CN114117020A - Multi-channel conversation continuing method and system - Google Patents
Multi-channel conversation continuing method and system Download PDFInfo
- Publication number
- CN114117020A CN114117020A CN202210068771.9A CN202210068771A CN114117020A CN 114117020 A CN114117020 A CN 114117020A CN 202210068771 A CN202210068771 A CN 202210068771A CN 114117020 A CN114117020 A CN 114117020A
- Authority
- CN
- China
- Prior art keywords
- conversation
- user
- text
- progress
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- User Interface Of Digital Computer (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to a multi-channel conversation continuing method, which comprises the following steps: recording the voice conversation progress when a user carries out voice conversation; when the voice conversation is detected to meet the switching condition, generating a text conversation interface, and sending the text conversation interface to a user; and taking the voice conversation progress as a text conversation progress, applying the text conversation progress to a text conversation interface, and enabling a user to switch to the text conversation in the text conversation interface and continue the voice conversation progress. The method switches the user to the text conversation mode when the voice conversation identification is inaccurate or can not be identified through the continuous conversation mode, thereby ensuring the identification accuracy; the conversation progress of the user is kept during switching, and the conversation can be continued from the interrupted position, so that the use experience and the efficiency of the user are greatly improved.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a multi-channel conversation continuing method and a multi-channel conversation continuing system.
Background
With the development of technologies such as artificial intelligence and semantic analysis, speech and text conversation robots with automatic conversation functions are increasingly applied to the field of customer service or data collection. However, the existing automatic dialogue function has certain defects in both voice dialogue and text dialogue, and the voice dialogue has the serious condition that special characters are not accurately identified or can not be completely identified, is easily influenced by environmental noise and dialect, and is difficult to use when a large amount of data information is interacted with a user; the text conversation has low communication efficiency with the user, and the user is required to input a large amount of characters.
There is therefore a need for a method that combines the advantages of voice dialogs and text dialogs and remedies their respective deficiencies so that the automatic dialogs by the user can be both efficient and accurate.
Disclosure of Invention
Based on the above-mentioned shortcomings and drawbacks of the prior art, it is an object of the present invention to at least solve one or more of the above-mentioned problems of the prior art, in other words, to provide a multi-channel dialog connecting method and system that meets one or more of the above-mentioned needs.
In order to achieve the purpose, the invention adopts the following technical scheme:
a multi-channel dialog continuation method comprises the following steps:
recording the voice conversation progress when a user carries out voice conversation;
when the voice conversation is detected to meet the switching condition, generating a text conversation interface, and sending the text conversation interface to a user; and taking the voice conversation progress as a text conversation progress, applying the text conversation progress to a text conversation interface, and enabling a user to switch to the text conversation in the text conversation interface and continue the voice conversation progress.
As a preferred scheme, sending the text dialog interface to the user specifically includes:
generating a text conversation interface on a webpage;
and sending the website link of the webpage to the user, and opening the webpage containing the text conversation interface after the user clicks the website link.
As a further preferred scheme, sending the website link of the webpage to the user specifically includes:
converting the link of the webpage into a short link;
and sending the short link to the user in a short message form.
As a further preferable aspect, the method further includes:
allocating a dialogue ID for each dialogue, and constructing a website link by using the dialogue ID;
and determining the continued conversation according to the conversation ID contained in the website link accessed by the user.
As a further preferable aspect, the method further includes:
adding a current timestamp in the website link when the website link is constructed;
and setting expiration time, judging whether the dialogue is expired or not according to the timestamp and the expiration time when the user opens the website link, and reminding the user that the dialogue is expired if the dialogue is expired.
As a preferred scheme, when detecting that the voice conversation meets the switching condition, soliciting a switching confirmation from a user, and if the user confirms, switching; if the user refuses or the timeout is not confirmed, the voice conversation is continuously maintained.
As a preferred scheme, switching is started when the voice conversation is detected to meet one or more switching conditions; the switching conditions include:
the voice content of the user is difficult to recognize;
a user inquires or inputs data;
the user actively requests to switch text conversations.
