Disclosure of Invention
The embodiment of the invention provides a display method, a display device and a display device, which can reduce the operation cost of a user for screening target comment information from massive comment information and improve the efficiency of the user for acquiring the target comment information.
In order to solve the above problems, an embodiment of the present invention discloses a display method, which includes:
When the query information input by a user is identified to hit a target theme, target comment information corresponding to the target theme is obtained, wherein the target comment information comprises comment information which is screened from at least one third-party platform, is related to the target theme and is classified according to account types;
And in the search result page of the query information, the target comment information is displayed according to the account category classification.
Optionally, the obtaining the target comment information corresponding to the target theme includes:
Searching in at least one third party platform based on the target subject to obtain related comment information of the target subject;
Carrying out semantic recognition on the related comment information of the target subject to obtain effective comment information;
Carrying out account identification on the effective comment information, and determining account types corresponding to the effective comment information;
Clustering the effective comment information according to the identified account categories to obtain target comment information of each account category corresponding to the target subject.
Optionally, the performing semantic recognition on the related comment information of the target theme to obtain effective comment information includes:
identifying emotion tendencies corresponding to each piece of related comment information of the target theme;
and determining the relevant comment information with the emotion tendency conforming to the first direction as effective comment information, and determining the relevant comment information with the emotion tendency conforming to the second direction as non-effective comment information.
Optionally, after the valid comment information is obtained, the method further includes:
Counting related data of the effective comment information, wherein the related data comprises at least one of comment numbers, praise numbers and forwarding numbers of the effective comment information;
and ordering the effective comment information according to the related data of the effective comment information to obtain effective comment information of N before ordering, wherein N is a positive integer.
Optionally, the identifying the account of the valid comment information, determining an account category corresponding to the valid comment information includes:
extracting account identifiers of the effective comment information;
Acquiring identity association information of the account identifier, wherein the identity association information comprises a relationship map corresponding to the account identifier and/or third party authentication information corresponding to the account identifier;
And determining the account category corresponding to the effective comment information according to the account identifier and the identity association information of the account identifier.
Optionally, the method further comprises:
acquiring related comment information of the target comment information;
extracting target keywords from related comment information of the target comment information;
Marking labels on the target comment information according to the target keywords contained in the related comment information of the target comment information and the duty ratio of the contained target keywords;
And displaying the target comment information in the search result page of the query information according to the account category classification, and further comprising:
and displaying the label corresponding to the target comment information at the relevant position where the target comment information is displayed.
Optionally, the displaying the target comment information according to the account category classification in the search result page of the query information includes:
displaying a comment information interface in a reduced mode in a search result page of the query information, wherein the comment information interface in the reduced mode comprises key information of the target comment information;
And responding to the triggering operation of the comment information interface in the reduced mode, displaying the comment information interface in the unfolding mode, wherein the comment information interface in the unfolding mode comprises at least one tab page, and the tab page is used for displaying target comment information of different account categories.
Optionally, the method further comprises:
and displaying interactive comment information in a bullet screen form in a search result page of the query information, wherein the interactive comment information comprises target comment information corresponding to the target theme and/or filtered comment information related to the target theme.
In another aspect, an embodiment of the present invention discloses a display device, the device including:
The information acquisition module is used for acquiring target comment information corresponding to a target theme when identifying that query information input by a user hits the target theme, wherein the target comment information comprises comment information which is screened from at least one third-party platform, is related to the target theme and is classified according to account types;
And the information display module is used for displaying the target comment information in a classified manner according to the account category in the search result page of the query information.
Optionally, the information acquisition module includes:
The information retrieval sub-module is used for retrieving in at least one third party platform based on the target subject to obtain related comment information of the target subject;
The semantic recognition sub-module is used for carrying out semantic recognition on the related comment information of the target theme to obtain effective comment information;
The account identification sub-module is used for carrying out account identification on the effective comment information and determining account types corresponding to the effective comment information;
And the information clustering sub-module is used for clustering the effective comment information according to the identified account categories to obtain target comment information of the target subject corresponding to each account category.
Optionally, the semantic recognition sub-module includes:
the emotion recognition unit is used for recognizing emotion tendencies corresponding to the relevant comment information of the target theme;
And the information determining unit is used for determining the relevant comment information with the emotion tendency conforming to the first direction as effective comment information and determining the relevant comment information with the emotion tendency conforming to the second direction as non-effective comment information.
Optionally, the apparatus further comprises:
The data statistics module is used for counting related data of the effective comment information, wherein the related data comprises at least one of comment numbers, praise numbers and forwarding numbers of the effective comment information;
And the information ordering module is used for ordering the effective comment information according to the related data of the effective comment information to obtain N effective comment information before ordering, wherein N is a positive integer.
Optionally, the account identification sub-module includes:
The identification extraction unit is used for extracting account identifications of the effective comment information;
The association acquisition unit is used for acquiring identity association information of the account identifier, wherein the identity association information comprises a relationship map corresponding to the account identifier and/or third party authentication information corresponding to the account identifier;
And the category determining unit is used for determining the account category corresponding to the effective comment information according to the account identifier and the identity association information of the account identifier.
