CN113177170B - Comment display method and device and electronic equipment - Google Patents
Comment display method and device and electronic equipment Download PDFInfo
- Publication number
- CN113177170B CN113177170B CN202110393038.XA CN202110393038A CN113177170B CN 113177170 B CN113177170 B CN 113177170B CN 202110393038 A CN202110393038 A CN 202110393038A CN 113177170 B CN113177170 B CN 113177170B
- Authority
- CN
- China
- Prior art keywords
- content
- score
- user
- comment
- target user
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application discloses a comment display method and device and electronic equipment, and belongs to the technical field of computers. The method comprises the following steps: acquiring first content displayed on a display interface; determining, based on the first content, a target user feature from a set of target user features that matches the first content; the target user features comprise a first user feature and a second user feature, and the second user feature is a sub-feature under the first user feature; and displaying comments corresponding to the first content according to the first content and the target user characteristics.
Description
Technical Field
The application belongs to the technical field of computers, and particularly relates to a comment display method and device and electronic equipment.
Background
Under various scenes such as purchasing products and browsing information, users can be involved in comments, and people can often obtain more products, information and the like which are more close to own demands from comments published by other users. In the prior art, when the comments of the user are displayed, the comments are displayed after being sequenced according to the posting time or praise number of the comments, however, the comments cannot meet the personalized requirements of the user, and therefore the user needs to spend a great deal of time in browsing the displayed comments to find the comments meeting the requirements of the user.
Disclosure of Invention
The embodiment of the application aims to provide a comment display method which can solve the problem that comments cannot be displayed in a personalized mode for different users.
In a first aspect, an embodiment of the present application provides a comment exhibiting method, where the method includes:
acquiring first content displayed on a display interface;
determining, based on the first content, a target user feature from a set of target user features that matches the first content; the target user features comprise a first user feature and a second user feature, and the second user feature is a sub-feature under the first user feature;
and displaying comments corresponding to the first content according to the first content and the target user characteristics.
In a second aspect, an embodiment of the present application provides a comment exhibiting device, including:
the acquisition module is used for acquiring the first content displayed on the display interface;
a determining module, configured to determine, based on the first content, a target user feature matching the first content from a target user feature set; the target user features comprise a first user feature and a second user feature, and the second user feature is a sub-feature under the first user feature;
And the display module is used for displaying comments corresponding to the first content according to the first content and the target user characteristics.
In a third aspect, embodiments of the present application provide an electronic device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, the program or instruction implementing the steps of the method according to the first aspect when executed by the processor.
In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a program or instructions which when executed by a processor implement the steps of the method according to the first aspect.
In a fifth aspect, embodiments of the present application provide a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and where the processor is configured to execute a program or instructions to implement a method according to the first aspect.
In the embodiment of the application, after the first content displayed on the display interface is acquired, determining the target user characteristic matched with the first content from the target user characteristic set based on the first content, and displaying the comment corresponding to the first content according to the first content and the matched target user characteristic. Because the target user features comprise the first user features and the second user features, and the second user features are sub-features under the first user features, the second user features can better reflect the preference of the target user for comments, namely, comments can be distinguished according to the preference of the user in a finer granularity, so that comments which are focused and interested by the user can be ranked ahead, and personalized comment display is realized.
Drawings
Fig. 1 is a flowchart of a comment exhibiting method provided in an embodiment of the present application;
fig. 2 to fig. 5 are schematic views of interface display of an electronic device according to an embodiment of the present application;
FIG. 6 is a flow chart of a comment presentation method of one example of the present application;
fig. 7 is a schematic structural diagram of a comment display device according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
Technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The comment display method provided by the embodiment of the application is described in detail through specific embodiments and application scenes thereof with reference to the accompanying drawings.
Please refer to fig. 1, which is a flowchart of a comment showing method provided in an embodiment of the present application. The method can be applied to electronic equipment, and the electronic equipment can be a mobile phone, a tablet personal computer, a notebook personal computer and the like. As shown in fig. 1, the method may include steps S1100 to S1300, which will be described in detail below.
Step S1100, obtaining first content displayed on a display interface.
The first content may be content of a product, information, etc. currently being browsed by the target user. The target user is a user currently browsing the first content such as the product, information, etc.
In one example, the following step of determining a target user feature matching the first content from the target user feature set based on the first content may be performed directly after the first content displayed on the display interface is acquired.
In one example, after the first content displayed on the display interface is acquired, a selection frame for selecting a sorting mode of the comments is provided; and acquiring a sorting mode selected by the target user through the selection frame, so that the following steps of determining target user characteristics matched with the first content from the target user characteristic set based on the first content are executed only when the selected sorting mode is a personalized sorting mode.
It may be understood that, in the case that the selected sorting manner is the default sorting manner, the comment corresponding to the first content may be directly displayed according to the attribute information of the comment, for example, the sorting information of the comment corresponding to the first content may be determined first according to the attribute information, and then the comment corresponding to the first content is displayed according to the sorting information. The attribute information of the comment is, for example, but not limited to, the posting time of the comment, the number of praise of the comment, and the like.
For example, as shown in fig. 2, after the basketball game information with the first content being "team a VS team B" is displayed on the display interface, the electronic device may provide a selection box for selecting the ranking mode of the comments, where the following step of determining, based on the first content, the target user feature matching the first content from the target user feature set may be performed after the target user selects "personalized ranking". Alternatively, as shown in fig. 3, when the target user selects "default ranking", the comments corresponding to the basketball game information, for example, 5 comments, may be ranked according to the posting time of the comments, so that the comments corresponding to the basketball game information, for example, the 5 comments, are displayed.
For example, after the basketball game information of "team a VS team B" is displayed on the display interface, the electronic device may not provide a selection interface for selecting the ranking mode, but directly execute the following steps of determining, based on the first content, the target user feature matching with the first content from the target user feature set, and rank, according to the basketball game information and the target user feature, the comments corresponding to the basketball game information, for example, 5 comments, so as to display the comments corresponding to the basketball game information, for example, the 5 comments.
After the first content displayed by the display interface is acquired, entering:
step S1200 determines, based on the first content, a target user feature matching the first content from the target user feature set.