Preferably, the voice conversation progress and the text conversation progress include:
a session start time;
session history information;
current session node information;
data collected in a conversation.
Preferably, the method further comprises: and recording the text conversation progress when the user starts the text conversation, and switching to the voice conversation and continuing the text conversation progress by taking the text conversation progress as the voice conversation progress when detecting that the text conversation meets the switching condition.
In another aspect, the present invention further provides a multi-channel dialog continuation system, which applies any one of the above methods, and the system includes:
the voice conversation server is used for carrying out voice conversation with the user;
the text conversation server is used for generating a text conversation interface and carrying out text conversation with the user;
the user terminal is used for carrying out conversation with the voice conversation server and the text conversation server by a user;
the conversation progress database is used for storing the current voice conversation progress and the continuous text conversation progress of each conversation;
and the switching server is used for detecting the switching condition, calling the conversation progress in the conversation progress database and controlling the conversation of the user terminal to be switched between the voice conversation server and the text conversation server.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method switches the user to the text conversation mode when the voice conversation identification is inaccurate or can not be identified through the continuous conversation mode, thereby ensuring the identification accuracy;
(2) the conversation progress of the user is kept during switching, and the conversation can be continued from the interrupted position, so that the use experience and the efficiency of the user are greatly improved;
(3) when the user needs to carry out the conversation of complex data, the user can be ensured to conveniently and accurately input a large amount of data and view the result of the large amount of data by switching to the text conversation.
Drawings
FIG. 1 is a flow chart of soliciting a handoff confirmation from a user in an embodiment of the present invention;
fig. 2 is a flowchart of a user continuing a dialog after opening a web page according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention, the following description will explain the embodiments of the present invention with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
Example (b): in the multi-channel conversation connection method of the embodiment, the voice conversation progress is recorded when the user performs voice conversation with the voice conversation robot, and whether the voice conversation meets the switching condition or not is detected in the conversation process. And if the voice conversation is detected to meet the switching conditions, such as poor current voice quality, serious dialect unrecognizable by the user and the like, switching the user to the text conversation, and using the voice conversation progress recorded in the voice conversation as a starting point of the text conversation to continue the conversation progress of the user to the text conversation.
More specifically exemplified as follows, the method comprises the steps of:
when a voice conversation of a user is connected, a conversation ID, namely a session ID, is generated for the conversation, the session ID is used as a credential for accessing the session data and points to the session data, the conversation progress of the voice conversation is stored in the session data, and the progress of the voice conversation can be obtained by inquiring the session data. Further, session data may be stored using a redis storage system.
And in the voice conversation process, detecting and judging whether the conversation needs to be switched to the text conversation and continuing according to the user operation and the voice conversation proceeding state.
Preferably, the state judgment according to the voice conversation may include: the voice content of the user cannot be identified by the automatic voice conversation service due to too much environmental noise, the voice content cannot be identified due to too heavy dialect accent of the user, and the like; the determining according to the user operation may include: voice input is inconvenient when a user inputs a large amount of array or table data, voice listening is inconvenient when the user needs to present a large amount of array or table data, the user actively selects to switch to a text conversation, and the like.
And when the switching condition is detected to be met, generating a text conversation interface, sending the text conversation interface to the user, and switching the voice conversation of the user to a text conversation connection. Therefore, when the voice conversation works well, the conversation can be quickly carried out in a voice conversation mode, the conversation can be switched to a text conversation when the voice conversation is not clearly listened and the recognition is not accurate, the accuracy of the conversation is guaranteed, and the input and the output of a large amount of data can be facilitated.