Optionally, the apparatus further comprises:
The related acquisition module is used for acquiring related comment information of the target comment information;
The target extraction module is used for extracting target keywords from the related comment information of the target comment information;
the tag marking module is used for marking the target comment information according to the target keywords contained in the related comment information of the target comment information and the duty ratio of the contained target keywords;
the apparatus further comprises:
And the label display module is used for displaying the label corresponding to the target comment information at the relevant position for displaying the target comment information.
Optionally, the information display module includes:
the first display sub-module is used for displaying a comment information interface in a reduced mode in a search result page of the query information, wherein the comment information interface in the reduced mode comprises key information of the target comment information;
and the second display sub-module is used for responding to the triggering operation of the comment information interface in the reduced mode, displaying the comment information interface in the expanded mode, wherein the comment information interface in the expanded mode comprises at least one tab page, and the tab page is used for displaying target comment information of different account categories.
Optionally, the apparatus further comprises:
the bullet screen display module is used for displaying interactive comment information in a bullet screen form in a search result page of the query information, wherein the interactive comment information comprises target comment information corresponding to the target theme and/or filtered comment information related to the target theme.
In yet another aspect, an embodiment of the present invention discloses a device for presentation, comprising a memory, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for performing a presentation method as described in one or more of the foregoing.
In yet another aspect, embodiments of the present invention disclose a machine-readable medium having instructions stored thereon, which when executed by one or more processors of an apparatus, cause the apparatus to perform a presentation method as described in one or more of the preceding.
The embodiment of the invention has the following advantages:
In the embodiment of the invention, when the query information input by the user is identified to hit the target subject in the user searching process, the target comment information corresponding to the target subject hit by the query information is acquired in addition to the search result corresponding to the query information. The target comment information includes comment information related to the target subject and classified by account category screened from at least one third party platform. In the embodiment of the invention, the target comment information is displayed in the search result page of the query information according to the account category classification. According to the method and the device for displaying the target comment information, the search results can be displayed for the user in a classified mode, meanwhile valuable target comment information related to the query information is displayed for the user, the user can be prevented from browsing one by one in the comment area of the search result page, excessive meaningless spam comments are checked, the user can quickly obtain more valuable comment information, the operation cost of the user for screening the target comment information from the massive comment information is reduced, and the efficiency of the user for obtaining the target comment information is improved.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second, and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged where appropriate so that embodiments of the invention may be practiced in orders other than those illustrated and described herein, and that the objects identified by "first," "second," etc. are generally of the type and do not limit the number of objects, e.g., the first object may be one or more. Furthermore, the terms "and/or" in the description and in the claims are used to describe an association of associated objects, meaning that there may be three relationships, for example, A and/or B, and that there may be three cases where A alone exists, while A and B exist, and B alone exists. The character "/'' generally indicates that the context associated object is a kind of" or "relationship". The term "plurality" in embodiments of the present invention refers to two or more, and other adjectives are similar thereto.
Method embodiment
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a method of the present invention may specifically include the following steps:
Step 101, when query information input by a user is identified to hit a target topic, target comment information corresponding to the target topic is obtained, wherein the target comment information comprises comment information which is screened from at least one third party platform, is related to the target topic and is classified according to account types;
and 102, displaying the target comment information in a classified manner according to the account category in a search result page of the query information.
The display method provided by the invention can be applied to electronic equipment, including but not limited to servers, smart phones, recording pens, tablet computers, electronic book readers, MP3 (dynamic image expert compression standard audio layer 3,Moving Picture Experts Group Audio Layer III) players, MP4 (dynamic image expert compression standard audio layer 4,Moving Picture Experts Group Audio LayerIV) players, laptop computers, vehicle-mounted computers, desktop computers, set-top boxes, smart televisions, wearable equipment and the like.
The embodiment of the invention can be applied to various scenes using search engine technology, including but not limited to general search engines, search engines in application programs and the like.
The query information refers to information input by a user in a search box of a search engine, and the query information is used for triggering a query request to acquire search results related to the query information. After receiving a query request triggered by a user, the electronic device responds to the query request to identify whether query information carried in the query request hits a target theme.
The target topic may be a preset topic, and the target topic may include, but is not limited to, any one or more of a target hot topic, a target news event, and a target entity. Where an entity refers to various objects and concepts present in the real world, such as a person name, place name, event, organization, brand, merchandise, work, date, and so forth.
It should be noted that, the embodiment of the present invention does not limit the specific type of the query information. The query information may be text information, voice information, image information, etc. When the query information is text information, the text information can be analyzed to identify whether the text information hits a target theme, when the query information is voice information, the voice information can be subjected to voice recognition to obtain corresponding text information, then the text information is analyzed, when the query information is image information, if the image information contains text content, the image information can be subjected to text recognition to obtain corresponding text information, then the text information is analyzed, and if the image information does not contain text content, the image information can be subjected to image processing to identify the content contained in the image information, and whether the content contained in the image information hits the target theme is identified.
The identifying that the query information input by the user hits the target topic includes, but is not limited to, identifying that the query information input by the user contains the same keywords as the target topic and/or identifying that the query information input by the user contains the same entities as the target topic and/or identifying that the query information input by the user is semantically related to the target topic.
When the query information input by the user is identified to hit the target theme, the embodiment of the invention obtains the target comment information corresponding to the target theme in addition to the search result corresponding to the query information. The target comment information includes comment information related to the target subject and classified by account category screened from at least one third party platform.