The target user feature set is a user feature set corresponding to the target user, and is a set formed by user features reflecting the preference of the target user, which are collected in advance based on the historical behaviors of the target user. The target user feature set comprises a plurality of target user features, each target user feature comprises a first user feature and a second user feature, the second user feature is a sub-feature under the first user feature, and each first user feature can correspond to a plurality of second user features.
The above first user features are coarse-grained user features that can reflect the preferences of the target user from a certain level. Illustratively, the first user characteristic may include: basketball, music, entertainment, fun.
The above second user features are fine-grained user features of relatively coarse-grained user features, which can well reflect the preferences of the target user. It will be appreciated that coarse-grained user features and fine-grained user features are relative, e.g., the user is interested in basketball, and that the team supported is team B, which is a relatively coarse-grained user feature, i.e., the first user feature, and team B is a fine-grained user feature, i.e., the second user feature. Illustratively, the second user characteristic may include: team B, team B's player, team C's player, singer 1, singer 2, actor a, actor B, actor C, comedy talk show, vocal community, vocal actor.
Illustratively, the target user feature set includes a plurality of target user features, which may be basketball: [ team B, team B players, team C players ], music: [ singer 1, singer 2], entertainment: [ actor a, actor B, actor C ], and fun: [ comedy talk show, vocal community, vocal actor ], where the target user feature set may be: { basketball } [ team B, team B players, team C players ]; music: [ singer 1, singer 2]; entertainment of actor a, actor b, actor c ]; laughter [ comedy talk show, vocal community, vocal actor ] }.
Continuing with the above example, it may be that after the basketball game information of "team A VS B" is displayed on the display interface, the electronic device determines a target user feature matching the basketball game information "team A VS B" from the set of target user features.
In this embodiment, the determining, in step S1200, the target user feature matching the first content from the target user feature set based on the first content may further include steps S1210 to S1220 as follows:
step S1210, a category label of the first content is acquired.
The category label of the first content may be a category label to which the topic name of the first content belongs.
Continuing with the above example, the category label of basketball game information "team A VS B" is "basketball".
Step S1220, determining a target user feature matching the first content according to the category label of the first content and the target user feature set.
In the step S1220, determining the target user feature matching the first content according to the category label and the target user feature set of the first content may further include the following steps S1221 to S1222:
step S1221, obtaining the alternative target user characteristic according to the category label of the first content and the target user characteristic set.
In step S1221, since the first user feature of the target user is collected according to the category label of the first content, the first user feature of the target user and the category label of the first content adopt the same label system, so that character matching can be directly performed.
Continuing with the example above, the first content displayed by the display interface is basketball game information of "team A VS B", and because the category label of the basketball game information is "basketball", the category label of the basketball game information is character matched with the target user feature set { basketball } [ team B, team B players, team C players ], music: [ singer 1, singer 2], entertainment: [ actor a, actor B, actor C ], and fun: [ comedy talk show, vocal community, vocal actor ] }, and the alternative target user feature "basketball: [ team B, team B players, team C players ]".
Step S1222, obtaining the second user characteristic meeting the third condition from the candidate target user characteristics, and obtaining the processed candidate target user characteristics as the determined target user characteristics matched with the first content.
The third condition includes: the similarity score between the second user feature and the first content is greater than a set second score threshold. The set second score threshold may be a value set according to an actual application scenario and an actual requirement.
In this step S1222, after the candidate target user feature is obtained, since the content name of the first content does not necessarily include all the second user features in the candidate target user feature, the content name of the first content is also matched with the second user features in the candidate target user feature, so as to filter the second user features in the candidate target user feature, that is, fine-grained user features.
In this step S1222, when the second user feature of the candidate target user features satisfies the above third condition, the second user feature is retained, and the retained second user feature and the first user feature are combined to be matched with the target user feature of the first content.
In this step S1222, a semantic relevance score between the content name of the first content and each of the second user features in the candidate target user features may be calculated by using a similarity-LSTM (Long Short-Term Memory) model, and the semantic relevance score is used as a similarity score between the two, where the similarity score is typically a value between 0 and 1, and the closer the similarity score is to 1, the more semantically relevant the second user feature is indicated to the content name of the first content. And comparing the calculated similarity score between the content name of the first content and each second user feature in the candidate target user features with a second score threshold, retaining the corresponding second user feature under the condition that the similarity score is larger than the second score threshold, and filtering the corresponding second user feature under the condition that the similarity score is smaller than or equal to the second score threshold.
Continuing with the example above, the candidate target user characteristics are "basketball: [ team B, team B's members, team C ]", and since the information topic of the basketball game information is named "team a VS team B", the similarity scores between "team B", "team B's members", "team C" and "team a VS team B" are calculated, respectively, the similarity scores p1 of "team B" and "team a VS team B" are obtained, the similarity scores p2 of "team B" and "team a VS team B", and the similarity scores p3 of "team C" and "team a VS team B" are obtained, and since the similarity score p3 between "team C" and "team a VS team B" is less than the second score threshold, the "team B" and "team B" in the candidate target user characteristics are retained, respectively, and the "team B" and "team B" in the candidate target user characteristics are filtered out, and the game information of "team B: [ B, B ]" is obtained as the target team B's matching the game information.
According to the steps S1221 to S1222, for the first content, the target user feature set is semantically matched, and redundant user features which do not conform to the first content are filtered, so that the data processing efficiency is improved.
After determining, based on the first content, a target user feature from the set of target user features that matches the first content, entering:
step S1300, displaying comments corresponding to the first content according to the first content and the target user characteristics.
In this embodiment, after determining, based on the first content, the target user feature matching the first content from the target user feature set according to the above step S1200, the comment corresponding to the first content may be displayed according to the first content and the target user feature according to the present step S1300.
In this embodiment, according to the first content and the target user feature in the present step S1300, displaying the comment corresponding to the first content may further include the following steps S1331 to S1335:
step S1331, obtaining a user association degree score between the comment corresponding to the first content and the target user feature.
The user relevance score can reflect the relevance between the comment and the target user feature. The user relevance score is typically a number between 0-1, where a higher user relevance score indicates that the comment is more relevant to the target user feature.
