on the voice search page to prompt the user how to perform voice search. 29. The apparatus of claim 26, wherein, The voice search jump unit is further adapted to display a page closing control on the voice search page, and when the page closing control is triggered, close the voice search page and return to the home page of the browser client. 30. The apparatus of claim 28, wherein, The search interaction unit is further adapted to jump to the search result page corresponding to the hot search word in response to the event that the hot search word on the voice search page is clicked; The display unit is further adapted to load and display a search result page corresponding to the hot search term. 31. The device of any one of claims 18-30, wherein, The voice conversion interaction unit is adapted to receive corresponding multiple character information returned after the voice conversion server recognizes the voice signal; The display unit is further adapted to display the plurality of character information for selection by the user; The search interaction unit is adapted to send a search request to a search server using character information selected by a user as a search word. 32. The device according to any one of claims 18-30, wherein the device further comprises: a network detection unit; The network detection unit is adapted to obtain the network connection status of the mobile device before the voice conversion interaction unit sends the voice signal to the voice conversion server; The voice conversion interaction unit is further adapted to send the voice signal to a voice conversion server when the network detection unit detects that the mobile device is connected to a normal network; The display unit is further adapted to display a message indicating that the network connection status of the mobile device is abnormal when the network detection unit detects that the mobile device has access to a problematic network. 33. The device of any one of claims 18-30, wherein, The presentation unit is further adapted to display the information indicating an error in recognition when the voice conversion interaction unit receives information indicating an error in recognition returned by the voice conversion server after recognizing the voice signal. 34. The device according to any one of claims 18-30, wherein the device further comprises: an instruction execution unit; The voice conversion interaction unit is further adapted to receive the voice conversion server performing semantic recognition on the character information and returning instruction information according to the recognized semantics; The instruction executing unit is adapted to execute corresponding operations according to the instruction information. 35. A browser client for implementing voice search, comprising the device for implementing voice search according to any one of claims 18-34.