In one example, assuming that query information input by a user is received as 'HongStark donation 5000 ten thousand', and assuming that a target topic 'HongStark donation 5000 ten thousand' is included in a preset topic, it is determined that the query information hits the target topic. The embodiment of the invention can acquire the search result corresponding to the query information 'Hongxingke donation 5000 ten thousand', and acquire the target comment information corresponding to the target theme. The target comment information includes comment information related to the target subject and classified by account category screened from at least one third party platform. Wherein the account category may be used to represent an account domain and/or an account rating of the comment information publisher. For example, in a particular application, account categories may include general net friend accounts, official accounts, principal accounts, large V accounts, and the like.
In this example, it is assumed that the account category "general net friends" includes 10 item subject comments that are screened out as being related to the target subject. The account category official includes 15 comments related to the target subject. The account category 'principal' includes 10 item subject comments related to the target subject. The account category 'big V' comprises 5 selected comments related to the target theme. The target comment information contained in each account category can be classified and displayed according to the account category in a search result page for displaying the search result corresponding to the query information 'Hongxingkong donation 5000 ten thousand'.
The embodiment of the invention does not limit the specific form of displaying the target comment information in the search result page. In an optional embodiment of the present invention, the displaying, in step 102, the target comment information according to the account category classification in the search result page of the query information may include:
Step S11, displaying a comment information interface in a reduced mode in a search result page of the query information, wherein the comment information interface in the reduced mode comprises key information of the target comment information;
And step S12, responding to the triggering operation of the comment information interface in the reduced mode, and displaying the comment information interface in the expanded mode, wherein the comment information interface in the expanded mode comprises at least one tab page, and the tab page is used for displaying target comment information of different account categories.
When identifying that query information input by a user hits a target theme, the embodiment of the invention displays search results corresponding to the query information in a search result page. In addition, in the search result page of the query information, a comment information interface in a reduced mode is displayed, wherein the comment information interface in the reduced mode comprises key information of the target comment information.
The comment information interface is used for displaying target comment information. The reduced mode may display only a portion of the comment information interface. The key information may be part of the target comment information displayed in the comment information interface. For example, the key information may be the complete content of a certain piece of target comment information in the comment information interface, or the key information may be a content summary of a certain piece of target comment information in the comment information interface, or the key information may be first target comment information in the comment information interface in order, etc. It will be appreciated that embodiments of the present invention do not limit the specific content of the key information.
Referring to FIG. 2, a schematic diagram of a comment information interface showing a condensed mode in a search results page is shown, according to an embodiment of the present invention. The search results page as shown in fig. 2 shows a comment information interface of the search results and the reduced mode. Optionally, a trigger key for triggering the unfolding mode may be further displayed in the comment information interface of the shrinking mode. Optionally, a switching key for switching key information may be displayed in the comment information interface in the reduced mode, for example, switching to display the comment information of the previous item or switching to display the comment information of the next item.
It should be noted that, the embodiment of the invention does not limit the display mode of the comment information interface in the reduced mode. Alternatively, the comment information interface in the reduced mode may be shown below the search results page. Of course, in implementation, the comment information interface of the reduced mode may also be displayed above or beside the search result page.
Referring to FIG. 3, a schematic diagram of a comment information interface showing a condensed mode in a search results page in one specific example of the invention is shown. As shown in the bottom section of the interface "each side of the mind" section.
When receiving a triggering operation of a user on the comment information interface in the reduced mode, the embodiment of the invention displays the comment information interface in the expanded mode in response to the triggering operation, such as the triggering operation executed on a triggering key in the comment information interface in the reduced mode.
In an embodiment of the present invention, the triggering operation includes, but is not limited to, a mouse click operation, such as a left click, a right click, a touch operation on a touch display screen of the electronic device, and the like. The touch operation may be performed by a target object (e.g., a finger, a stylus, etc.) approaching or contacting a touch display screen of the electronic device. In one example, the touch operation may include a click (including single click, double click, triple click) operation, a long press operation, a slide operation, and the like.
Further, the triggering operation may include a gesture operation, which may be a gesture track, etc., or a combination operation of a gesture operation and a device input operation other than the gesture operation. For example, the combination operation of the gesture operation and the key operation of a certain function key on the electronic device may be combined operation of the gesture operation and the sound control operation, or the combination operation of the gesture operation and the touch operation, or the combination operation of the gesture operation and the fingerprint collection operation may be combined operation. Correspondingly, the equipment other than the gesture operation can be a function key of the electronic equipment, a touch screen, a fingerprint acquisition equipment or a voice acquisition equipment and the like.
The expansion mode can display a complete comment information interface. The comment information interface in the unfolding mode comprises at least one tab page, and the tab page is used for displaying target comment information of different account categories.
Referring to FIG. 4, a schematic diagram of a comment information interface showing an expanded mode in a search results page is shown, according to an embodiment of the present invention. The comment information interface of the expanded mode is shown in an elastic layer form in the search result page as shown in fig. 4. The comment information interface exhibiting the expanded mode may be overlaid over the search results interface. The comment information interface of the unfolding mode comprises 4 label pages of net friends view, authorities, parties and big V comment. The 'net friends' tab page is used to display target comment information included in the account category 'ordinary net friends'. The 'official' tab page is used to display target comment information included in the account category 'official'. 'principal' tab page is used to display target comment information included in account category 'principal'. 'big V comment' tab page is used to display target comment information included in account category 'big V'. Different tab pages may switch displays. As shown in FIG. 3, the current interface displays a "net friends opinion" tab page.