Further, as shown in fig. 1, in order to improve the user experience, after it is determined that a text dialog needs to be switched to due to a recognition error or the like, and before a text dialog interface is generated, a switching confirmation needs to be requested from the user, specifically, a dialog record for switching the text dialog needs to be played to the user, and an approval or rejection instruction of the user is waited. The instruction for waiting for the approval or rejection of the user may be information for waiting for the user to press a key, for example, pressing 1 is to approve the switch, and pressing 2 is to reject the switch. If the user agrees, starting to switch to the text conversation and generating a text conversation interface; if the user refuses or waits for a timeout without replying, the voice conversation continues.
Preferably, the generated text dialog interface is generated on a web page, and particularly may be generated on an H5 web page, and the website link is sent to the user after the generation of the web page including the text dialog interface is completed, and the user clicks the website link to open the web page including the text dialog interface, so that a subsequent text dialog can be started in the text dialog interface. The terminal for the user to receive the website link and open the webpage can be a mobile phone, a tablet computer, a notebook computer, wearable equipment and other terminal equipment capable of communicating.
In order to improve convenience of sending the text dialogue interface to the user and using by the user, it is further preferable that a web page including the text dialogue interface is generated, a link of the web page is converted into a short link of only 10-bit character length, and then the short link is sent to the user through a short message. After the user clicks the short link, the short link server analyzes the short link to restore the short link into a website link of the original webpage, and the user jumps to the webpage containing the text conversation interface.
The website link and the session ID of the session have a corresponding relation, and the session data of the session and the session progress data can be found by accessing the specific website link and determining the session carried out by the user. Preferably, the website link is generated from the session id, and the session id may be directly extracted from the website link and then located to the session data corresponding to the session id.
Preferably, because the dialog generally has timeliness, in order to screen out the dialog which is out of date, a timestamp of the current time is added to the website link when the website link of the webpage is constructed, an expiration time is preset, and when the user opens the website link, whether the dialog of the website link is out of date is judged according to the timestamp in the website link and the expiration time. The dialog may continue if it has not expired, and a new sessionID may be generated and a new text dialog may be started from scratch if it has expired.
Based on the two preferred improvements, sessionID and timestamp of current time of the dialog can be simultaneously inserted into the website link, a dialog _ state _ key keyword string unique to each dialog is generated according to the sessionID and the timestamp, and the website link is generated by using the dialog _ state _ key keyword string.
Based on the preferred improvement, when the user opens the webpage and then continues the dialog flow chart as shown in fig. 2, the short link in the short message is accessed, and after the short link is converted, the converted website link address is skipped. The website link address comprises a dialog _ state _ key keyword string, the dialog _ state _ key keyword string is analyzed to obtain a session ID and expiration time of a dialog corresponding to the website link, whether the dialog is still in progress is judged according to the expiration time, if the dialog is still in progress, session data is inquired according to the session ID and a server of redis, a voice dialog progress is obtained, the voice dialog progress is used as a text dialog progress, a text dialog interface is led in to restore a dialog state, and then the dialog is continued in the text dialog interface of the webpage. If and then get the conversation progress information of the previous voice conversation. If the dialog has expired, a new sessionID is generated and a new text dialog is started from the beginning.
Further, the voice conversation progress and the text conversation progress include a conversation start time, conversation history information, current conversation node information, data collected in the conversation, which enable the conversation to be made progress when switching between voice and text.
Preferably, the present embodiment further includes the following method: when the text dialogue is detected to meet the switching condition, if the user actively requires to switch to the voice dialogue, the text dialogue is switched back to the voice dialogue approximately by the method. And continuing the progress of the text dialog after the switching to take advantage of the high efficiency of the voice dialog at a suitable time.
The embodiment also provides a multi-channel conversation continuing system which is used for realizing the method and comprises a voice conversation server, a text conversation server, a user terminal, a conversation progress database and a switching server. The voice dialogue server and the text dialogue server are respectively used for carrying out voice and text dialogue with the user terminal, and the text dialogue server is also used for generating a text dialogue interface and a webpage where the text dialogue interface is located. The user terminal is a main bearing body for a user to have a conversation with the voice conversation server and the text conversation server, and can be a plurality of communicable terminal devices such as a mobile phone, a tablet computer, a notebook computer and wearable equipment. The dialog progress database may be a redis storage system in the preferred embodiment described above for storing the voice dialog progress and the text dialog progress for each dialog. The switching server is used for detecting the switching condition and calling the conversation progress in the conversation progress database, so that the conversation at the user terminal can be switched between the pointing voice conversation server and the text conversation server, and the conversation progress is kept in the switching process.
