CN114237460B - Label display method, device, terminal, storage medium and computer program product - Google Patents
Label display method, device, terminal, storage medium and computer program product Download PDFInfo
- Publication number
- CN114237460B CN114237460B CN202111199807.9A CN202111199807A CN114237460B CN 114237460 B CN114237460 B CN 114237460B CN 202111199807 A CN202111199807 A CN 202111199807A CN 114237460 B CN114237460 B CN 114237460B
- Authority
- CN
- China
- Prior art keywords
- content
- label
- comment
- interactive
- selected times
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004590 computer program Methods 0.000 title claims abstract description 24
- 230000002452 interceptive effect Effects 0.000 claims abstract description 130
- 230000001960 triggered effect Effects 0.000 claims abstract description 32
- 238000011156 evaluation Methods 0.000 claims description 58
- 230000000694 effects Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 238000012552 review Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000008451 emotion Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 208000033614 Joint crepitation Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000001145 finger joint Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0483—Interaction with page-structured environments, e.g. book metaphor
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- User Interface Of Digital Computer (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the application provides a label display method, a label display device, a label display terminal, a label display storage medium and a label display computer program product, and relates to the field of content recommendation. The label display method comprises the following steps: displaying a user interface for displaying interactive content, wherein a plurality of label controls corresponding to comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment tag is generated based on the characteristic information of the interactive content; and responding to the triggering operation of at least one of the label controls, and updating and displaying the selected times corresponding to the triggered label controls. The embodiment of the application is used for solving the technical problem of low-quality content such as low colloquial content of the community, and the accuracy of pushing the community content is improved.
Description
Technical Field
The present application relates to the field of content recommendation technologies, and in particular, to a tag display method, a tag display device, a tag display terminal, a storage medium, and a computer program product.
Background
At present, the governance content community atmosphere is often managed by adopting a hard regulation system, and as in the actual law and regulation, some ground rule and rule of forbidden behavior are formulated, and when a user touches the rule, the user is subjected to corresponding punishment. In particular, in a network community, common practice is to touch forbidden keywords, forbidden pictures or manually determined illegal words, delete the words, and take penalizing measures such as forbidden words and forbidden sealing for the words author.
However, the following problems exist in the treatment process of the content community atmosphere: the regulation system is often only set by a bottom line, and only when words such as abuse, defamation and low custom are seriously occurred, the rule is punished only, and the method can not play a role in community atmosphere such as more extensive words, ideas, emotion negatives and the like. According to data research, the touch strong rule is only 10% of all the problems in the community atmosphere problems to be optimized, and the larger problems come from the atmosphere problem types. The community atmosphere content is reduced for a long time, and forward guidance cannot be provided for users, so that a great deal of loss of the users is caused. Meanwhile, the community can not provide effective information for the content pushed by the user, and the accuracy of pushing the community content is reduced.
Disclosure of Invention
The embodiment of the application provides a tag display method, a tag display device, a tag display terminal, a tag display medium and a tag display computer program product, which are used for solving the technical problem of low-quality content such as low-custom content of community atmosphere content and the like, and improving the accuracy of community content pushing.
According to an aspect of the embodiments of the present application, there is provided a tag display method, including:
Displaying a user interface for displaying interactive content, wherein a plurality of label controls corresponding to comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment tag is generated based on the characteristic information of the interactive content;
and responding to the triggering operation of at least one of the label controls, and updating and displaying the selected times corresponding to the triggered label controls.
In one possible implementation, the feature information includes semantic features, and the comment tag is generated based on the feature information of the interactive content, including:
extracting semantic features of the interactive content;
determining the content type corresponding to the semantic features;
and determining comment tags associated with the interactive content according to the content type.
In one possible implementation, the method further includes:
taking the interactive content meeting the preset content evaluation condition as the content to be tested;
performing effect evaluation on the corresponding triggering operation according to the selected times of the label control corresponding to the content to be tested to obtain evaluation parameters, wherein the evaluation parameters comprise accuracy and recall rate;
and carrying out iterative training on a pre-established content recommendation model according to the evaluation parameters and the content to be tested so as to recommend content to a user according to the trained content recommendation model.
In one possible implementation manner, the performing effect evaluation on the corresponding triggering operation according to the selected times of the label control corresponding to the content to be tested to obtain an evaluation parameter includes:
sorting the selected times of comment tags corresponding to the content to be tested according to the sequence from big to small, screening comment tags arranged in the front a position, wherein a is more than or equal to 1 and less than or equal to n, and n is the number of the comment tags;
judging whether the meaning of the content to be detected is consistent with that of the comment label screened out; if yes, marking the content to be detected as first interactive content; otherwise, marking as second interactive content;
and calculating an evaluation parameter of the triggering operation corresponding to the content to be tested according to the first interactive content and the second interactive content.
In one possible implementation, the method further includes:
according to the selected times corresponding to the label control of the interactive content, carrying out value adjustment on the weight of the interactive content;
and determining the content recommended to the user based on the weight value of the interactive content.
In one possible implementation manner, the comment tag includes a positive tag that meets a preset positive comment condition and a negative tag that meets a preset negative comment, and the value adjustment is performed on the weight of the interactive content according to the selected times corresponding to the tag control of the interactive content, where the value adjustment includes:
Determining the interactive content of which the negative label meets the preset negative content judgment condition as negative content; the negative content judgment condition comprises that the selected times of the negative labels are not smaller than the selected times of the positive labels, and/or the selected times of the negative labels exceed a preset first threshold value;
and reducing the weight value of the negative content.
In one possible implementation manner, the determining the content recommended to the user based on the weight value of the interactive content further includes:
determining the interactive content of which the positive tag meets the preset positive content judgment condition as positive content, wherein the positive content judgment condition comprises that the selected times of the positive tag is larger than the selected times of the negative tag, and/or the selected times of the positive tag exceeds a preset second threshold value;
organizing the positive content and the negative content into an interactive content instance;
and sharing the interactive content examples to the user.