In step S1331, a user association score between the comment corresponding to the first content and the target user feature may be obtained according to a preset first model. The input of the preset first model is any comment and target user characteristic corresponding to the first content, and the output is the calculated user association degree score between the comment and the target user characteristic. The preset first model may be a neural network model, for example, but not limited to, a BP (Back Propagation) neural network model, a convolutional neural network model, etc., and the embodiment is not specifically limited herein.
Continuing with the above example, the target user characteristic of "team A VS team B" in accordance with the basketball game information is "basketball: [ team B, team B players ]", where a relevance score between the comment corresponding to the basketball game information and "basketball: [ team B, team B players ]", may be calculated. For example, comment 1 [ team A fueling ]! Support your-! The relevance score between "basketball: [ team B, team B players ]" is used as the user relevance score for comment 1, and comment 2 [ team B general champion ]! The following is carried out The relevance score between the basketball team and the basketball team is used as the user relevance score of the comment 2, and if the user relevance score of the comment 2 is higher than the user relevance score of the comment 1, the comment 2 is more relevant to the target user characteristics.
Step S1332, obtaining content association scores between comments corresponding to the first content and the first content.
The content relevance score can reflect a relevance between the comment and the first content. The content relevance score is typically a number between 0-1, where a higher content relevance score indicates that the comment is more relevant to the first content.
In this step S1332, a content association score between the comment corresponding to the first content and the first content may be obtained according to a preset second model. The input of the preset second model is any comment corresponding to the first content and the first content, and the output is the calculated content association degree score between the comment and the first content. The preset second model may be a neural network model, for example, but not limited to, a BP (Back Propagation) neural network model, a convolutional neural network model, etc., and the embodiment is not specifically limited herein.
Continuing with the above example, the target user characteristic corresponding to the basketball game information "team A VS team B" is "basketball: [ team B, team B players ]", where the correlation score between the comment corresponding to the basketball game information and the basketball game information may be calculated. For example, comment 1 [ team A fueling ]! Support your-! The relevance score between the basketball game information is used as the content relevance score of comment 1, comment 2 [ team B general champion ]! The following is carried out The relevance score with the basketball game information is used as the content relevance score of comment 2, and comment 3 [ comment area says what is? And the relevance score between the basketball game information is used as the content relevance score of the comment 3, and in the comment, the comment 3 has low relevance to the basketball game information content, so that the quality of the comment 3 is not high.
It should be noted that, the method can be that a Listwise method is adopted to train the preset first model and the preset second model respectively, and in the training process, the model can receive a plurality of comments at one time, and the model can better distinguish the quality and the bad quality of the comments through the contrast learning of different comments. In an actual scene, ordering labels can be built according to facts such as praise or browsing time of a user and the like and comments in a comment set, and the data are used for training a model, so that an output result of the model is consistent with the ordering labels as much as possible.
According to this step S1332, since the comments really intended by the user cannot be completely screened out only by virtue of the relevance of the comments to the user characteristics, the comments are scored from the dimension of the quality of the comments, and the higher the quality, the higher the score is the more appropriate the content and information of the comments; and the scores of the irrigation comments, irrelevant comments, and unintelligible comments may be lower.
Step S1333, fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain the target score of the comment corresponding to the first content.
In this embodiment, in step S1333, the user relevance score and the content relevance score of the comment corresponding to the first content are fused, and the obtaining of the target score of the comment corresponding to the first content may further include the following steps S1333-1 to S1333-3:
step S1333-1, fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain the fused score of the comment corresponding to the first content.
In this step S1333-1, the user relevance Score and the content relevance Score of each comment may be linearly fused to obtain the target Score of each comment, where the user relevance Score and the content relevance Score of the comment may be fused by using the following linear function to obtain the target Score of the ith comment i ：
Score i ＝S i1 *m+S i2 *(1-m) (1)
Wherein i is an integer of 1 to n, n is the total number of comments corresponding to the first content, S i1 S is the user association score of the ith comment calculated according to the above step S1331 i2 For the content relevance score of the i-th comment calculated according to the above step S1332, m is a parameter value smaller than 1, which represents the importance degree of the user relevance score.
According to the step S1333, the fused scores are used as the final sorting basis, so that the relation between comments and user characteristics and the quality of the comments are comprehensively considered.
And S1333-2, obtaining the emotion polarity score of the comment corresponding to the first content.
The emotion polarity of a comment indicates whether the predisposed emotion represented by the comment is positive or negative. The emotion polarity score of a comment is usually a numerical value between 0 and 1, and the higher the emotion polarity score of the comment is, the higher the probability that the emotion polarity of the comment is positive is, the lower the emotion polarity score of the comment is, and the higher the probability that the emotion polarity of the comment is negative is.
In this step S1333-2, the emotion polarity score of the comment may be calculated using a bidirectional LSTM model, where the input of the bidirectional LSTM model is the comment and the output is the emotion polarity score of the comment.
And S1333-3, obtaining the target score of the comment corresponding to the first content according to the emotion polarity score and the fusion score of the comment corresponding to the first content.
In this step S1333-3, the target score final of the ith comment may be calculated using the following formula i ：
final i ＝Score i *S i3 (2)
Wherein Score i Representing a fused score of the ith comment, S i3 And (5) representing the emotion polarity score of the ith comment.
According to the step S1333-3, the emotion polarity score of the comment is calculated, and the comment which has high correlation degree of the user characteristics but does not accord with the preference of the user in emotion polarity is subjected to weight reduction processing.
Step S1334, determining ranking information of the comments corresponding to the first content according to the target score of the comments corresponding to the first content.
In this embodiment, after the target score of the comment corresponding to the first content is obtained according to the above step S1333, the comment corresponding to the first content may be ranked according to the present step S1334, so as to obtain ranking information of the comment corresponding to the first content.