It should be noted that the above-mentioned embodiments are merely illustrative of the preferred embodiments and principles of the present invention, and those skilled in the art will appreciate that there are variations in the specific embodiments based on the ideas provided by the present invention, and these variations should be considered as the scope of the present invention.
Claims (10)
1. A multi-channel dialog continuation method, the method comprising:
recording the voice conversation progress when a user carries out voice conversation;
when detecting that the voice conversation meets the switching condition, generating a text conversation interface, and sending the text conversation interface to a user; and applying the text conversation progress to the text conversation interface by taking the voice conversation progress as the text conversation progress, wherein the user can switch to a text conversation in the text conversation interface and continue the voice conversation progress.
2. The method for multi-channel dialog continuation according to claim 1, wherein said sending said text dialog interface to a user specifically comprises:
generating the text dialog interface on a webpage;
and sending the website link of the webpage to a user, and opening the webpage containing the text conversation interface after the user clicks the website link.
3. The method for multi-channel dialog continuation according to claim 2, wherein said sending the web site link of the web page to the user specifically comprises:
converting the link of the webpage into a short link;
and sending the short link to the user in a short message form.
4. The method for multi-channel dialog continuation of claim 2, further comprising:
allocating a conversation ID for each conversation, and constructing the website link by using the conversation ID;
and determining the continued conversation according to the conversation ID contained in the website link accessed by the user.
5. The method for multi-channel dialog continuation of claim 2, further comprising:
adding a current timestamp in the website link when the website link is constructed;
and setting expiration time, judging whether the conversation is expired or not according to the timestamp and the expiration time when the user opens the website link, and reminding the user that the conversation is expired if the conversation is expired.
6. The method according to claim 1, wherein when it is detected that the voice dialog satisfies the switching condition, soliciting a switching confirmation from the user, and if the user confirms, performing the switching; if the user refuses or the timeout is not confirmed, the voice conversation is continuously maintained.
7. The method of claim 1, wherein the switching is initiated when detecting that the voice dialog satisfies one or more switching conditions; the switching conditions include:
the voice content of the user is difficult to recognize;
a user inquires or inputs data;
the user actively requests to switch text conversations.
8. The multi-channel dialog continuation method of claim 1 wherein said voice dialog progress and said text dialog progress comprise:
a session start time;
session history information;
current session node information;
data collected in a conversation.
9. The method for multi-channel dialog continuation according to claim 1, further comprising: and recording the text conversation progress when the user starts the text conversation, and switching to the voice conversation and continuing the text conversation progress by taking the text conversation progress as the voice conversation progress when detecting that the text conversation meets the switching condition.