It should be noted that, the embodiment of the invention does not limit the display mode of the comment information interface in the unfolding mode. Alternatively, the comment information interface of the expansion mode may be displayed in a bullet layer form, where the bullet layer form includes a bullet window, a floating layer, a layer, and the like.
Referring to FIG. 5, a schematic diagram of a comment information interface showing an expanded mode in a search results page in one specific example of the invention is shown.
In the embodiment of the invention, in the process of searching a user, besides the search result corresponding to the query information, the target comment information corresponding to the target subject hit by the query information is also acquired. The target comment information includes comment information related to the target subject and classified by account category screened from at least one third party platform. In the embodiment of the invention, the target comment information is displayed in the search result page of the query information according to the account category classification. According to the method and the device for displaying the target comment information, the search results can be displayed for the user, meanwhile, valuable target comment information related to the query information is displayed for the user in a classified mode, the user can be prevented from viewing too many meaningless junk comments, the user can quickly acquire more valuable comment information, the operation cost of screening the target comment information from the massive comment information is reduced, and the efficiency of acquiring the target comment information by the user is improved.
In an optional embodiment of the present invention, the obtaining, in step 101, the target comment information corresponding to the target theme may include:
step S21, searching in at least one third party platform based on the target subject to obtain related comment information of the target subject;
s22, carrying out semantic recognition on the related comment information of the target subject to obtain effective comment information;
step S23, carrying out account identification on the effective comment information, and determining account types corresponding to the effective comment information;
And S24, clustering the effective comment information according to the identified account categories to obtain target comment information of the target subject corresponding to each account category.
For a certain target topic, a unique Identification (ID) corresponding to the target topic may be created. And searching in at least one third-party platform based on the target theme to obtain the related comment information of the target theme. The third party platform may be any network platform, such as each news media website. In addition, the embodiment of the invention can acquire the topic related to the target topic, and associate the related topic to the unique Identifier (ID) corresponding to the target topic, so that the comment information of the topic related to the target topic is also used as the related comment information of the target topic. Comment information related to the target topic may be aggregated from the whole network based on a unique Identification (ID) corresponding to the target topic.
In one example, the target topic may be a network trending event. Since the rise of the network popular event is generally accompanied by a large number of news stories, when the target topic is a network popular event, the relevant comment information of the searched target topic may be news story text related to the network popular event and news comment text corresponding to the news stories crawled from each news media website.
After the related comment information of the target theme is retrieved, semantic recognition can be performed on the related comment information of the target theme, and effective comment information is obtained.
And carrying out semantic recognition on the related comment information of the target theme, and filtering out the worthless comment information. The non-valuable comment information at least comprises any one or more of comment information containing repeated nonsensical characters, comment information containing non-civilized expressions and comment information containing repeated contents. The comment information of the repeated nonsensical characters is included, for example: haha ha a haha ha hip-hop, haha hiccup, and the like. The comment information containing the repeated content refers to comment information copying the comment content of other people.
Further, the related comment information of the target theme is subjected to semantic recognition, and comment information which does not meet emotion tendencies can be filtered.
In an optional embodiment of the present invention, the performing semantic recognition on the relevant comment information of the target subject in step S22 to obtain valid comment information may include:
step S221, identifying emotion tendencies corresponding to the relevant comment information of the target theme;
Step S222, determining relevant comment information with emotion tendencies conforming to the first direction as valid comment information, and determining relevant comment information with emotion tendencies conforming to the second direction as non-valid comment information.
Among these emotional tendencies may include three tendencies, positive, negative, and neutral.
In an alternative embodiment, the first direction may comprise a positive direction and a neutral direction and the second direction may comprise a negative direction. The embodiment of the invention can determine that the related comment information with the emotion tendency conforming to the first direction is effective comment information and determine that the related comment information with the emotion tendency conforming to the second direction is ineffective comment information. Of course, in a specific application, the first direction and the second direction may be determined according to actual needs. Such as may determine that the first direction includes neutral and negative directions, and that the second direction includes positive directions, etc.
It should be noted that, the embodiment of the present invention does not limit a specific manner of identifying emotional tendency corresponding to each relevant comment information of the target subject.
Optionally, semantic recognition may be performed on each relevant comment information of the target subject, a keyword related to emotion contained in the relevant comment information is extracted, and an emotional tendency corresponding to each relevant comment information of the target subject is determined according to the extracted keyword related to emotion. For example, if a positive and positive emotion-related keyword is extracted from a certain piece of related comment information, the emotion tendency corresponding to the piece of related comment information can be determined to be positive, if a negative and negative emotion-related keyword is extracted from a certain piece of related comment information, the emotion tendency corresponding to the piece of related comment information can be determined to be negative, otherwise, the emotion tendency corresponding to the piece of related comment information can be determined to be neutral.
Alternatively, an emotion recognition model for recognizing emotion tendencies may be trained in advance, and each piece of relevant comment information of the target subject may be sequentially input into the emotion recognition model, and through the emotion recognition model, the emotion tendencies corresponding to each piece of relevant comment information of the target subject may be output.