According to another aspect of the embodiments of the present application, there is provided a tag display device including:
the label control display module is used for displaying a user interface for displaying interactive contents, wherein a plurality of label controls corresponding to comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment tag is generated based on the characteristic information of the interactive content;
And the triggering module is used for responding to the triggering operation of at least one of the label controls and updating and displaying the selected times corresponding to the triggered label controls.
According to another aspect of the embodiments of the present application, there is provided a terminal, which includes a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the tag display method described in the foregoing embodiments.
According to still another aspect of the embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the tag display method described in the above embodiments.
According to an aspect of the embodiments of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the tag display method described in the above embodiments.
The beneficial effects that technical scheme that this application embodiment provided brought are:
the label display method comprises the steps of displaying a user interface for displaying interactive contents, wherein a plurality of label controls corresponding to comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment labels are generated based on the characteristic information of the interactive content, so that voting results of comment labels of other users of the community on the interactive content can be intuitively displayed for the users, effective basis is provided for objective authenticity judgment of the users on the content, meanwhile, the acquisition efficiency of the users on the content information is improved, and accordingly the selected times corresponding to the triggered label controls are updated and displayed in response to triggering operation of at least one label control, the technical problem of low-quality content such as low colloquiality of community atmosphere content can be effectively solved, the problem of poor community atmosphere is solved, forward guidance is provided for the users, and user loss can be effectively prevented.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that are required to be used in the description of the embodiments of the present application will be briefly described below.
FIG. 1 is a schematic diagram of a computer system architecture according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a label display method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a user interface display process provided in one exemplary embodiment of the present application;
FIG. 4 is a schematic diagram of a user interface display process provided in accordance with another exemplary embodiment of the present application;
fig. 5 is a schematic structural diagram of a label display device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a terminal according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described below with reference to the drawings in the present application. It should be understood that the embodiments described below with reference to the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application, and the technical solutions of the embodiments of the present application are not limited.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and "comprising," when used in this application, specify the presence of stated features, information, data, steps, operations, elements, and/or components, but do not preclude the presence or addition of other features, information, data, steps, operations, elements, components, and/or groups thereof, all of which may be included in the present application. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein indicates at least one of the items defined by the term, e.g. "a and/or B" indicates implementation as "a", or as "B", or as "a and B".
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a computer system architecture according to an embodiment of the present application. The computer system 1 includes a terminal 1000 and a server 2000, wherein the terminal 1000 and the server 2000 are connected through a communication network, and the terminal 1000 and the server 2000 may be directly or indirectly connected through a wired or wireless communication manner, which is not limited in this application.
Terminal 1000 is an electronic device equipped with an application for installing a user interface for presenting interactive contents, which supports posting of interactive contents including multimedia contents such as text, image, video, and voice, posting of interactive contents, reading, forwarding, praying, and the like of interactive contents. The application is illustratively a terminal-side application of a multimedia platform. By way of example, the multimedia platform includes a social application platform, a game application platform, a life service platform, and the like, and the type of the multimedia platform is not limited in the present application. For better explanation of the present application, the following embodiments of the present application are described with community posts as examples, but the present application is not limited to this scenario, and may also be applied to game platforms, public numbers, and the like.
By way of example, the terminal 1000 can be a smart phone, tablet computer, notebook computer, desktop computer, smart wearable device, etc., and the embodiments of the present application are not limited thereto. With respect to the hardware configuration, the terminal 1000 includes a display, a memory, a processor, and an input device, but is not limited thereto.
The server 2000 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, a content distribution network, basic cloud computing services such as big data and an artificial intelligence platform. A multimedia platform is carried on server 2000, and server 2000 provides background services for applications installed and running in terminal 1000. Illustratively, upon receiving a triggered posting operation for an interactive content comment, terminal 1000 sends comment content and a comment posting request to server 2000, and server 2000 stores the comment content of the community post based on the comment posting request. And when receiving the triggered review operation of the interactive content review, terminal 1000 sends a review request to server 2000, and server 2000 returns the stored review content of the interactive content to terminal 1000 based on the review request, so that terminal 1000 displays the review content of the interactive content.
Fig. 2 is a flowchart of a label display method according to an embodiment of the present application. In the embodiment of the present application, a label display method is provided for the terminal 1000 illustrated in fig. 1, and the method includes steps S201 to S202.
S201, displaying a user interface for displaying interactive contents, wherein a plurality of label controls corresponding to comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment tag is generated based on the feature information of the interactive content.
S202, responding to triggering operation of at least one of the label controls, and updating and displaying the selected times corresponding to the triggered label controls.
An application program is installed and run on terminal 1000, and supports functions of publishing, viewing, commenting, forwarding, and praying interactive contents. An application program is started on terminal 1000, and a user interface of the application program is displayed, wherein the user interface displays interactive content issued by a user, a forwarding control for forwarding the interactive content, a comment control for commenting on the interactive content, a forwarding control corresponding to a comment label, a label control, a praise control for praise the interactive content and the like. In addition, the number of times of triggering the comment control, the label control, the praise control and other controls are marked.
In this embodiment, each interactive content corresponds to a plurality of comment labels and label controls of the comment labels, so that a user selects a label control corresponding to a corresponding comment label according to the interactive content, and the number of triggering times marked on the label control is the number of times of selecting the comment label corresponding to the label control. For example, when a user clicks on two tab controls, selection of the corresponding comment tab is triggered. Thus, when one or more tab controls are triggered, terminal 1000 obtains a trigger instruction for the corresponding tab control and sends it to server 2000, and server 2000 accumulates and updates the number of triggers for the tab control and returns to terminal 1000 so that terminal 1000 displays the number of triggers marked by the tab control. The terminal 1000 receives a triggering operation of inputting a label control on an application program through an input device such as a touch screen or a mouse, where the triggering operation may include at least one of a clicking operation, a long-press operation, and a finger joint clicking operation.