Continuing with the above example, as shown in FIG. 3, the set of comments for the basketball game information above includes 5 comments [ team A refuel ]! Support your-! Is the talk of? "I feel the requisite for team A }, { I wish to win team B }, { team B general champion-! The following is carried out [ MEANS FOR SOLVING PROBLEMS ], wherein, as shown in FIG. 2, the comments issued by user 5 [ team B general champion ]! The following is carried out The target score of the comment (I hope for B team win) issued by the user 4 is larger than the target score of the comment (I hope for B team win) issued by the user 1, the target score of the comment (I hope for B team win) is larger than the target score of the comment (A team refuel-! Support your-! Target score of ]! Support your-! The target score of [ [ i feel ] of team a must be found ] of the comments made by user 3 is greater than the target score of [ [ i feel ] of team a must be found ] of the comments made by user 3, and the target score of [ i feel ] of team a must be found ] of the comments made by user 2 is greater than the target score of [ i feel ] of the comments made by user 2? Target score. Here, the 5 comments corresponding to the basketball game information are ranked according to the target scores of the 5 comments, and the obtained ranking information is, for example, a ranking label of [ 3,5,4,2,1 ].
Step S1335, displaying comments corresponding to the first content according to the ordering information.
In this embodiment, after the ranking information of the comments corresponding to the first content is obtained according to the above step S1334, the comments corresponding to the first content may be displayed according to the ranking information according to the present step S1335.
Continuing with the above example, 5 comments included in the comment set of basketball game information above [ team A refuels ]! Support your-! Is the talk of? "I feel the requisite for team A }, { I wish to win team B }, { team B general champion-! The following is carried out The ranking information corresponding to the ranking information is, for example, the ranking label is [ 3,5,4,2,1 ], and here, as shown in fig. 2, the 5 comments corresponding to the basketball game information are displayed according to the ranking label [ 3,5,4,2,1 ].
In the embodiment of the application, after the first content displayed on the display interface is acquired, determining the target user characteristic matched with the first content from the target user characteristic set based on the first content, and displaying the comment corresponding to the first content according to the first content and the target user characteristic. Because the target user features comprise the first user features and the second user features, and the second user features are sub-features under the first user features, the second user features can better reflect the preference of the target user for comments, namely, comments can be distinguished according to the preference of the user in a finer granularity, so that comments which are focused and interested by the user can be ranked ahead, and personalized comment display is realized.
It should be noted that, in the comment display method provided by the embodiment of the present application, the execution subject may be a comment display device, or a control module in the comment display device for executing the comment display method. In the embodiment of the application, a comment display method executed by a comment display device is taken as an example, and the comment display method provided by the embodiment of the application is described.
In one embodiment, before determining, based on the first content, the target user feature matching the first content from the target user feature set according to the above step S1200, the comment presentation method further includes a step of acquiring the target user feature set, which may further include steps S1010 to S1040 as follows:
step S1010, obtaining a first user characteristic of a target user and text information corresponding to the target user.
For example, as shown in fig. 4, when the target user registers any xx application program, a category label of interest is selected in the xx application program, where the category label may be referred to as a first user feature of the target user, and since the category label selected by the target user is: basketball, music, entertainment, fun, where the first user characteristics of the target user may be: basketball, music, entertainment, fun.
For another example, when the target user browses information by using the xx application program, the category label of the information frequently browsed by the target user may be used as the first user feature, and if the category label of the information frequently browsed by the target user is smiling, the first user feature may be: and (5) making a joke.
Illustratively, the first user characteristics of the target user that are collected include { basketball, music, entertainment, fun }.
The text information corresponding to the target user is the text information of interest to the target user. The text information corresponding to the target user includes comments and/or second content, which may be, for example, comments and/or second content of interest to the target user. And, the second content has the same category attribute as the first content, for example, when the first content is information, the text information corresponding to the target user may include comments and/or history information of interest to the target user, and specifically, may be comments and/or history information praised by the target user.
For example, as shown in fig. 5, after the target user enters the comment interface, the comments "general champion of the B team" (comments posted by the user 5) and "4-2A team" (comments posted by the user 6) that the target user likes (comments are praised by black circles in the figure) may be used as text information that the target user is interested in.
Step S1020, classifying the text information according to the first class label of the first user feature to obtain a second class label of the text information.
The first category label of the first user feature may be a name of the first user feature. Illustratively, the first user characteristics of the target user that are collected include { basketball, music, entertainment, fun }, where the first category labels of the first user characteristics are { basketball, music, entertainment, fun }, respectively.
In step S1020, after the text information corresponding to the target user is collected, the text information is classified according to the first class labels of the first user features, and the text information of different classes is aggregated to obtain the second class labels of the text information. By way of example, the second category labels of the text information may be { basketball, music, entertainment, fun }, for example, the category labels of the above text information "general champion of team B" and "team B4-2A" are both "basketball".
Step S1030, obtaining the second user characteristics of the target user according to the second class labels.
In this embodiment, according to the second category label in the step S1030, obtaining the second user characteristic of the target user may further include the following steps S1030-1 to S1030-3:
And step S1030-1, obtaining keywords meeting the first condition from the second category labels to obtain alternative keywords corresponding to the second category labels.
In step S1030-1, keywords in text information included in each second-class label are extracted first, a corresponding relationship between the keywords and the second-class labels is established, and then keywords satisfying the first condition are obtained from the second-class labels, so as to obtain alternative keywords corresponding to the second-class labels.
Continuing the above example, keyword extraction is performed on the text information "general champion of the B team" and "team 4-2A team" respectively, and keywords are extracted: team B, team A, because the text information "team B general champion" and the second category labels of team B4-2A "are: basketball, here, keyword: "team B" and "team A" are keywords in the second category labels.
The first condition includes: the co-occurrence ratio of the keywords is greater than a set duty cycle threshold. The co-occurrence ratio of the keywords is equal to the ratio of the number of text messages containing the keywords under the second category label to the total number of text messages containing the keywords under the second category label, specifically, the co-occurrence ratio x of the q-th keyword containing the j-th second category label can be calculated according to the following formula q ：
Wherein w is q Representing the number of text messages containing the q-th keyword under the j-th second category label, w Total (S) Representing the total number of text messages under the j-th second category label.
The set duty ratio threshold value can be a numerical value set according to the actual application scene and the actual requirement.
In step S1030-1, when the keyword in the second category label satisfies the above first condition, the keyword is reserved, and the reserved keyword is used as an alternative keyword in the second category label.
In step S1031, the co-occurrence ratio of the keywords in each of the second category labels is calculated. And comparing the calculated co-occurrence ratio of the keywords with a set duty ratio threshold, retaining the corresponding keywords under the condition that the co-occurrence ratio is larger than the set duty ratio threshold, and filtering the corresponding keywords under the condition that the co-occurrence ratio is smaller than or equal to the set duty ratio threshold.