The emotion recognition model can be obtained by performing supervised training on the existing neural network according to a large number of training samples and machine learning methods. The training sample of the emotion recognition model may include a large amount of collected historical comment information and emotion tendency labeling data of each piece of historical comment information. It should be noted that, the embodiment of the present invention does not limit the model structure and training method of the emotion recognition model. The emotion recognition model may incorporate a variety of neural networks. The neural network includes, but is not limited to, at least one or a combination, superposition, nesting of at least two of CNN (Convolutional Neural Network ), LSTM (Long Short-Term Memory) network, RNN (Simple Recurrent Neural Network, recurrent neural network), attention neural network, etc.
In an optional embodiment of the present invention, after the obtaining valid comment information, the method may further include:
step S31, counting related data of the effective comment information, wherein the related data comprises at least one of comment numbers, praise numbers and forwarding numbers of the effective comment information;
And step S32, sorting the effective comment information according to the related data of the effective comment information to obtain effective comment information of N before sorting, wherein N is a positive integer.
According to the embodiment of the invention, after the related comment information of the target subject is subjected to semantic recognition to obtain the effective comment information, the obtained effective comment information can be further sequenced to screen out the high-quality comment information with N top ranking from the effective comment information.
Specifically, the relevant data of the valid comment information may be counted, and the relevant data includes at least one of a comment number, a praise number, and a forwarding number of the valid comment information.
And sorting the effective comment information according to the related data of the effective comment information, so that the effective comment information of N before sorting can be obtained, wherein the effective comment information of N before sorting is the screened high-quality comment information. Therefore, the embodiment of the invention can provide better target comment information for the user, and further reduce the operation cost of browsing the worthless junk comment information by the user.
In an optional embodiment of the present invention, the identifying the account of the valid comment information in step S23, and determining the account category corresponding to the valid comment information may include:
step S231, extracting account identifiers of the effective comment information;
Step S232, acquiring identity association information of the account identifier, wherein the identity association information comprises a relationship map corresponding to the account identifier and/or third party authentication information corresponding to the account identifier;
step S233, determining the account category corresponding to the effective comment information according to the account identifier and the identity association information of the account identifier.
In embodiments of the invention, account categories may be used to represent account areas and/or account ratings of comment information publishers.
After carrying out semantic recognition on related comment information of the target subject to obtain effective comment information, or after sorting the obtained effective comment information to obtain effective comment information N before sorting, the embodiment of the invention extracts account identification of the effective comment information and obtains identity related information of the account identification.
Wherein the account identification may include an account ID and/or an account name. The identity association information of the account identifier may include a relationship graph corresponding to the account identifier and/or third party authentication information corresponding to the account identifier.
The relational graph and data visualization technology can present data in a structured and visual mode, establish a knowledge system with keywords as centers and display the interrelationship among the data. For example, a social relationship network diagram reflecting the real world may be constructed based on people, things, places, organizations, and entity-relationship-events. In the relationship graph, there may be a relationship between an object of an entity class and an object of an entity class, a relationship between an object of an entity class and an object of an event class, or a relationship between an object of an event class and an object of an event class.
The third party authentication information refers to authentication information given by the third party platform to the account identifier after the account identifier is authenticated by the third party platform. For example, after a certain account information is authenticated by the microblog platform, the microblog platform gives the account identifier 'large V' authentication information.
According to the account identification of the publisher of a certain piece of effective comment information and the identity association information of the account identification, the account category corresponding to the effective comment information can be obtained.
For example, for a piece of valid comment information, it is assumed that a keyword representing a public security management department in a certain region is included in an account identifier of a publisher, and the account identifier can be determined to belong to an official account according to the keyword query relationship map.
Optionally, the embodiment of the invention can also pre-train an account identification model for identifying account types, input the account identification of the effective comment information into the account identification model, and output the account types corresponding to the account identification through the account identification model.
The account identification model can be obtained by performing supervised training on the existing neural network according to a large number of training samples and machine learning methods. The training sample of the account identification model may include a collection of account identifications and account category annotation data for each account identification. It should be noted that, the embodiment of the present invention does not limit the model structure and training method of the account identification model. The account identification model may incorporate a variety of neural networks. The neural network includes, but is not limited to, at least one or a combination, superposition, nesting of at least two of a CNN network, an LSTM network, an RNN network, an attention neural network, etc.
In an alternative embodiment of the present invention, the method may further include:
Step S41, obtaining relevant comment information of the target comment information;
Step S42, extracting target keywords from related comment information of the target comment information;
And S43, marking the target comment information with a label according to the target keywords contained in the related comment information of the target comment information and the duty ratio of the contained target keywords.
According to the embodiment of the invention, on the basis of classifying and displaying the target comment information according to the account category, the corresponding label can be marked on the target comment information according to the related comment information of the target comment information. When the target comment information is displayed in a classified manner, labels corresponding to different target comment information can be displayed so as to highlight the uniqueness of the target comment information.
Specifically, the embodiment of the invention can acquire the related comment information of the target comment information. The related comment information of the target comment information refers to comment information made by other users on the target comment information. The embodiment of the invention identifies and extracts the target keywords from the related comment information of the target comment information.