10. A multi-channel dialog continuation system applying the method according to any of claims 1-9, characterized in that the system comprises:
the voice conversation server is used for carrying out voice conversation with the user;
the text conversation server is used for generating the text conversation interface and carrying out text conversation with the user;
the user terminal is used for carrying out conversation with the voice conversation server and the text conversation server by a user;
a conversation progress database for storing the voice conversation progress and the text conversation progress of each conversation;
and the switching server is used for detecting the switching condition, calling the conversation progress in the conversation progress database and controlling the conversation of the user terminal to be switched between the voice conversation server and the text conversation server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210068771.9A CN114117020A (en) | 2022-01-21 | 2022-01-21 | Multi-channel conversation continuing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210068771.9A CN114117020A (en) | 2022-01-21 | 2022-01-21 | Multi-channel conversation continuing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114117020A true CN114117020A (en) | 2022-03-01 |
Family
ID=80360985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210068771.9A Pending CN114117020A (en) | 2022-01-21 | 2022-01-21 | Multi-channel conversation continuing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114117020A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080147406A1 (en) * | 2006-12-19 | 2008-06-19 | International Business Machines Corporation | Switching between modalities in a speech application environment extended for interactive text exchanges |
| CN101207655A (en) * | 2006-12-19 | 2008-06-25 | 国际商业机器公司 | Method and system switching between voice and text exchanging forms in a communication conversation |
| US8593501B1 (en) * | 2012-02-16 | 2013-11-26 | Google Inc. | Voice-controlled labeling of communication session participants |
| US20170078490A1 (en) * | 2015-09-16 | 2017-03-16 | International Business Machines Corporation | Adaptive voice-text transmission |
| US20210090563A1 (en) * | 2019-09-20 | 2021-03-25 | Hyundai Motor Company | Dialogue system, dialogue processing method and electronic apparatus |
-
2022
- 2022-01-21 CN CN202210068771.9A patent/CN114117020A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080147406A1 (en) * | 2006-12-19 | 2008-06-19 | International Business Machines Corporation | Switching between modalities in a speech application environment extended for interactive text exchanges |
| CN101207655A (en) * | 2006-12-19 | 2008-06-25 | 国际商业机器公司 | Method and system switching between voice and text exchanging forms in a communication conversation |
| US8593501B1 (en) * | 2012-02-16 | 2013-11-26 | Google Inc. | Voice-controlled labeling of communication session participants |
| US20170078490A1 (en) * | 2015-09-16 | 2017-03-16 | International Business Machines Corporation | Adaptive voice-text transmission |
| US20210090563A1 (en) * | 2019-09-20 | 2021-03-25 | Hyundai Motor Company | Dialogue system, dialogue processing method and electronic apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111192060B (en) | Full-channel self-service response implementation method based on power IT service | |
| CN201504266U (en) | User voice processing system based on telephone bank | |
| US9761241B2 (en) | System and method for providing network coordinated conversational services | |
| DE69937962T2 (en) | DEVICE AND METHOD FOR PROVIDING NETWORK COORDINATED CONVERSION SERVICES | |
| CN106409283B (en) | Man-machine mixed interaction system and method based on audio | |
| CN102984666B (en) | Address list voice information processing method in a kind of communication process and system | |
| CN110049270A (en) | Multi-person conference speech transcription method, apparatus, system, equipment and storage medium | |
| KR101901920B1 (en) | System and method for providing reverse scripting service between speaking and text for ai deep learning | |
| CN105100360A (en) | Communication auxiliary method and device for voice communication | |
| CN111128241A (en) | Intelligent quality inspection method and system for voice call | |
| CN105206272A (en) | Voice transmission control method and system | |
| CN113782022B (en) | Communication method, device, equipment and storage medium based on intention recognition model | |
| TWI690811B (en) | Intelligent Online Customer Service Convergence Core System | |
| CN101699840B (en) | Intelligent speech interactive system in converged communication and method for implementing same | |
| CN112583984A (en) | Agent allocation method, device, system, equipment and medium based on voice interaction | |
| CN117424960A (en) | Intelligent voice service method, device, terminal equipment and storage medium | |
| CN111554280A (en) | Real-time interpretation service system for mixing interpretation contents using artificial intelligence and interpretation contents of interpretation experts | |
| CN111339282A (en) | Intelligent online response method and intelligent customer service system | |
| CN114117020A (en) | Multi-channel conversation continuing method and system | |
| CN104715045A (en) | Information transmitting method and terminal | |
| CN110502631B (en) | Input information response method and device, computer equipment and storage medium | |
| CN109147791A (en) | A kind of shorthand system and method | |
| CN110445934A (en) | Call-information processing method, system, terminal and readable storage medium storing program for executing | |
| CN101656803A (en) | Operator position system capable of recognizing voices and voice recognition method thereof | |
| CN201130994Y (en) | Words consultation auto-answer system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220301 |