Continuing the above example, keyword extraction is performed on the text information "general champion of the B team" and "team 4-2A team" respectively, and the extracted keywords are: and respectively calculating the co-occurrence ratios of the 'B team' and the 'A team', wherein the 'A team' is filtered out and only the 'B team' is reserved because the co-occurrence ratio of the 'A team' is smaller than a set duty ratio threshold value.
And step S1030-2, obtaining the keywords meeting the second condition from the alternative keywords to obtain the processed alternative keywords.
The second condition includes: the emotion polarity score of the keyword is larger than a set first score threshold. The emotion polarity score of the keyword is equal to the average value of emotion polarity scores of text information containing the keyword under the second category label, specifically, the emotion polarity score x of the q-th keyword under the j-th second category label can be calculated by using the following formula q ：
Wherein m represents the number of text information containing the q-th keyword under the j-th second category label,
representing the j-th second class labelThe emotion polarity score of the p-th text information containing the q-th keyword can be calculated using the following formula>
Wherein, when the p text information of the q-th keyword has obvious user preference characteristics, the emotion polarity score of the text information is 1, for example, the text information of the user praise can be basically judged to be in accordance with the user preference; otherwise, calculating the emotion polarity score of the text information by adopting a bidirectional LSTM model, wherein the emotion polarity score which is closer to 1 indicates that the text information is more likely to be forward emotion.
The set first score threshold may be a numerical value set according to an actual application scenario and an actual requirement.
According to the step, the average value of emotion polarity scores of all text information containing the keyword in the second category label is used as the emotion polarity score of the keyword, the keyword with emotion polarity score smaller than or equal to a set first score threshold is filtered, and the keyword with emotion polarity score larger than the set first score threshold is reserved as a final second user feature.
And step S1030-3, obtaining the second user characteristics of the target user according to the processed candidate keywords.
Illustratively, the second user features corresponding to the second category label "basketball" are { team B, team B players, team C players }, the second user features corresponding to the second category label "music" are { singer 1, singer 2}, the second user features corresponding to the second category label "entertainment" are { actor a, actor B, actor C }, and the second user features corresponding to the second category label "joke" are { comedy talk show, vocal community, vocal actors }.
In this step S1030-3, keywords with emotion polarity scores greater than the set first score threshold are retained as final second user features.
Step S1040, according to the first category label and the second category label, the first user feature and the second user feature are combined to obtain a target user feature set.
Illustratively, the first user feature { basketball, music, entertainment, fun } and the second user feature { B team, team player, C team player, singer 1, singer 2, actor a, actor B, actor C, comedy talk show, voice community, voice actor } are combined according to the first category label { basketball, music, entertainment, fun } and the second category label { basketball, music, entertainment, fun }, to obtain a plurality of target user features, which may be basketball: [ team B, team B player, music: [ player 1, singer 2], entertainment: [ actor a, actor B, actor C ], and fun: [ comedy talk show, actor voice community ], where the target user feature set may be: { basketball } [ team B, team B players, team C players ]; music: [ singer 1, singer 2]; entertainment [ actor a, actor b, actor c ]; laughter [ comedy talk show, vocal community, vocal actor ] }.
According to the embodiment of the disclosure, emotion analysis and content understanding can be performed on the historical behaviors of the target user, so that first user characteristics and second user characteristics which accord with user preferences are mined, and a target user characteristic set is constructed.
Next, taking the first content as information as an example, a comment exhibiting method of an example is shown, as shown in fig. 6, in which the comment exhibiting method includes the steps of:
step S6010, obtaining information displayed on the display interface.
In step S6020, the display interface provides a selection frame for selecting the ranking mode of the comments, and in the case where the ranking mode of the comments selected by the user is the personalized ranking mode, the following step S6030 is executed, whereas the following step S6070 is executed.
Step S6030, acquiring a target user feature set.
The target user is a user browsing the information, and the target user features include a first user feature and a second user feature.
In step S6030, the first user feature of the target user and the text information corresponding to the target user may be obtained first, and the text information is classified according to the first class label of the first user feature to obtain the second class label of the text information; then extracting keywords in the text information, and establishing a corresponding relation between the keywords and the second category labels; meanwhile, obtaining keywords meeting the first condition from each second category label to obtain alternative keywords of each second category label, and obtaining keywords meeting the second condition from each alternative keyword to obtain processed alternative keywords; and finally, according to each processed alternative keyword, obtaining a second user characteristic of the target user, and according to the first category label and the second category label, combining the first user characteristic and the second user characteristic to obtain a target user characteristic set.
Step S6040, determining the target user characteristics matched with the information from the target user characteristic set according to the information displayed on the display interface.
In step S6040, the category label of the information is matched with the first user feature in the target user feature set to obtain the first user feature and each second user feature according with the information; and secondly, matching the content of the information with each second user characteristic, screening out the second user characteristics related to the semantics of the information content, and combining the first user characteristics conforming to the information with the second user characteristics reserved after screening to serve as target user characteristics matched with the information.
Step S6050, determining the target score of the comment corresponding to the information according to the information and the matched target user characteristics.
In step S6050, a user association score between a comment corresponding to the information and a target user feature is obtained according to a preset first model, a content association score between a comment corresponding to the information and a content of the information is obtained according to a preset second model, and the user association score and the content association score of each comment are fused to obtain a fusion score of each comment; and then, the emotion polarity score of each comment is obtained, and the target score of each comment is obtained according to the emotion polarity score of each comment and the corresponding fusion score.
Step S6060, determining the ranking information of the comments corresponding to the information according to the target scores of the comments corresponding to the information, and executing step S6080.
Step S6070, determining the ranking information of the comments corresponding to the information according to the attribute information of the comments.
Step S6080, displaying the comments corresponding to the information according to the ordering information.
Corresponding to the above embodiment, referring to fig. 7, the embodiment of the present application further provides a comment exhibiting device 700, including:
the acquiring module 7100 is configured to acquire first content displayed on the display interface.
A determining module 7200 for determining a target user feature matching the first content from a set of target user features based on the first content; the target user features comprise a first user feature and a second user feature, and the second user feature is a sub-feature under the first user feature.