The target keyword may include information such as text for evaluating, supporting, or countering target comment information. For example, the target keywords may include textual information of "top," "smart," "praise," "cattle," "support," and "disfigurement," "praise," "insulator," and "good" etc. The embodiment of the invention identifies the target keywords contained in the relevant comment information of each item of comment information, and counts the duty ratio of each target keyword contained in the relevant comment information of each item of comment information. And marking corresponding labels for each item of comment information according to the target keywords contained in the related comment information of each item of comment information and the duty ratio of the contained target keywords. Of course, the tag may not be marked for target comment information that does not contain a target keyword.
In one example, given that a target keyword "praise" contained in the relevant comment information of a certain item of comment information has a higher duty ratio, the item of comment information may be labeled "praise". In another example, assuming that a target keyword "god comment" included in related comment information of a certain item of comment information has a higher duty ratio, the item of comment information may be labeled as "god comment".
Optionally, the embodiment of the invention can also pre-train a label prediction model for predicting labels, input relevant comment information of a certain item of target comment information into the label prediction model, and output labels corresponding to the target comment information through the label prediction model.
The label prediction model can be obtained by performing supervised training on the existing neural network according to a large number of training samples and a machine learning method. The training sample of the label prediction model may include a large amount of collected historical comment information and label labeling data of each piece of historical comment information. It should be noted that, the embodiment of the present invention does not limit the model structure and the training method of the label prediction model. The label prediction model may incorporate a variety of neural networks. The neural network includes, but is not limited to, at least one or a combination, superposition, nesting of at least two of a CNN network, an LSTM network, an RNN network, an attention neural network, etc.
In an optional embodiment of the present invention, in step 102, the displaying the target comment information according to the account category classification in the search result page of the query information may further include:
and displaying the label corresponding to the target comment information at the relevant position where the target comment information is displayed.
In the embodiment of the invention, when the target comment information is displayed in the search result page of the query information according to the account category classification, the label corresponding to the target comment information can be displayed at the relevant position for displaying the target comment information. For example, if a label is "god comment" for a piece of target comment information, the label "god comment" may be displayed at a relevant position of the piece of target comment information when the piece of target comment information is presented. For another example, for another piece of target comment information, the label is "stalk king", and when the item of target comment information is displayed, the label "stalk king" can be displayed at the relevant position of the item of target comment information.
The relevant position may include any position near the target comment information, such as an upper left corner or an upper right corner of the target comment information.
Optionally, the embodiment of the invention can provide two modes of obtaining the target comment information corresponding to the target theme in an offline mode and an online mode.
The offline mode is to directly query and acquire target comment information corresponding to a target subject according to a pre-constructed database. Specifically, a database may be constructed, where the database includes target comment information corresponding to a preset theme constructed in advance, where the target comment information in the database is classified according to account types. When the query information input by the user is identified to hit the target subject, the target subject hit by the query information is used as a keyword, and the pre-constructed database is searched, so that the target comment information corresponding to the target subject can be directly obtained.
The online mode is that when query information input by a user is received and the query information input by the user is identified to hit a target theme, relevant comment information of the target theme is searched in at least one third-party platform in real time, and the relevant comment information obtained by searching is processed and classified in real time to obtain target comment information corresponding to the target theme.
Of course, the method can also adopt a mode of combining an offline mode and an online mode, and synchronously update the database constructed offline through the target comment information corresponding to the target subject acquired in the online mode.
In an alternative embodiment of the present invention, the method may further include:
and displaying interactive comment information in a bullet screen form in a search result page of the query information, wherein the interactive comment information comprises target comment information corresponding to the target theme and/or filtered comment information related to the target theme.
The embodiment of the invention can also display the interactive comment information in a bullet screen form in the search result page of the query information so as to increase the diversity of comment information display and the interactivity of users.
The interactive comment information displayed in the bullet screen form can comprise target comment information corresponding to the target theme and/or filtered comment information related to the target theme.
The filtered comment information related to the target subject may include related comment information with the emotion tendency identified in step S221 conforming to the second direction.
In an alternative embodiment, the filtered comment information with low value can be displayed in a bullet screen form in the search result page of the query information, so as to set the atmosphere and mobilize the interactivity of the user, and the screened target comment information with high value can be displayed in a fixed form, so that the user can conveniently and quickly acquire the high-quality comment information.
In another alternative embodiment, all relevant comment information (including filtered comment information and screened target comment information) of the target subject can be displayed in a bullet screen form in a search result page of the query information, so as to set up atmosphere, mobilize interactivity of a user, and display screened target comment information with higher value in a fixed form, so that the user can conveniently and quickly acquire high-quality comment information.
It should be noted that, the embodiment of the invention does not limit the specific display position of the interactive comment information displayed in the form of a barrage. Alternatively, the interactive comment information may be presented in a bullet screen form in the title portion of the first search result in the search result page.
Therefore, according to the embodiment of the invention, the target comment information related to the query information can be displayed in a classified manner while the search results are displayed in the search result page. The method comprises the steps of displaying interactive comment information in a bullet screen mode and displaying target comment information of different account categories in a tag page mode. Through a plurality of display forms, different types of comment information are displayed, so that the operation cost of screening target comment information from massive comment information by a user can be reduced, and the efficiency of obtaining the target comment information by the user is improved.