Therefore, the label control of a plurality of comment labels is displayed through the user interface, and a user can directly trigger one label control to express comment contents characterized by corresponding comment labels, namely, a way capable of expressing different views and simple in form is provided for the user. Meanwhile, by displaying the triggered result of the label control, the user can quickly grasp the views of other users in the community aiming at the interactive content without consulting the user comments in the comment area, the efficiency of acquiring information reflected by the interactive content by the user is improved, and the operation mode is simple, convenient and quick. In addition, aiming at community atmosphere management in the prior art, in the aspect of judging the authenticity of information, management personnel are difficult to objectively decide.
In some embodiments, the feature information includes semantic features, the comment tag is generated based on the feature information of the interactive content, comprising:
extracting semantic features of the interactive content;
determining the content type corresponding to the semantic features;
and determining comment tags associated with the interactive content according to the content type.
It should be noted that, preset example content of different content types, screen out example comment labels according to example content, and then verify the above-mentioned example comment labels online, keep and store the vocabulary that information is high, use accurate and ambiguity little as the comment label that this content type corresponds. The comment labels can reflect symptoms and encouragement contents of community atmosphere treatment, can play roles in counteracting and resolving treatment results, reduce bad playing, wrong throwing and abrupt conditions, and adopt easily understood words with accurate meanings.
Further, the content type of the interactive content is determined according to the semantic features of the interactive content, and further the stored corresponding comment tags are determined according to the content type. In this embodiment, the content types of the posts include, but are not limited to, genuineness disputes, negative energy posts, question posts, informative posts, negative posts with a strong bias of view and/or subjective color, posts involving privacy class posts and posts whose expression pattern does not conform to community regulations, is not civilized or is too intense. For example, for an authenticity dispute paste, the label "fit fact" may be selected to indicate approval for the post content, and the label "no evidence" may indicate doubt or objection to the post content; for negative energy posts, a label of' feeling the same as the person is used for expressing care and resonance; for the question paste, a label of same question can be selected to represent that the question is added to the post content; for posts with information, the label "useful" can be selected to express appreciation and thank you for the information of the post, and the label "useless" can be selected to express positive effect of the information of the post; for negative posts with strong viewpoint bias and/or subjective color, the label of 'missing bias' can be selected to represent the identification of the posts with the content type; for posts involving privacy class, the label "involving privacy" may be selected to represent the identification of the content type of post; for posts with expression modes which do not accord with community adjustability, are not civilized or are too violent, the label of 'words and words overdriving' can be selected to represent the identification of the posts with the content types, and comment labels of the application are not limited to the above examples, but are not limited to the above examples. In addition, the semantic features of each interactive content can conform to one or more content types, and the application does not limit the content types and the number of comment labels corresponding to the content types. Therefore, the comment tags related to the interactive content are provided for the user through the semantic features of the interactive content, the accurate comment tags can be quickly identified and selected, and the accuracy of expressing the views by the user selecting the comment tags is improved, so that the information authenticity of the interactive content is accurately and objectively reflected.
For example, fig. 3 is a schematic diagram illustrating a user interface display process provided in an exemplary embodiment of the present application, where an application is a social communication program corresponding to a social application platform, and a terminal displays a user interface 31 related to "xx staff" in the application, where user information of a user, such as a user head portrait, a user ID name, a user class, a post posting time (or a time when a post is posted from the current time), post content, a focus control 311 focused on the post, and a topic label 312 of the post (such as "staff groove party", "programmer's daily" in fig. 3) are displayed on the user interface 31.
Optionally, as shown in fig. 3, the user interface also displays a forwarding control 313, a comment control 314, a praise control 315, and an objection control 316 of the community post. The trigger operation times of the forwarding control 313, the comment control 315 and the praise control 315 are 3, 22 and 9 in sequence. The forwarding control 313 is used to implement operations on the application 31 to forward the post when triggered, such as entering an interface to select a forwarding object, such that the post content is sent to the selected forwarding object. The comment control 314 is used to implement operations on the application program to comment on the post when triggered, such as popping up an editing interface (e.g., editing widget) of comment content, so that the user edits and publishes comment content on the editing interface. The endorsing control 315 is used to effect endorsing the post on the application when triggered. The objection control 316 is used to display on the application when triggered that objection to the post content.
Optionally, as shown in FIG. 3, the user interface also displays tab controls 317, including "in fact", "in-mind", "in-question", "helpful", "without evidence", "with misdirection", "involving privacy", and "overdriving". The label controls 317 of the community user for "feel same" and "same" are triggered, and the number of triggers is 1, which indicates that the community user's opinion about the post content is indicative of resonance and doubts about the post content, and the opinion about the label viewpoint may be considered as a forward attitude.
Optionally, as shown in fig. 3, the above-mentioned user interface 31 further displays a comment display area of comment contents of other users in the community on the post, where the comment display area displays user information of the comment user, comment contents, a praise control (the praise control is further marked with the number of times of triggering the praise control, as shown in fig. 3, the number of times of praise is 6), comment posting time, and a reply control 318, where the reply control 318 is used to implement an operation of replying to the comment contents on the application program when triggered, such as popping up an editing interface (such as an editing widget) of the reply contents, so that the user edits and posts the reply contents on the editing interface.
In some embodiments, a label collapse control 3192 for collapsing the non-triggered label controls, or a label expand control 3191 for expanding all of the label controls, is displayed on the user interface. For example, as shown in fig. 3, the tab expansion control 3191 and the triggered tab control 317, such as "like-catch", "same question" and the number of triggers of the tab control 317, are displayed on the user interface 31, where the tab expansion control 3191 is configured to expand and display all tab controls 317 and the number of triggers marked by the tab control 317 when triggered. FIG. 4 is a schematic diagram of a user interface display process according to another exemplary embodiment of the present application, and for the interactive content in FIG. 4, comment labels may include "accord with facts", "feel", "same question", "helpful", "no evidence", "have misdirection", "involve privacy", and "overdriving", where the label controls of the community user for "have misdirection", "overdriving" are triggered, the number of times of triggering is 1, which reflects that the interactive content does not accord with community tonality, is not civilized or is too intense, and is in negative attitude with respect to viewpoint deviant and/or subjective color, for which community atmosphere management needs to be made to provide positive and effective reference for the user. Wherein the user interface 31 displays a label folding control 3192, the label folding control 3192 is configured to fold and display, when triggered, the label control 317 that is not triggered, such as "in fact", "like", "helpful", "no evidence", "related to privacy", and only displays the label control that is triggered, such as "mismatching", "words overdriving". Therefore, the embodiment simplifies the user interface by setting the label folding control 3192 and the label unfolding control 3191, so that the user can quickly identify the triggered label control and the triggering times thereof.