And a display module 7300, configured to display a comment corresponding to the first content according to the first content and the target user feature.
In one embodiment, the acquiring module 7100 is further configured to: acquiring a first user characteristic of a target user and text information corresponding to the target user; wherein the text information comprises comments and/or second content; classifying the text information according to the first class label of the first user characteristic to obtain a second class label of the text information; obtaining second user characteristics of the target user according to the second class labels; and combining the first user characteristic and the second user characteristic according to the first class label and the second class label to obtain the target user characteristic set.
In one embodiment, the acquiring module 7100 is specifically configured to: obtaining keywords meeting a first condition from the second category labels to obtain alternative keywords corresponding to the second category labels; obtaining keywords meeting a second condition from the alternative keywords to obtain processed alternative keywords; and obtaining the second user characteristics of the target user according to the processed alternative keywords.
The first condition includes: the co-occurrence ratio of the keywords is larger than a set duty ratio threshold, and the co-occurrence ratio of the keywords is equal to the ratio of the number of text messages containing the keywords under the second category labels to the total number of text messages containing the keywords under the second category labels.
The second condition includes: the emotion polarity score of the keyword is larger than a set first score threshold, and the emotion polarity score of the keyword is equal to the average value of emotion polarity scores of text information containing the keyword under the second category label.
In one embodiment, the determining module 7300 is specifically configured to: obtaining a user association degree score between the comment corresponding to the first content and the target user characteristic; acquiring a content association degree score between the comment corresponding to the first content and the first content; fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain a target score of the comment corresponding to the first content; determining ordering information of comments corresponding to the first content according to the target score of comments corresponding to the first content; and displaying the comments corresponding to the first content according to the ordering information.
In one embodiment, the determining module 7300 is specifically configured to: fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain the fused score of the comment corresponding to the first content; acquiring the emotion polarity score of the comment corresponding to the first content; and obtaining the target score of the comment corresponding to the first content according to the emotion polarity score and the fusion score of the comment corresponding to the first content.
The comment display device in the embodiment of the application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. By way of example, the mobile electronic device may be a cell phone, tablet computer, notebook computer, palm computer, vehicle-mounted electronic device, wearable device, ultra-mobile personal computer (ultra-mobile personal computer, UMPC), netbook or personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device may be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., and the embodiments of the present application are not limited in particular.
The comment presentation device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.
The comment display device provided in the embodiment of the present application can implement each process implemented by the foregoing method embodiment, and in order to avoid repetition, details are not repeated here.
In correspondence to the above embodiment, optionally, as shown in fig. 8, the embodiment of the present application further provides an electronic device 800, including a processor 801, a memory 802, and a program or an instruction stored in the memory 802 and capable of running on the processor 801, where the program or the instruction implements each process of the above embodiment of the evaluation and display method when executed by the processor 801, and the process can achieve the same technical effect, and is not repeated herein.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device described above.
Fig. 9 is a schematic hardware structure of an electronic device implementing an embodiment of the present application.
The electronic device 900 includes, but is not limited to: radio frequency unit 901, network module 902, audio output unit 903, input unit 904, sensor 905, display unit 906, user input unit 907, interface unit 908, memory 909, and processor 910.
Those skilled in the art will appreciate that the electronic device 900 may also include a power source (e.g., a battery) for powering the various components, which may be logically connected to the processor 910 by a power management system to perform functions such as managing charge, discharge, and power consumption by the power management system. The electronic device structure shown in fig. 9 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than shown, or may combine certain components, or may be arranged in different components, which are not described in detail herein.
The processor 910 is configured to obtain first content displayed on the display interface; determining, based on the first content, a target user feature from a set of target user features that matches the first content; the target user features comprise a first user feature and a second user feature, and the second user feature is a sub-feature under the first user feature; and displaying comments corresponding to the first content according to the first content and the target user characteristics.
In one embodiment, the processor 910 is further configured to obtain a first user characteristic of a target user, and text information corresponding to the target user; wherein the text information comprises comments and/or second content; classifying the text information according to the first class label of the first user characteristic to obtain a second class label of the text information; obtaining second user characteristics of the target user according to the second class labels; and combining the first user characteristic and the second user characteristic according to the first class label and the second class label to obtain the target user characteristic set.
In one embodiment, the processor 910 is further configured to obtain, from the second category label, a keyword that meets the first condition, and obtain an alternative keyword corresponding to the second category label; obtaining keywords meeting a second condition from the alternative keywords to obtain processed alternative keywords; and obtaining the second user characteristics of the target user according to the processed alternative keywords.
In one embodiment, the processor 910 is further configured to obtain a user association score between the comment corresponding to the first content and the target user feature; acquiring a content association degree score between the comment corresponding to the first content and the first content; fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain a target score of the comment corresponding to the first content; determining ordering information of comments corresponding to the first content according to the target score of comments corresponding to the first content; and displaying the comments corresponding to the first content according to the ordering information.
In one embodiment, the processor 910 is further configured to fuse the user relevance score and the content relevance score of the comment corresponding to the first content, and obtain a fused score of the comment corresponding to the first content; acquiring the emotion polarity score of the comment corresponding to the first content; and obtaining the target score of the comment corresponding to the first content according to the emotion polarity score and the fusion score of the comment corresponding to the first content.
It should be appreciated that in embodiments of the present application, the input unit 904 may include a graphics processor (Graphics Processing Unit, GPU) 9041 and a microphone 9042, with the graphics processor 9041 processing image data of still pictures or video obtained by an image capture device (e.g., a camera) in a video capture mode or an image capture mode. The display unit 906 may include a display panel 9061, and the display panel 9061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 907 includes a touch panel 9071 and other input devices 9072. Touch panel 9071, also referred to as a touch screen. The touch panel 9071 may include two parts, a touch detection device and a touch controller. Other input devices 9072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein. Memory 909 may be used to store software programs as well as various data including, but not limited to, application programs and an operating system. The processor 910 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 910.