In an alternative embodiment of the present invention, the method may further include:
Step S51, when a forwarding request aiming at the target comment information is received, forwarding information corresponding to the target comment information is generated;
And step S52, the forwarding information is sent to a target application in response to the forwarding request.
The forwarding information may include any one or a combination of a plurality of text information, picture information, graphics context information and link information. Through the link information, the original page of the forwarded target comment information can be jumped to.
According to the embodiment of the invention, the target comment information displayed in the search result page can be forwarded or shared to the target application, so that the user can recommend the interested target comment information to friends or forward the target comment information.
In summary, in the process of searching by a user, when the query information input by the user is identified to hit a target topic, the embodiment of the invention acquires target comment information corresponding to the target topic hit by the query information in addition to the search result corresponding to the query information. The target comment information includes comment information related to the target subject and classified by account category screened from at least one third party platform. In the embodiment of the invention, the target comment information is displayed in the search result page of the query information according to the account category classification. According to the method and the device for displaying the target comment information, the search results can be displayed for the user in a classified mode, meanwhile valuable target comment information related to the query information is displayed for the user, the user can be prevented from browsing one by one in the comment area of the search result page, excessive meaningless spam comments are checked, the user can quickly obtain more valuable comment information, the operation cost of the user for screening the target comment information from the massive comment information is reduced, and the efficiency of the user for obtaining the target comment information is improved.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
Device embodiment
Referring to fig. 6, there is shown a block diagram of an embodiment of a display device of the present invention, which may include:
The information obtaining module 601 is configured to obtain target comment information corresponding to a target topic when it is identified that query information input by a user hits the target topic, where the target comment information includes comment information that is screened from at least one third party platform, is related to the target topic, and is classified according to an account category;
And the information display module 602 is configured to display the target comment information in the search result page of the query information according to the account category classification.
Optionally, the information acquisition module includes:
The information retrieval sub-module is used for retrieving in at least one third party platform based on the target subject to obtain related comment information of the target subject;
The semantic recognition sub-module is used for carrying out semantic recognition on the related comment information of the target theme to obtain effective comment information;
The account identification sub-module is used for carrying out account identification on the effective comment information and determining account types corresponding to the effective comment information;
And the information clustering sub-module is used for clustering the effective comment information according to the identified account categories to obtain target comment information of the target subject corresponding to each account category.
Optionally, the semantic recognition sub-module includes:
the emotion recognition unit is used for recognizing emotion tendencies corresponding to the relevant comment information of the target theme;
And the information determining unit is used for determining the relevant comment information with the emotion tendency conforming to the first direction as effective comment information and determining the relevant comment information with the emotion tendency conforming to the second direction as non-effective comment information.
Optionally, the apparatus further comprises:
The data statistics module is used for counting related data of the effective comment information, wherein the related data comprises at least one of comment numbers, praise numbers and forwarding numbers of the effective comment information;
And the information ordering module is used for ordering the effective comment information according to the related data of the effective comment information to obtain N effective comment information before ordering, wherein N is a positive integer.
Optionally, the account identification sub-module includes:
The identification extraction unit is used for extracting account identifications of the effective comment information;
The association acquisition unit is used for acquiring identity association information of the account identifier, wherein the identity association information comprises a relationship map corresponding to the account identifier and/or third party authentication information corresponding to the account identifier;
And the category determining unit is used for determining the account category corresponding to the effective comment information according to the account identifier and the identity association information of the account identifier.
Optionally, the apparatus further comprises:
The related acquisition module is used for acquiring related comment information of the target comment information;
The target extraction module is used for extracting target keywords from the related comment information of the target comment information;
the tag marking module is used for marking the target comment information according to the target keywords contained in the related comment information of the target comment information and the duty ratio of the contained target keywords;
the apparatus further comprises:
And the label display module is used for displaying the label corresponding to the target comment information at the relevant position for displaying the target comment information.
Optionally, the information display module includes:
the first display sub-module is used for displaying a comment information interface in a reduced mode in a search result page of the query information, wherein the comment information interface in the reduced mode comprises key information of the target comment information;
and the second display sub-module is used for responding to the triggering operation of the comment information interface in the reduced mode, displaying the comment information interface in the expanded mode, wherein the comment information interface in the expanded mode comprises at least one tab page, and the tab page is used for displaying target comment information of different account categories.
Optionally, the apparatus further comprises:
the bullet screen display module is used for displaying interactive comment information in a bullet screen form in a search result page of the query information, wherein the interactive comment information comprises target comment information corresponding to the target theme and/or filtered comment information related to the target theme.
Optionally, the apparatus further comprises:
The poster generation module is used for generating poster information corresponding to the target comment information when receiving a forwarding request aiming at the target comment information;
and the information forwarding module is used for forwarding the poster information to a target application in response to the forwarding request.