In some embodiments, at least one piece of comment content of the same interactive content and at least one piece of reply content of the same comment content are displayed in a folded manner on the user interface. Illustratively, as shown in FIG. 4, the comment content in the comment presentation area of the post has a total of 3 pieces of reply content, 1 piece of reply content is displayed on the user interface, and the other 2 pieces of reply content are folded. Thus, the control that folds the comment/reply content updates the display with the number of comment/reply contents folded, as shown in fig. 4, which is a "view all 2 replies" control that when triggered, unfolds all comment/reply contents folded. The comment/reply content may be displayed according to a rule such as a time sequence, a word sequence, etc., so that the content ordered in the rear position is displayed in a folded manner, which is not limited in this application.
In some embodiments, the label control displays emoticons and text associated with the comment label. For example, as shown in fig. 3, the expression image corresponding to the "fact-conforming" of the label control is "smiling face", which represents a favorable and satisfied attitude, thereby increasing interest and enriching the expression form of the label control.
In some embodiments, the method further comprises:
Taking the interactive content meeting the preset content evaluation condition as the content to be tested;
performing effect evaluation on the corresponding triggering operation according to the selected times of the label control corresponding to the content to be tested to obtain evaluation parameters, wherein the evaluation parameters comprise accuracy and recall rate;
and carrying out iterative training on a pre-established content recommendation model according to the evaluation parameters and the content to be tested so as to recommend content to a user according to the trained content recommendation model.
In this embodiment, content evaluation conditions (i.e., basis for judging content to be tested) are preset, and evaluation content types corresponding to different content evaluation conditions are determined so as to evaluate effects of triggering operation events of label controls corresponding to interactive content satisfying the content evaluation conditions.
Wherein, the evaluation content types comprise the content of feeling community warp, the content of feeling very anxiety, the content of feeling community view extreme, the content of feeling community non-object/non-information negative content, the content of positive energy content being excluded, the content of suspicion authenticity, and the like. Illustratively, the evaluation content type is the content with feeling community warp, and the judgment basis (namely the content evaluation condition) can be coarse/35881-gram/personal attack/group attack. The evaluation content type is content which feels very anxious, the judgment basis can be negative energy of the content itself, and the evaluation content belongs to negative emotion expression with information, for example, interactive content is' technology 32 years old, 985 book, xx is only 40k, no option exists, work is very tired, the body is not very good, any support in the home is not obtained, the unfortunate family is poor, the parent relationship is very bad, the family is not careless, the family is also faced with a break, how the family is alive is not known, the feeling is difficult, a person has passed through a small and a half, and is wanting to find a small place to be hidden, and the life is very bad. The evaluation content type is the content with extremely high sense community views, the judgment basis can be negative content, the assumption with strong subjective color and conclusion expression, for example, the interactive content is' hearing xx, more feel dim and irrelevant, no business and management layer even logic of a product can be self-consistent completely, a plurality of responsible persons of the product do not understand the management on the whole-day playing line of the logic, and how is the product brought well? See again? Not accompany the game, tired to the extreme. The evaluation content type is the content which senses that the community has no object/no information content and has more negative content, the judgment basis can be word little/no information content, and the content or expression is negative, such as the interactive content is 'wanting to leave, move'. The evaluation content type is the content of which the positive energy content is pushed out, and the judgment basis can be positive forward of the content, and the friendly temperature is expressed. The evaluation content type is the content which looks at the doubt authenticity, and the judgment basis can be negative information of explosion payroll, company eight diagrams and the like which possibly have infirm information.
Based on the foregoing embodiments, in some embodiments, the performing effect evaluation on the corresponding trigger operation according to the selected times of the label control corresponding to the content to be tested, to obtain an evaluation parameter includes:
sorting the selected times of comment tags corresponding to the content to be tested according to the sequence from big to small, screening comment tags arranged in the front a position, wherein a is more than or equal to 1 and less than or equal to n, and n is the number of the comment tags;
judging whether the meaning of the content to be detected is consistent with that of the comment label screened out; if yes, marking the content to be detected as first interactive content; otherwise, marking as second interactive content;
and calculating an evaluation parameter of the triggering operation corresponding to the content to be tested according to the first interactive content and the second interactive content.
In this embodiment, when the meaning of the interactive content is inconsistent with the meaning of the comment tag (such as the comment tag with the second rank of the selected number of times) triggered by the number of times, the interactive content is marked as the second interactive content. Illustratively, if the post content is an objective description that expresses any emotion, but is selected as a comment tag that resembles a word too high, and if the post content does not agree significantly with the tag selection result, it is apparent that the post content does not agree with the tag selection result. And when the interaction content is consistent with the meaning of the comment labels with more triggered times, marking as first interaction content. For example, when the post content of the overstress and the coarse language is pointed, the label selection result is a result biased to the negative direction, for example, the comment label with more selected times is 'vigorous speaking'; when the contents without things or information are said, the label selection result is a result biased to the negative direction; when a certain objective description is provided for spitting, and no content of overcustom speech is provided, the label selection result is positive or negative, and the meaning of the label selection result is consistent. Therefore, according to the related quantity of the first interactive content and the second interactive content in the content to be detected, evaluation parameters such as the accuracy rate, the recall rate and the like of the triggering operation corresponding to the content to be detected are calculated, and the evaluation parameters are used for indicating whether the comment of the comment label selection result of the user on the interactive content is accurate or not.