The embodiment of the application further provides a readable storage medium, on which a program or an instruction is stored, where the program or the instruction realizes each process of the embodiment of the evaluation display method when executed by a processor, and the same technical effect can be achieved, so that repetition is avoided, and no further description is given here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium such as a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
The embodiment of the application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled with the processor, and the processor is used for running a program or an instruction, so as to implement each process of the embodiment of the evaluation display method, and achieve the same technical effect, so that repetition is avoided, and no redundant description is provided here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are also within the protection of the present application.
Claims (8)
1. A comment presentation method, the method comprising:
acquiring first content displayed on a display interface;
determining, based on the first content, a target user feature from a set of target user features that matches the first content; the target user features comprise a first user feature and a second user feature, and the second user feature is a sub-feature under the first user feature;
displaying comments corresponding to the first content according to the first content and the target user characteristics;
before the determining, based on the first content, a target user feature matching the first content from a set of target user features, further comprising:
acquiring a first user characteristic of a target user and text information corresponding to the target user; wherein the text information comprises comments and/or second content;
classifying the text information according to the first class label of the first user characteristic to obtain a second class label of the text information;
obtaining keywords meeting a first condition from the second category labels to obtain alternative keywords corresponding to the second category labels; wherein the first condition includes: the co-occurrence ratio of the keywords is larger than a set duty ratio threshold value, and the co-occurrence ratio of the keywords is equal to the ratio of the number of text messages containing the keywords under the second category labels to the total number of text messages containing the keywords under the second category labels;
Obtaining keywords meeting a second condition from the alternative keywords to obtain processed alternative keywords; wherein the second condition includes: the emotion polarity score of the keyword is larger than a set first score threshold value, and the emotion polarity score of the keyword is equal to the average value of emotion polarity scores of text information containing the keyword under the second category label;
obtaining second user characteristics of the target user according to the processed alternative keywords;
and combining the first user characteristic and the second user characteristic according to the first class label and the second class label to obtain the target user characteristic set.
2. The method of claim 1, wherein the presenting the comment corresponding to the first content according to the first content and the target user characteristic comprises:
obtaining a user association degree score between the comment corresponding to the first content and the target user characteristic;
acquiring a content association degree score between the comment corresponding to the first content and the first content;
fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain a target score of the comment corresponding to the first content;
Determining ordering information of comments corresponding to the first content according to the target score of comments corresponding to the first content;
and displaying the comments corresponding to the first content according to the ordering information.
3. The method of claim 2, wherein the fusing the user relevance score and the content relevance score for the comment corresponding to the first content to obtain the target score for the comment corresponding to the first content, further comprises:
fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain the fused score of the comment corresponding to the first content;
acquiring the emotion polarity score of the comment corresponding to the first content;
and obtaining the target score of the comment corresponding to the first content according to the emotion polarity score and the fusion score of the comment corresponding to the first content.
4. A comment presentation apparatus characterized by comprising:
the acquisition module is used for acquiring the first content displayed on the display interface;
a determining module, configured to determine, based on the first content, a target user feature matching the first content from a target user feature set; the target user features comprise a first user feature and a second user feature, and the second user feature is a sub-feature under the first user feature;
The display module is used for displaying comments corresponding to the first content according to the first content and the target user characteristics;
wherein, the acquisition module is further configured to: acquiring a first user characteristic of a target user and text information corresponding to the target user; wherein the text information comprises comments and/or second content;
classifying the text information according to the first class label of the first user characteristic to obtain a second class label of the text information;
obtaining keywords meeting a first condition from the second category labels to obtain alternative keywords corresponding to the second category labels; wherein the first condition includes: the co-occurrence ratio of the keywords is larger than a set duty ratio threshold value, and the co-occurrence ratio of the keywords is equal to the ratio of the number of text messages containing the keywords under the second category labels to the total number of text messages containing the keywords under the second category labels;
obtaining keywords meeting a second condition from the alternative keywords to obtain processed alternative keywords; wherein the second condition includes: the emotion polarity score of the keyword is larger than a set first score threshold value, and the emotion polarity score of the keyword is equal to the average value of emotion polarity scores of text information containing the keyword under the second category label;
Obtaining second user characteristics of the target user according to the processed alternative keywords;
and combining the first user characteristic and the second user characteristic according to the first class label and the second class label to obtain the target user characteristic set.
5. The device according to claim 4, wherein the display module is specifically configured to:
obtaining a user association degree score between the comment corresponding to the first content and the target user characteristic;
acquiring a content association degree score between the comment corresponding to the first content and the first content;
fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain a target score of the comment corresponding to the first content;
determining ordering information of comments corresponding to the first content according to the target score of comments corresponding to the first content;
and displaying the comments corresponding to the first content according to the ordering information.
6. The device according to claim 5, wherein the display module is specifically configured to:
fusing the user relevance score and the content relevance score of the comment corresponding to the first content to obtain the fused score of the comment corresponding to the first content;
Acquiring the emotion polarity score of the comment corresponding to the first content;
and obtaining the target score of the comment corresponding to the first content according to the emotion polarity score and the fusion score of the comment corresponding to the first content.
7. An electronic device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the comment presentation method of any of claims 1-3.