In the embodiment of the invention, when the query information input by the user is identified to hit the target subject in the user searching process, the target comment information corresponding to the target subject hit by the query information is acquired in addition to the search result corresponding to the query information. The target comment information includes comment information related to the target subject and classified by account category screened from at least one third party platform. In the embodiment of the invention, the target comment information is displayed in the search result page of the query information according to the account category classification. According to the method and the device for displaying the target comment information, the search results can be displayed for the user in a classified mode, meanwhile valuable target comment information related to the query information is displayed for the user, the user can be prevented from browsing one by one in the comment area of the search result page, excessive meaningless spam comments are checked, the user can quickly obtain more valuable comment information, the operation cost of the user for screening the target comment information from the massive comment information is reduced, and the efficiency of the user for obtaining the target comment information is improved.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
The embodiment of the invention provides a device for displaying, which comprises a memory and more than one program, wherein the more than one program is stored in the memory, the more than one program is configured to be executed by more than one processor and comprises instructions for acquiring target comment information corresponding to a target theme when identifying that query information input by a user hits the target theme, the target comment information comprises comment information which is screened from at least one third party platform, is related to the target theme and is classified according to account types, and the target comment information is displayed in a search result page of the query information according to the account types.
Optionally, the obtaining the target comment information corresponding to the target theme includes:
Searching in at least one third party platform based on the target subject to obtain related comment information of the target subject;
Carrying out semantic recognition on the related comment information of the target subject to obtain effective comment information;
Carrying out account identification on the effective comment information, and determining account types corresponding to the effective comment information;
Clustering the effective comment information according to the identified account categories to obtain target comment information of each account category corresponding to the target subject.
Optionally, the performing semantic recognition on the related comment information of the target theme to obtain effective comment information includes:
identifying emotion tendencies corresponding to each piece of related comment information of the target theme;
and determining the relevant comment information with the emotion tendency conforming to the first direction as effective comment information, and determining the relevant comment information with the emotion tendency conforming to the second direction as non-effective comment information.
Optionally, the device is also configured to execute the one or more programs by one or more processors, including instructions for:
Counting related data of the effective comment information, wherein the related data comprises at least one of comment numbers, praise numbers and forwarding numbers of the effective comment information;
and ordering the effective comment information according to the related data of the effective comment information to obtain effective comment information of N before ordering, wherein N is a positive integer.
Optionally, the identifying the account of the valid comment information, determining an account category corresponding to the valid comment information includes:
extracting account identifiers of the effective comment information;
Acquiring identity association information of the account identifier, wherein the identity association information comprises a relationship map corresponding to the account identifier and/or third party authentication information corresponding to the account identifier;
And determining the account category corresponding to the effective comment information according to the account identifier and the identity association information of the account identifier.
Optionally, the device is also configured to execute the one or more programs by one or more processors, including instructions for:
acquiring related comment information of the target comment information;
extracting target keywords from related comment information of the target comment information;
Marking labels on the target comment information according to the target keywords contained in the related comment information of the target comment information and the duty ratio of the contained target keywords;
And displaying the target comment information in the search result page of the query information according to the account category classification, and further comprising:
and displaying the label corresponding to the target comment information at the relevant position where the target comment information is displayed.
Optionally, the displaying the target comment information according to the account category classification in the search result page of the query information includes:
displaying a comment information interface in a reduced mode in a search result page of the query information, wherein the comment information interface in the reduced mode comprises key information of the target comment information;
And responding to the triggering operation of the comment information interface in the reduced mode, displaying the comment information interface in the unfolding mode, wherein the comment information interface in the unfolding mode comprises at least one tab page, and the tab page is used for displaying target comment information of different account categories.
Optionally, the device is also configured to execute the one or more programs by one or more processors, including instructions for:
and displaying interactive comment information in a bullet screen form in a search result page of the query information, wherein the interactive comment information comprises target comment information corresponding to the target theme and/or filtered comment information related to the target theme.
Fig. 7 is a block diagram illustrating an apparatus 800 for presentation according to an example embodiment. For example, apparatus 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.
Referring to FIG. 7, the apparatus 800 may include one or more of a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.
The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing element 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.
The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice information processing mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to, a home button, a volume button, an activate button, and a lock button.
The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the apparatus 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also exhibit a change in position of the apparatus 800 or one component of the apparatus 800, the presence or absence of user contact with the apparatus 800, an orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on radio frequency information processing (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of apparatus 800 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
Fig. 8 is a schematic diagram of a server in some embodiments of the invention. The server 1900 may vary considerably in configuration or performance and may include one or more central processing units (central processing units, CPUs) 1922 (e.g., one or more processors) and memory 1932, one or more storage mediums 1930 (e.g., one or more mass storage devices) that store applications 1942 or data 1944. Wherein the memory 1932 and storage medium 1930 may be transitory or persistent. The program stored in the storage medium 1930 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, a central processor 1922 may be provided in communication with a storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.
The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input/output interfaces 1958, one or more keyboards 1956, and/or one or more operating systems 1941, such as WindowsServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.
A non-transitory computer readable storage medium, which when executed by a processor of an apparatus (server or terminal), enables the apparatus to perform the presentation method shown in fig. 1.
A non-transitory computer readable storage medium, when executed by a processor of an apparatus (server or terminal), causes the apparatus to perform a presentation method comprising, upon identifying that query information entered by a user hits a target topic, obtaining target comment information corresponding to the target topic, the target comment information including comment information related to the target topic and classified by account category screened from at least one third party platform, and presenting the target comment information by account category classification in a search result page of the query information.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
The foregoing has outlined some of the more detailed description of a display method, a display device and a device for displaying the invention, wherein specific examples are provided herein to illustrate the principles and embodiments of the invention and to help understand the method and core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.