In a specific embodiment, semantic recognition is performed on the content to be detected according to a preset semantic scene, so that the content to be detected conforming to the semantic scene is marked, that is, the marking can generate positive or negative emotion content or expression, and the semantic scene specifically includes the following steps: 1. the content itself is a negative information describing a value that does not fit the public; 2. description of a phenomenon of strange air in yin and yang; 3. a judgment with a strong subjective color; 4. very heavy or coarse speech; 5. no information amount spitting groove. Further, judging whether the marked content to be detected is consistent with the meaning of the selection result of the comment label, if so, considering that the true meaning is consistent with the expected meaning, and the semantic meaning accords with the expected meaning; otherwise, the true meaning is not considered to be consistent with the intended meaning. Judging whether the untagged content to be detected is consistent with the selection result of the comment label, if so, considering that the true meaning is consistent with the expected meaning; otherwise, the true meaning is not considered to be consistent with the intended meaning. Further, according to the judging result, calculating the accuracy of the triggering operation corresponding to the content to be detected by the content to be detected with the same true meaning as the expected meaning and the quantity of all the content to be detected. And calculating the recall rate of the triggering operation corresponding to the content to be detected according to the identified content to be detected and the number of the identified content to be detected, wherein the actual meaning of the identified content to be detected is consistent with the expected meaning.
Therefore, in this embodiment, the effect evaluation parameters of the triggering operation event of the content to be tested are iteratively trained on the content recommendation model, so as to reduce the pushing frequency of the interactive content with poor effect evaluation results (the meaning of the comment label with more triggered times can be considered inconsistent with that of the content) or recall the interactive content. Therefore, the embodiment can effectively improve the accuracy of expressing the user's views by the comment tags, improve the accuracy and information effectiveness of content recommendation, and improve the efficiency of community atmosphere management.
According to the label display method, through displaying the user interface for displaying the interactive content, label controls corresponding to a plurality of comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment labels are generated based on the characteristic information of the interactive content, so that voting results of comment labels of other users of the community on the interactive content can be intuitively displayed for the users, effective basis is provided for objective authenticity judgment of the users on the content, meanwhile, the acquisition efficiency of the users on the content information is improved, and accordingly the selected times corresponding to the triggered label controls are updated and displayed in response to triggering operation of at least one label control, the technical problem of low-quality content such as low colloquiality of community atmosphere content can be effectively solved, the problem of poor community atmosphere is solved, forward guidance is provided for the users, and user loss can be effectively prevented.
In some embodiments, the method further comprises:
according to the selected times corresponding to the label control of the interactive content, carrying out value adjustment on the weight of the interactive content;
and determining the content recommended to the user based on the weight value of the interactive content.
According to the method and the device for selecting the comment labels, the selection results of the comment labels of other users in the community on the interactive content can be intuitively displayed to the user according to the triggering times of the user on the label control, namely the selection times of the comment labels, and effective basis is provided for objective and authenticity judgment of the user on the content. Meanwhile, the selection result of the comment tag can reflect whether the post content is positive content or negative content, so that the efficiency of community atmosphere management is improved.
In some embodiments, the comment tag includes a positive tag that meets a preset positive comment condition and a negative tag that meets a preset negative comment, and the adjusting the weight of the interactive content according to the selected times corresponding to the tag control of the interactive content includes:
determining the interactive content of which the negative label meets the preset negative content judgment condition as negative content; the negative content judgment condition comprises that the selected times of the negative labels are not smaller than the selected times of the positive labels, and/or the selected times of the negative labels exceed a preset first threshold value;
And reducing the weight value of the negative content.
In this embodiment, according to the semantics and usage of the comment tags, the positive direction and the negative direction of each comment tag are preset, that is, the comment tag conforming to the positive comment condition and the comment tag conforming to the negative comment condition are predefined. Illustratively, comment tags "conform to facts", "feel like", "same question", "helpful" are defined as positive tags, comment tags "no evidence", "misshapen", "related to privacy" and "oversteer" are defined as negative tags.
The post content with excessive number of negative labels is widely considered as negative energy by users, so that the platform is not beneficial to actively and effectively guiding the users and favorable development of community atmosphere, therefore, the method and the device for pushing the negative content reduce the number of times of pushing the negative content to the users, the platform provides effective and useful information for the users, the accuracy and the utilization rate of pushing the content are improved, the user experience is improved, and the user loss is effectively prevented.
In some embodiments, the determining content recommended to the user based on the weight value of the interactive content further includes:
Determining the interactive content of which the positive tag meets the preset positive content judgment condition as positive content, wherein the positive content judgment condition comprises that the selected times of the positive tag is larger than the selected times of the negative tag, and/or the selected times of the positive tag exceeds a preset second threshold value;
organizing the positive content and the negative content into an interactive content instance;
and sharing the interactive content examples to the user.
Wherein the application does not define the first threshold value and the second threshold value.
Illustratively, forward content determined by the user's comment tag selection results, such as a post that 2342 users feel "like" and a post that 997 users feel "helpful"; and negative content determined by the user's comment tag selection results, such as 98 posts that the user feels "uttered hard", 112 posts that the user feels "viewpoint biased". The positive content and the negative content are announced and transmitted so as to summarize and comb encouraged and discouraged demonstration in the community, and the education effect of community specification can be achieved.
Therefore, the embodiment of the application pushes the content to the user by adjusting the release weights of the positive content and the negative content, so that the condition that the low-quality content is pushed to the community is avoided, the quality of the content recommended to the user is ensured, the efficiency of community atmosphere management is improved, the accuracy of community content pushing is improved, the user requirement is better met, and the viscosity of the community user is kept.
Referring to fig. 5, a schematic structural diagram of a label display device according to an embodiment of the present application, a label display device 500 includes:
the label control display module 501 is configured to display a user interface for displaying interactive content, where a plurality of label controls corresponding to comment labels respectively and a selected number of times corresponding to each label control are displayed on the user interface; the comment tag is generated based on the characteristic information of the interactive content;
and the triggering module 502 is configured to respond to a triggering operation on at least one of the label controls, and update and display a selected number of times corresponding to the triggered label control.
In some embodiments, the label control display module 501 includes:
the feature extraction unit is used for extracting semantic features of the interactive content;
a content type determining unit, configured to determine a content type corresponding to the semantic feature;
and the comment label determining unit is used for determining comment labels associated with the interactive content according to the content type.
In some embodiments, the apparatus further comprises:
the sampling unit is used for taking the interactive content meeting the preset content evaluation condition as the content to be tested;
the effect evaluation unit is used for evaluating the effect of the corresponding triggering operation according to the selected times of the label control corresponding to the content to be tested, and obtaining evaluation parameters, wherein the evaluation parameters comprise accuracy and recall rate;
And the first content recommending unit is used for carrying out iterative training on a pre-established content recommending model according to the evaluation parameters and the content to be measured so as to recommend the content to the user according to the trained content recommending model.
In some embodiments, the effect evaluation unit comprises:
the selecting and sorting unit is used for sorting the selected times of the comment labels corresponding to the content to be tested from large to small, screening out comment labels ranked in the front a position, wherein a is more than or equal to 1 and less than or equal to n, and n is the number of the comment labels;
the meaning judging unit is used for judging whether the meaning of the content to be detected is consistent with that of the selected comment label; if yes, marking the content to be detected as first interactive content; otherwise, marking as second interactive content;
and the evaluation unit is used for calculating the evaluation parameters of the triggering operation corresponding to the content to be tested according to the first interactive content and the second interactive content.
In some embodiments, the apparatus further comprises:
the weight adjusting unit is used for carrying out value adjustment on the weight of the interactive content according to the selected times corresponding to the label control of the interactive content;
and the second content recommending unit is used for determining the content recommended to the user based on the weight value of the interactive content.
In some embodiments, the weight adjustment unit includes:
the negative content determining unit is used for determining the interactive content of which the negative label meets the preset negative content judging condition as negative content; the negative content judgment condition comprises that the selected times of the negative labels are not smaller than the selected times of the positive labels, and/or the selected times of the negative labels exceed a preset first threshold value;
and the weight reducing unit is used for reducing the weight value of the negative content.
In some embodiments, the second content recommendation unit includes:
a positive content determining unit, configured to determine, as positive content, interactive content that the positive tag meets a preset positive content judgment condition, where the positive content judgment condition includes that a number of times the positive tag is selected is greater than a number of times the negative tag is selected, and/or the number of times the positive tag is selected exceeds a preset second threshold;
an interactive content example organization unit configured to organize the positive content and the negative content into interactive content examples;
and the example sharing unit is used for sharing the interactive content examples to the user.
The apparatus of the embodiments of the present application may perform the method provided by the embodiments of the present application, and implementation principles of the method are similar, and actions performed by each module in the apparatus of each embodiment of the present application correspond to steps in the method of each embodiment of the present application, and detailed functional descriptions of each module of the apparatus may be referred to in the corresponding method shown in the foregoing, which is not repeated herein.
The embodiment of the application provides a terminal, which comprises a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to realize the steps of a label display method, and compared with the prior art, the method can realize the steps of: the method and the device can intuitively display the voting results of other users in the community on the comment labels of the interactive contents to the users, provide effective basis for the objective and true judgment of the users on the contents, and improve the acquisition efficiency of the users on the content information, so that the technical problems of low quality contents such as low colloquiality of the community atmosphere contents can be effectively solved, the problem of poor community atmosphere is solved, forward guidance is provided for the users, and the loss of the users can be effectively prevented. .
In an alternative embodiment, a terminal is provided, as shown in fig. 6, and a terminal 1000 shown in fig. 6 includes: a processor 1001 and a memory 1003. The processor 1001 is coupled to the memory 1003, such as via a bus 1002. Optionally, terminal 1000 can also include a transceiver 1004, where transceiver 1004 can be used for data interaction between the terminal and other terminals, such as transmission of data and/or reception of data, etc. It should be noted that, in practical applications, the transceiver 1004 is not limited to one, and the structure of the terminal 1000 is not limited to the embodiments of the present application.
The processor 1001 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 1001 may also be a combination that implements computing functionality, such as a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
Bus 1002 may include a path to transfer information between the components. Bus 1002 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The bus 1002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 6, but not only one bus or one type of bus.
The Memory 1003 may be, but is not limited to, ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, EEPROM (Electrically Erasable Programmable Read Only Memory ), CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store a computer program and that can be Read by a computer.
The memory 1003 is used to store a computer program for executing the embodiments of the present application, and is controlled to be executed by the processor 1001. The processor 1001 is arranged to execute a computer program stored in the memory 1003 to implement the steps shown in the foregoing method embodiments.
Embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, may implement the steps and corresponding content of the foregoing method embodiments.
The embodiments of the present application also provide a computer program product, which includes a computer program, where the computer program can implement the steps of the foregoing method embodiments and corresponding content when executed by a processor.
It should be understood that, although the flowcharts of the embodiments of the present application indicate the respective operation steps by arrows, the order of implementation of these steps is not limited to the order indicated by the arrows. In some implementations of embodiments of the present application, the implementation steps in the flowcharts may be performed in other orders as desired, unless explicitly stated herein. Furthermore, some or all of the steps in the flowcharts may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or phases may be performed at the same time, or each of these sub-steps or phases may be performed at different times, respectively. In the case of different execution time, the execution sequence of the sub-steps or stages may be flexibly configured according to the requirement, which is not limited in the embodiment of the present application.
The foregoing is merely an optional implementation manner of the implementation scenario of the application, and it should be noted that, for those skilled in the art, other similar implementation manners based on the technical ideas of the application are adopted without departing from the technical ideas of the application, and also belong to the protection scope of the embodiments of the application.
Claims (9)
1. A label display method, comprising:
displaying a user interface for displaying interactive content, wherein a plurality of label controls corresponding to comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment tag is generated based on the characteristic information of the interactive content;
responding to the triggering operation of at least one of the label controls, and updating and displaying the selected times corresponding to the triggered label controls;
the method further comprises the steps of:
taking the interactive content which meets the preset content evaluation conditions and meets the evaluation content types corresponding to the preset content evaluation conditions as the content to be tested;
performing effect evaluation on the corresponding triggering operation according to the selected times of the label control corresponding to the content to be tested to obtain evaluation parameters, wherein the evaluation parameters comprise accuracy and recall rate;
and carrying out iterative training on a pre-established content recommendation model according to the evaluation parameters and the content to be tested so as to recommend content to a user according to the trained content recommendation model.
2. The tag display method according to claim 1, wherein the feature information includes semantic features, the comment tag is generated based on the feature information of the interactive content, comprising:
Extracting semantic features of the interactive content;
determining the content type corresponding to the semantic features;
and determining comment tags associated with the interactive content according to the content type.
3. The method for displaying a label according to claim 1, wherein the performing effect evaluation on the corresponding trigger operation according to the selected times of the label control corresponding to the content to be tested to obtain an evaluation parameter includes:
sorting the selected times of comment tags corresponding to the content to be tested according to the sequence from big to small, screening comment tags arranged in the front a position, wherein a is more than or equal to 1 and less than or equal to n, and n is the number of the comment tags;
judging whether the meaning of the content to be detected is consistent with that of the comment label screened out; if yes, marking the content to be detected as first interactive content; otherwise, marking as second interactive content;
and calculating an evaluation parameter of the triggering operation corresponding to the content to be tested according to the first interactive content and the second interactive content.
4. The label display method according to claim 1, characterized in that the method further comprises:
according to the selected times corresponding to the label control of the interactive content, carrying out value adjustment on the weight of the interactive content;
And determining the content recommended to the user based on the weight value of the interactive content.
5. The method for displaying labels according to claim 4, wherein the comment labels include positive labels meeting a preset positive comment condition and negative labels meeting a preset negative comment, and the adjusting the weight of the interactive content according to the selected times corresponding to the label control of the interactive content includes:
determining the interactive content of which the negative label meets the preset negative content judgment condition as negative content; the negative content judgment condition comprises that the selected times of the negative labels are not smaller than the selected times of the positive labels, and/or the selected times of the negative labels exceed a preset first threshold value;
and reducing the weight value of the negative content.
6. The tag display method of claim 5, wherein the determining content recommended to the user based on the weight value of the interactive content further comprises:
determining the interactive content of which the positive tag meets the preset positive content judgment condition as positive content, wherein the positive content judgment condition comprises that the selected times of the positive tag is larger than the selected times of the negative tag, and/or the selected times of the positive tag exceeds a preset second threshold value;
Organizing the positive content and the negative content into an interactive content instance;
and sharing the interactive content examples to the user.
7. A label display device, comprising:
the label control display module is used for displaying a user interface for displaying interactive contents, wherein a plurality of label controls corresponding to comment labels respectively and selected times corresponding to each label control are displayed on the user interface; the comment tag is generated based on the characteristic information of the interactive content;
the triggering module is used for responding to the triggering operation of at least one of the label controls and updating and displaying the selected times corresponding to the triggered label controls;
the apparatus further comprises:
taking the interactive content which meets the preset content evaluation conditions and meets the evaluation content types corresponding to the preset content evaluation conditions as the content to be tested;
performing effect evaluation on the corresponding triggering operation according to the selected times of the label control corresponding to the content to be tested to obtain evaluation parameters, wherein the evaluation parameters comprise accuracy and recall rate;
and carrying out iterative training on a pre-established content recommendation model according to the evaluation parameters and the content to be tested so as to recommend content to a user according to the trained content recommendation model.
8. A terminal comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to carry out the steps of the tag display method of any one of claims 1-6.
9. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor realizes the steps of the label display method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111199807.9A CN114237460B (en) | 2021-10-14 | 2021-10-14 | Label display method, device, terminal, storage medium and computer program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111199807.9A CN114237460B (en) | 2021-10-14 | 2021-10-14 | Label display method, device, terminal, storage medium and computer program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114237460A CN114237460A (en) | 2022-03-25 |
| CN114237460B true CN114237460B (en) | 2024-01-30 |
Family
ID=80743145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111199807.9A Active CN114237460B (en) | 2021-10-14 | 2021-10-14 | Label display method, device, terminal, storage medium and computer program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114237460B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622396A (en) * | 2011-11-30 | 2012-08-01 | 浙江大学 | Web service clustering method based on labels |
| CN104462487A (en) * | 2014-12-19 | 2015-03-25 | 南开大学 | Individualized online news comment mood forecast method capable of fusing multiple information sources |
| CN104598588A (en) * | 2015-01-19 | 2015-05-06 | 河海大学 | Automatic generating algorithm of microblog user label based on biclustering |
| CN107153641A (en) * | 2017-05-08 | 2017-09-12 | 北京百度网讯科技有限公司 | Comment information determines method, device, server and storage medium |
| CN107832776A (en) * | 2017-10-12 | 2018-03-23 | 如是科技（大连）有限公司 | The processing method and processing device that position is recommended |
| CN108460060A (en) * | 2017-02-22 | 2018-08-28 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| WO2019037195A1 (en) * | 2017-08-25 | 2019-02-28 | 平安科技（深圳）有限公司 | Method and device for identifying interest of user, and computer-readable storage medium |
| CN110516245A (en) * | 2019-08-27 | 2019-11-29 | 蓝盾信息安全技术股份有限公司 | Fine granularity sentiment analysis method, apparatus, computer equipment and storage medium |
| CN110688475A (en) * | 2019-09-05 | 2020-01-14 | 上海异势信息科技有限公司 | Article recommendation method and system based on content subjective tendency |
| CN111046438A (en) * | 2019-11-26 | 2020-04-21 | 山东爱城市网信息技术有限公司 | Forum platform information processing method, device and medium based on block chain |
| CN111291220A (en) * | 2020-01-20 | 2020-06-16 | 北京字节跳动网络技术有限公司 | Label display method and device, electronic equipment and computer readable medium |
| CN111325571A (en) * | 2019-12-30 | 2020-06-23 | 北京航空航天大学 | Method, device and system for automatically generating commodity comment labels for multitask learning |
| CN111522940A (en) * | 2020-04-08 | 2020-08-11 | 百度在线网络技术（北京）有限公司 | Method and device for processing comment information |
| CN112434164A (en) * | 2020-12-03 | 2021-03-02 | 西安交通大学 | Network public opinion analysis method and system considering topic discovery and emotion analysis |
| WO2021062996A1 (en) * | 2019-09-30 | 2021-04-08 | 厦门邑通软件科技有限公司 | Method for accurately collecting interactive webpage data |
| CN113486251A (en) * | 2021-07-29 | 2021-10-08 | 北京字节跳动网络技术有限公司 | Information display method and device and computer storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10853826B2 (en) * | 2012-02-07 | 2020-12-01 | Yeast, LLC | System and method for evaluating and optimizing media content |
-
2021
- 2021-10-14 CN CN202111199807.9A patent/CN114237460B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622396A (en) * | 2011-11-30 | 2012-08-01 | 浙江大学 | Web service clustering method based on labels |
| CN104462487A (en) * | 2014-12-19 | 2015-03-25 | 南开大学 | Individualized online news comment mood forecast method capable of fusing multiple information sources |
| CN104598588A (en) * | 2015-01-19 | 2015-05-06 | 河海大学 | Automatic generating algorithm of microblog user label based on biclustering |
| CN108460060A (en) * | 2017-02-22 | 2018-08-28 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN107153641A (en) * | 2017-05-08 | 2017-09-12 | 北京百度网讯科技有限公司 | Comment information determines method, device, server and storage medium |
| WO2019037195A1 (en) * | 2017-08-25 | 2019-02-28 | 平安科技（深圳）有限公司 | Method and device for identifying interest of user, and computer-readable storage medium |
| CN107832776A (en) * | 2017-10-12 | 2018-03-23 | 如是科技（大连）有限公司 | The processing method and processing device that position is recommended |
| CN110516245A (en) * | 2019-08-27 | 2019-11-29 | 蓝盾信息安全技术股份有限公司 | Fine granularity sentiment analysis method, apparatus, computer equipment and storage medium |
| CN110688475A (en) * | 2019-09-05 | 2020-01-14 | 上海异势信息科技有限公司 | Article recommendation method and system based on content subjective tendency |
| WO2021062996A1 (en) * | 2019-09-30 | 2021-04-08 | 厦门邑通软件科技有限公司 | Method for accurately collecting interactive webpage data |
| CN111046438A (en) * | 2019-11-26 | 2020-04-21 | 山东爱城市网信息技术有限公司 | Forum platform information processing method, device and medium based on block chain |
| CN111325571A (en) * | 2019-12-30 | 2020-06-23 | 北京航空航天大学 | Method, device and system for automatically generating commodity comment labels for multitask learning |
| CN111291220A (en) * | 2020-01-20 | 2020-06-16 | 北京字节跳动网络技术有限公司 | Label display method and device, electronic equipment and computer readable medium |
| CN111522940A (en) * | 2020-04-08 | 2020-08-11 | 百度在线网络技术（北京）有限公司 | Method and device for processing comment information |
| CN112434164A (en) * | 2020-12-03 | 2021-03-02 | 西安交通大学 | Network public opinion analysis method and system considering topic discovery and emotion analysis |
| CN113486251A (en) * | 2021-07-29 | 2021-10-08 | 北京字节跳动网络技术有限公司 | Information display method and device and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114237460A (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9591089B2 (en) | Content preview generation using social network analysis | |
| Irani | The cultural work of microwork | |
| Mostafa | More than words: Social networks’ text mining for consumer brand sentiments | |
| US8769417B1 (en) | Identifying an answer to a question in an electronic forum | |
| US8972428B2 (en) | Providing an answer to a question left unanswered in an electronic forum | |
| JP6261547B2 (en) | Determination device, determination method, and determination program | |
| CN109983455A (en) | The diversified media research result on online social networks | |
| CN110474944B (en) | Network information processing method, device and storage medium | |
| KR20200030252A (en) | Apparatus and method for providing artwork | |
| CN111522940B (en) | Method and device for processing comment information | |
| CN112307336B (en) | Hot spot information mining and previewing method and device, computer equipment and storage medium | |
| Bornmann et al. | Overlay maps based on M endeley data: The use of altmetrics for readership networks | |
| CN110110218A (en) | A kind of Identity Association method and terminal | |
| JP2017201535A (en) | Determination device, learning device, determination method, and determination program | |
| AU2013201006A1 (en) | Information classification program, information classification method, and information processing apparatus | |
| CN114237460B (en) | Label display method, device, terminal, storage medium and computer program product | |
| Fourie et al. | Insights for Organizational Scholarship from Documentaries on the Australian ‘Black Summer’Bushfires | |
| Ranfagni et al. | An online research approach for a dual perspective analysis of brand associations in art museums | |
| WO2023159766A1 (en) | Catering data analysis method and apparatus, and electronic device and storage medium | |
| Lamrharia et al. | Business intelligence using the fuzzy-Kano model | |
| Vuori et al. | The 5C categorization of social media tools | |
| Lee et al. | Qtag: tagging as a means of rating, opinion-expressing, sharing and visualizing | |
| Kang et al. | Analysis of online education reviews of universities using NLP techniques and statistical methods | |
| CN111125387B (en) | Multimedia list generation and naming method and device, electronic equipment and storage medium | |
| CN112434144A (en) | Method, device, electronic equipment and computer readable medium for generating target problem |
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 |