8. A readable storage medium having stored thereon a program or instructions which when executed by a processor performs the steps of the comment presentation method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110393038.XA CN113177170B (en) | 2021-04-12 | 2021-04-12 | Comment display method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110393038.XA CN113177170B (en) | 2021-04-12 | 2021-04-12 | Comment display method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113177170A CN113177170A (en) | 2021-07-27 |
| CN113177170B true CN113177170B (en) | 2023-05-23 |
Family
ID=76923570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110393038.XA Active CN113177170B (en) | 2021-04-12 | 2021-04-12 | Comment display method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113177170B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113515663A (en) * | 2021-08-03 | 2021-10-19 | 广州酷狗计算机科技有限公司 | Comment information display method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271512A (en) * | 2018-08-29 | 2019-01-25 | 中国平安保险(集团)股份有限公司 | The sentiment analysis method, apparatus and storage medium of public sentiment comment information |
| CN110134880A (en) * | 2019-05-20 | 2019-08-16 | 北京字节跳动网络技术有限公司 | Offer, display methods, device, electronic equipment and the storage medium of comment data |
| CN111309213A (en) * | 2020-03-12 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Comment display method and device, electronic equipment and storage medium |
| CN112256166A (en) * | 2020-09-23 | 2021-01-22 | 北京达佳互联信息技术有限公司 | Comment information display method and device and electronic equipment |
| WO2021016760A1 (en) * | 2019-07-26 | 2021-02-04 | 深圳市欢太科技有限公司 | Application pushing method and related device |
Family Cites Families (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013049529A1 (en) * | 2011-09-30 | 2013-04-04 | Technicolor Usa Inc | Method and apparatus for unsupervised learning of multi-resolution user profile from text analysis |
| US20140278986A1 (en) * | 2013-03-14 | 2014-09-18 | Clipfile Corporation | Tagging and ranking content |
| CN103399916A (en) * | 2013-07-31 | 2013-11-20 | 清华大学 | Internet comment and opinion mining method and system on basis of product features |
| CN104156390A (en) * | 2014-07-07 | 2014-11-19 | 乐视网信息技术（北京）股份有限公司 | Comment recommendation method and system |
| US10482090B2 (en) * | 2015-11-16 | 2019-11-19 | Facebook, Inc. | Ranking and filtering comments based on feed interaction history |
| US10341278B2 (en) * | 2016-08-08 | 2019-07-02 | Flipboard, Inc. | Adaptive presentation of comments based on sentiment |
| US10579625B2 (en) * | 2016-09-15 | 2020-03-03 | Walmart Apollo, Llc | Personalized review snippet generation and display |
| JP2017201543A (en) * | 2017-06-14 | 2017-11-09 | 株式会社Ｕｂｉｃ | Data analysis system, data analysis method, data analysis program, and recording media |
| CN108153856B (en) * | 2017-12-22 | 2022-09-06 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN108268619B (en) * | 2018-01-08 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Content recommendation method and device |
| CN108363790B (en) * | 2018-02-12 | 2021-10-22 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and storage medium for evaluating comments |
| CN108449642A (en) * | 2018-04-03 | 2018-08-24 | 优视科技有限公司 | A kind of screening display methods, device and the terminal device of video comments |
| US20200257762A1 (en) * | 2019-02-08 | 2020-08-13 | Royal Caribbean Cruises Ltd. | Text classification and sentimentization with visualization |
| CN109885770B (en) * | 2019-02-20 | 2022-01-07 | 杭州威佩网络科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN110428276B (en) * | 2019-06-21 | 2022-12-09 | 口碑(上海)信息技术有限公司 | Method, device and storage medium for selecting offline advertisement delivery area |
| CN110489553B (en) * | 2019-07-26 | 2022-07-05 | 湖南大学 | Multi-source information fusion-based emotion classification method |
| CN111460819B (en) * | 2020-03-31 | 2023-06-20 | 湖南大学 | Personalized comment text recommendation system and recommendation method based on fine granularity emotion analysis |
| CN111479169A (en) * | 2020-04-17 | 2020-07-31 | 广州华多网络科技有限公司 | Video comment display method, electronic equipment and computer storage medium |
| CN111638819B (en) * | 2020-05-21 | 2021-12-07 | 北京达佳互联信息技术有限公司 | Comment display method, device, readable storage medium and system |
| CN111966267A (en) * | 2020-07-31 | 2020-11-20 | 维沃移动通信有限公司 | Application comment method and device and electronic equipment |
| CN112069402B (en) * | 2020-08-28 | 2021-04-20 | 山东省人工智能研究院 | Personalized comment recommendation method based on emotion and graph convolution neural network |
-
2021
- 2021-04-12 CN CN202110393038.XA patent/CN113177170B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271512A (en) * | 2018-08-29 | 2019-01-25 | 中国平安保险(集团)股份有限公司 | The sentiment analysis method, apparatus and storage medium of public sentiment comment information |
| CN110134880A (en) * | 2019-05-20 | 2019-08-16 | 北京字节跳动网络技术有限公司 | Offer, display methods, device, electronic equipment and the storage medium of comment data |
| WO2021016760A1 (en) * | 2019-07-26 | 2021-02-04 | 深圳市欢太科技有限公司 | Application pushing method and related device |
| CN111309213A (en) * | 2020-03-12 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Comment display method and device, electronic equipment and storage medium |
| CN112256166A (en) * | 2020-09-23 | 2021-01-22 | 北京达佳互联信息技术有限公司 | Comment information display method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113177170A (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240086413A1 (en) | Methods, systems, and media for presenting search results | |
| CN109196496B (en) | Unknown word predictor and content integrated translator | |
| Shah et al. | Multimodal analysis of user-generated multimedia content | |
| US8549016B2 (en) | System and method for providing robust topic identification in social indexes | |
| US10198506B2 (en) | System and method of sentiment data generation | |
| US9460193B2 (en) | Context and process based search ranking | |
| US20130018875A1 (en) | System and method for ordering semantic sub-keys utilizing superlative adjectives | |
| US10311113B2 (en) | System and method of sentiment data use | |
| Guo et al. | LD-MAN: Layout-driven multimodal attention network for online news sentiment recognition | |
| US20170344631A1 (en) | Task completion using world knowledge | |
| Crestani et al. | Mobile information retrieval | |
| US11797590B2 (en) | Generating structured data for rich experiences from unstructured data streams | |
| Raghuvanshi et al. | A brief review on sentiment analysis | |
| US20180373719A1 (en) | Dynamic representation of suggested queries | |
| CN113177170B (en) | Comment display method and device and electronic equipment | |
| Feldman | The answer machine | |
| CN111752436A (en) | Recommendation method and device and recommendation device | |
| Zhu et al. | Intelligent product redesign strategy with ontology-based fine-grained sentiment analysis | |
| CN114611023A (en) | Search result display method, device, equipment, medium and program product | |
| Shah et al. | Multimodal semantics and affective computing from multimedia content | |
| CN111831938A (en) | Information display method, information display device, electronic equipment and medium | |
| Heimonen | Design and evaluation of user interfaces for mobile web search | |
| Dende | Sentimental Analysis in crime detection: A case study of Kenya law enforcement agencies | |
| RU2708790C2 (en) | System and method for selecting relevant page items with implicitly specifying coordinates for identifying and viewing relevant information | |
| Lops et al. | Adaptive and Personalized Systems Based on Semantics |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |