CN116150474A - Comment ordering method and device, electronic equipment and readable storage medium - Google Patents
Comment ordering method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116150474A CN116150474A CN202211415697.XA CN202211415697A CN116150474A CN 116150474 A CN116150474 A CN 116150474A CN 202211415697 A CN202211415697 A CN 202211415697A CN 116150474 A CN116150474 A CN 116150474A
- Authority
- CN
- China
- Prior art keywords
- comment
- cluster
- information
- comments
- ordering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; 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
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- 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)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a comment ordering method, a comment ordering device, electronic equipment and a computer readable storage medium, and relates to the field of Internet. The method comprises the following steps: acquiring data information of each comment in a comment set to be displayed; classifying the comment set according to the data information of the comments to obtain a plurality of cluster clusters; according to the data information of each comment in the cluster, first ordering information of each comment in the cluster is obtained; for each comment, obtaining second ordering information of the comments in the comment set according to the cluster type of the cluster in which the comment is positioned and the first ordering information; and displaying the evaluation set. According to the embodiment of the invention, valuable comments are screened out in various modes, more valuable comments can be exposed in the comment area, the interaction quantity and quality of the comment area can be benign increased, the interpretation and conception of the works by the creator can be better known, and a good discussion atmosphere is built.
Description
Technical Field
The application relates to the technical field of internet, in particular to a comment ordering method, a comment ordering device, electronic equipment and a readable storage medium.
Background
With more and more creators, the creators select to release own works in a post or video mode, and browsing comments in a comment area becomes a mode that users quickly know the contents of the creators and the watching experience of the works, meanwhile, the creators pay more attention to the contents of the comments, and feedback about the works is quickly obtained in a comment browsing mode.
In the prior art, the comment ordering mode comprises the mode of ordering comments according to the reverse order of comment posting time and the high and low number of praise, but both modes can enable valuable comments to be buried by non-valuable comments. If the comments are browsed in time sequence in the prior art, when comment contents close in posting time are all meaningless comments which only contain one expression or are connected in a comment area, a great amount of time is consumed when a user wants to turn over to find a valuable comment, and the cost of the user who wants to see the valuable comment is increased; similarly, if the comments with high praise numbers are ranked in a high-to-low ranking manner in the prior art, the comments with high praise numbers are directly ranked at the head, so that valuable new comments cannot be exposed, the comments with high praise numbers are seen by users in the comment areas, the number of the praise points of the head with high praise numbers is continuously increased, but the newly added valuable comments cannot be exposed, and the cost for the users to see the valuable comments is increased.
Disclosure of Invention
The embodiment of the application provides a comment ordering method, device, electronic equipment, computer readable storage medium and computer program product, which can solve the problem that valuable new comments cannot be exposed, and a user needs to spend a lot of time and energy when trying to find the valuable comments. The technical scheme is as follows:
according to one aspect of the embodiments of the present application, there is provided a method for ranking comments, applied to a server, the method including:
acquiring data information of each comment in a set of comments to be displayed, wherein the data information comprises comment content, release time, praise amount of the comment, identity information of a communication paste publisher where the comment is located and identity information of a comment publisher of a comment object;
classifying the comment set according to the comment data information to obtain a plurality of cluster clusters, wherein the cluster types corresponding to each cluster are different;
for each cluster, according to the praise amount and release time of each comment in the cluster, obtaining first ordering information of each comment in the cluster;
for each comment, obtaining second ordering information of the comment in the comment set according to the cluster type of the cluster in which the comment is located and the first ordering information;
And displaying the comment set according to the second ordering information of each comment.
According to a second mode of the embodiment of the present application, clustering comments according to data information of the comments, determining a cluster where each comment is located includes:
acquiring information entropy of the comment content of each comment;
and for any comment, if the information entropy corresponding to the comment is smaller than a preset threshold value, determining that the cluster in which the comment is positioned is a worthless cluster.
According to the third mode of the embodiment of the present application, according to the information entropy of the comment content of each comment, the method further includes:
for any comment, if the information entropy corresponding to the comment is larger than a preset threshold, and the identity information of the communication paste publisher where the comment of the comment is located is consistent with the identity information of the comment publisher, determining that the cluster where the comment is located is a top cluster.
According to a fourth mode of the embodiment of the present application, according to the information entropy of the comment content of each comment, the method further includes:
for any comment, if the information entropy corresponding to the comment is larger than a preset threshold value and the comment contains remark information, determining that the cluster in which the comment is located is a top cluster.
According to a fifth mode of the embodiment of the present application, according to the information entropy of the comment content of each comment, the method further includes:
for any comment, if the information entropy corresponding to the comment is larger than a preset threshold, comment does not contain remark information and the praise amount of the comment meets a preset condition, determining that the cluster where the comment is located is a praise cluster.
According to a sixth mode of the embodiment of the present application, the obtaining information entropy of comment content of each comment further includes:
for any comment, if the information entropy corresponding to the comment is larger than a preset threshold, the comment does not comprise remark information, and the praise amount of the comment does not meet a preset condition, determining a cluster in which the comment is located as a time sequence cluster.
According to a seventh mode of the embodiment of the present application, for each cluster, according to the praise amount and the posting time of each comment in the cluster, first ordering information of each comment in the cluster is obtained, including:
ranking the comments in the cluster from high to low based on the praise amount, and generating first ranking information of each comment in the cluster;
if the comment and approval amounts of any two comments are the same, determining the sequence of the two comments in the cluster based on the sequence of the posting time of the two comments.
According to an eighth aspect of the embodiments of the present application, for each comment, according to a cluster type of a cluster in which the comment is located and the first ranking information, obtaining second ranking information of the comment in a comment set includes:
determining third ordering information of each cluster in the comment set based on a predetermined ordering rule of each cluster;
and for each comment, obtaining second ordering information of the comment in the comment set according to the third ordering information of the cluster in which the comment is located and the first ordering information of the comment.
According to another aspect of an embodiment of the present application, there is provided an apparatus for comment sorting, applied to a server, including:
the data information acquisition module is used for acquiring data information of each comment in the comment set shown in the to-be-exhibited f, wherein the data information comprises comment content, release time, praise amount of the comment, identity information of a communication paste publisher where the comment is located and identity information of the comment publisher;
the cluster determining module is used for classifying the comment set according to the data information of the comments to obtain a plurality of clusters, and the cluster types corresponding to each cluster are different;
the first ordering information generation module is used for obtaining first ordering information of each comment in each cluster according to the praise amount and the release time of each comment in each cluster;
The second ordering information generation module is used for obtaining second ordering information of the comment in the comment set according to the cluster type of the cluster in which the comment is positioned and the first ordering information for each comment;
and the sorting result display module is used for displaying the comment set according to the second sorting information of each comment.
According to another aspect of the embodiments of the present application, there is provided an electronic device including: memory, a processor, and a computer program stored on the memory, the processor executing the computer program to perform the steps of any of the methods of the various embodiments of the present application.
According to yet another aspect of 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 comment ordering method of any of the plurality of embodiments.
The beneficial effects that technical scheme that this application embodiment provided brought are:
valuable comments are screened out in various modes, and the comments are ordered according to the value of the comments, so that more valuable comments can be exposed in the comment area, and the interaction quantity and quality of the comment area can be benign increased; meanwhile, the technical scheme provided by the application can reduce the time cost and experience cost for the user to see the valuable comments, and can better understand the interpretation and conception of the works by the creator, so that the user can better interact with other users by the creator; for operators, the better the atmosphere of the comment area is, the more interested the user is in the interaction of the comment area, and the service time of the software is prolonged.
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 view of an application scenario for implementing comment ordering provided in an embodiment of the present application;
fig. 2 is a flow chart of a comment ordering method provided in an embodiment of the present application;
fig. 3 is a schematic view of a scenario for ordering comments of a worthless cluster according to an embodiment of the present application;
fig. 4 is a schematic flow chart of a cluster classification method according to an embodiment of the present application;
fig. 5 is a flow chart of a comment ordering method provided in an embodiment of the present application;
fig. 6 is a schematic structural diagram of a comment sorting device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device 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" 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 that at least one of the items defined by the term, e.g., "a and/or B" may be implemented 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.
Several terms which are referred to in this application are first introduced and explained:
the clustering cluster can achieve the effect of reacting the types of the elements by adding the same elements into the same cluster, meanwhile, the clustering cluster is different from the collection that a new classification standard is created by a plurality of element collections of the same type, the clustering cluster is the prior classification standard, whether each element is compounded with the clustering cluster standard or not is judged, if the clustering cluster standard is met, the clustering cluster is added, and if the clustering cluster standard is not met, the clustering cluster is taken as a scattered value to continuously judge whether the next clustering cluster standard is met or not.
The information entropy refers to a measurement standard for judging the amount of useful information in a sentence, and if the information entropy of the sentence is larger, the more useful information in the sentence is, the more valuable the information is; similarly, if the entropy of information in a sentence is smaller, the useful information in the sentence is smaller, and the information is less valuable.
The comment ordering method, device, electronic equipment, computer readable storage medium and computer program product provided by the application aim to solve the technical problems in the prior art.
The technical solutions of the embodiments of the present application and technical effects produced by the technical solutions of the present application are described below by describing several exemplary embodiments. It should be noted that the following embodiments may be referred to, or combined with each other, and the description will not be repeated for the same terms, similar features, similar implementation steps, and the like in different embodiments.
Fig. 1 is a schematic diagram of a system architecture for implementing a comment ordering method according to an embodiment of the present application, where the system architecture includes a first terminal 101, a second terminal 102, and a server 103.
The first terminal 101 and the second terminal 103 install and run an application program with a comment function, and main functions of the application program may include functions of playing video examples, posting a communication paste, posting article information, posting a photo, and the like. The user A inputs comment information in the first terminal 101, the first terminal 101 sends comment data information to the server 103, the server 103 processes the comments and displays the sorting results, and the first terminal 101 and the second terminal 102 acquire the latest server display results for the user A and the user B to check. The first terminal 101 and the second terminal 102 are connected to the server 103 via a wireless network or a wired network. The server 103 may be in the form of a single server, multiple servers, a cloud computing platform, a virtualization center, or the like. The server 103 mainly performs tasks of acquiring comment data information, generating comment sorting results, storing comment sorting results, that is, comment data information, and the like.
The embodiment of the application provides a comment ordering method, as shown in fig. 2, applied to a server, wherein the method comprises the following steps:
s110, acquiring data information of each comment in a set of comments to be displayed, wherein the data information comprises comment content, release time, praise amount, identity information of a communication paste publisher where the comment is located and identity information of the comment publisher;
in this embodiment, the comment to be displayed is that an application program with a comment function is installed on an electronic device such as a mobile terminal used by a user, and the main functions of the application program may include playing a video such as Tencel video \B station \love art, issuing a communication paste such as a known \pulse \microblog and the like, issuing article information such as public numbers and the like, issuing a photo such as a reddish book and the like. It should be noted that, taking comments in the communication paste as an example, the user who issues the comments in the embodiment of the present application may include a communication paste issuer, any user who registers the account number of the application program, and the embodiment of the present application is not specifically limited.
The comments to be displayed refer to comments which are not updated in total sequence after the data change, wherein the comments which can be changed in data can comprise comments which are just released by a user, comments which are praised by the user, comments which are cancelled by the user, comments which are replied by the user, comments which are deleted by the user, comments which are marked as praised by an operator, comments which are marked as worthless by the operator, and the like.
The method comprises the steps that a user inputs comment information at an application terminal, the terminal sends the comment data information to a server, the server obtains the comment data information, the comments are classified according to the data information, and the comments are added into corresponding aggregation clusters, wherein the comment data information can comprise comment content, comment release time, comment approval, identity information of a comment publisher of an exchange paste where the comment is located and identity information of the comment publisher, remark information of the comment such as real-name comment statement information of which the user release information is marked, comment or non-value comment information of which information is marked by an operator during auditing information, and the like.
It should be noted that, taking comments in the communication paste as an example, the comment content of the comments may include text comment content, picture comment content and the like; after the comment posting time is acquired, converting time information from Beijing standard time to 11-bit Greenwich standard time through a preset algorithm, namely generating comment identification information through the comment posting time information, and taking the comment identification information as a comment ordering method in a server time dimension; the identity information of the comment promulgator may include the identity information of the communication paste promulgator, which is not specifically required in the present application.
S120, classifying the comment set according to the comment data information to obtain a plurality of cluster clusters, wherein the cluster types corresponding to each cluster are different;
in this embodiment of the present invention, after a terminal sends data information of different comments to a server, the server classifies all comments in a comment set according to a preset classification standard, where, taking a comment set of an ac patch as an example, comment positions in the comment set may include: comment information replied under comment patches, and the like, which is not particularly limited in this application.
The cluster is a preset set of comments with salient features, the cluster type of the cluster is characterized by the salient features common to all comments contained in the cluster, wherein the cluster type features can be used for distinguishing different cluster types, and different types of comments are added into different cluster types, so that the technical effect of classifying the comments through the different features of the comments is realized, wherein one cluster corresponds to one cluster type, and one comment corresponds to one cluster. It should be noted that the cluster type of the cluster can be adjusted according to the type of the application software and the commented object, if the commented object is a post, the remark condition can be newly added as a commentary keyword; similarly, if the commented object is a video, the new remark condition is time skip, and the operator performs personalized setting on the server according to the product requirement, which is not specifically required in the embodiment of the application.
Specifically, when classifying the concentrated comments of the comments according to the comment features, the classification standards related to multiple dimensions can include comment content value, comment publisher weights, comment liveness, comment approval, comment posting time, special comment labeling, comment attention, comment discussion and the like, the comments are evaluated by the multiple dimensions, and the comments are added into different clusters according to evaluation results.
S130, for each cluster, obtaining first ordering information of each comment in the cluster according to the praise amount and release time of each comment in the cluster;
in the embodiment of the application, after the comments are added into different clusters, the server generates local first ordering information of the comments in the clusters according to the data information of the comments, wherein the local first ordering information is generated based on part of data information including remark information of the comments, weight of comment publishers and identity information of the comment publishers. It should be noted that the local first information generated in different clusters may be the same or different, which is not specifically required in the embodiment of the present application.
After the local first ordering information is generated, other data information including praise amount, comment release time and the like of the comments is obtained, the obtained data information is subjected to processing including binary conversion, timestamp generation and the like, and global first ordering information is generated by combining the local first ordering information, wherein the global first ordering information of different comments in the same cluster can be different or the same.
If the global first ordering information is different, ordering comments in the cluster from high to low in different cluster clusters according to the calculation result of the global first ordering information in the cluster, and storing the ordering result in the cluster in a corresponding cluster;
if the global first ordering information is the same, comment posting time of a plurality of comments with the same global first ordering information in the cluster is obtained, a time stamp is generated according to the posting time of the comments, and comments with later posting time are preferentially displayed according to the time sequence, so that the technical problem that the global first ordering information is the same is solved. By comprehensively considering the ordering method generated by multiple dimensions, the method can meet the requirement that the user views valuable comment information, and can better display the attention and discuss comments of high-quality comments, and the beneficial effects of maintaining the attention of the user and prolonging the duration of the user using the software are achieved at the angle of an operator.
S140, for each comment, obtaining second ordering information of the comment in the comment set according to the cluster type of the cluster in which the comment is located and the first ordering information;
and S150, displaying the comment set according to the second ordering information of each comment.
In the embodiment of the application, after the comments in the cluster are ordered and the first ordering information is generated, the server sends the comment ordering result in the cluster to the total cluster corresponding to the comment set, after the comment set receives the ordering result sent by the server, third ordering information is generated according to the cluster where each comment is located, the third ordering information and the global first ordering information are combined in a preset mode to generate global second ordering information, the comments are ordered in the comment set from high to low according to the calculation result of the global second ordering information, and the ordering result is displayed in the comment set display interface. It should be noted that, the global second ranking information of different comments in the comment set may be different or the same, and the embodiment of the present application does not make a specific requirement.
And if the global second ordering information is different, ordering the comments in the comment set according to the calculation result of the global second ordering information from high to low, and displaying the comment ordering result on a comment display interface.
If the global second ordering information of the multiple comments with the same cluster mark is the same, comment posting time of the multiple comments is obtained, a time stamp is generated according to the posting time of the comments, and comments with later posting time are preferentially displayed according to the time sequence, so that the problem that the second ordering information is the same is solved; if the global second ordering information of the multiple comments with different cluster identifications is the same, third ordering information of the comments is obtained, and ordering is carried out from high to low according to the calculation result of the third ordering information of the comments;
According to the method and the device, the characteristics of the comments are analyzed, the comments are added into different clusters, the first ordering information is generated in the clusters, the second ordering information is generated according to the type of the clusters and the first ordering information, the comment ordered result is displayed by the comment set according to the second ordering information, the limitation that the comments are ordered according to the release time or the point approval amount in the prior art is broken, users can conveniently view the comments with richer content, the authors comments are viewed faster, the comments with high attention and high interaction amount are viewed faster, and the beneficial effect of bringing better use experience for users is achieved.
Based on the foregoing embodiments, as an optional embodiment, clustering the comments according to the data information of the comments, and determining a cluster in which each comment is located includes:
s210, obtaining information entropy of comment content of each comment;
the information entropy is a preset condition for screening the richness of comment content, the calculation mode of the information entropy can comprise the steps of screening useful information in the comment through an algorithm, calculating the duty ratio of the useful information through a mode of constructing a preset formula, and obtaining a result which is the information entropy; if the comment is detected to have text paragraphs which are not consistent with the reference value, such as the non-civilized expression, in the useful information screening, the comment is directly added into the non-value cluster, wherein if the system does not detect the non-value text paragraphs, or the system erroneously identifies the valuable text paragraphs as the non-value text paragraphs, operators can label the comment again, and the screening algorithm is optimized or reset so as to achieve the technical effect of judging whether the comment is the non-value comment.
According to the method and the device for setting the information entropy, different settings can be made according to different types of the comment objects, if the types of the comment objects are question-answer help-asking, if the comment content is only 'yes', the help-asking can be answered, and at the moment, the information entropy threshold can be lowered; if the comment object is of the type of the discussion post, the post discussion problem cannot be solved if the comment content is only 'yes', and the information entropy threshold can be modified to be within a threshold range capable of answering the post problem.
Besides the information entropy threshold, the comments can also ensure the screening of the worthless comments by setting detection of the unknown wording, periodic review of the comments by operators and the like. When an operator reviews the comments, in order to prevent that no characters in the comments are only punctuation marks as no value when information entropy is preset, but a user forms new characters or images which are attached to the subject of the comment object in the comments by using the arrangement and combination of various punctuation marks, the operator removes the comments from the no-value cluster, updates the setting and detection modes of the information entropy threshold value and enters the judgment of the next condition, so that the beneficial effect of preventing the valuable comments from being buried is achieved.
S220, for any comment, if the information entropy corresponding to the comment is smaller than a preset threshold, determining that the cluster in which the comment is located is a worthless cluster.
In this embodiment of the present invention, comment types included in a worthless cluster may include that comment content includes a non-civilized term, that comment content is all punctuation and does not include useful text information, that useful information included in a comment is less, that useful information included in a comment is not associated with a comment object, that comment includes a negative statement of inflammatory activity, and so on, and that a set formed by these comments, or a added cluster, does not have a reference value to a comment object and other users, because useful information included in these comments is less, the cluster is a worthless cluster.
As shown in fig. 3, if comment a in fig. 3 contains a non-civilized term preset by an operator, adding the comment into a worthless cluster; in fig. 3, comment b contains less valuable text information, the calculated information entropy is assumed to be 1, and the preset information entropy threshold is assumed to be 5, so that the comment information entropy is smaller than the preset threshold, and comment b is added into a worthless cluster; in fig. 3, comment c contains less valuable text information, and the calculated information entropy is assumed to be 1, and is smaller than a preset threshold value, comment c is added into a non-valuable cluster, and comment c is preferentially displayed in the non-valuable cluster because the praise amount of comment c is higher than that of comment b and comment a, and comment b and comment a are displayed in a sorted manner according to the time reversal order because the praise amounts of comment b and comment a are the same. It should be noted that, the operator may set to hide comments affecting the user browsing experience, such as a speaker with flaring, according to needs or user feedback, and not display, which is not specifically required in the present application.
According to the embodiment of the application, through the information entropy screening mode, the comments with single repetition of the content or the property of being profoundly harmful are preferentially screened out, and the comments are preferentially added into the worthless cluster, so that server resources can be saved, more resources can be distributed to the server to conduct classified display on the comments with rich content, and the technical effect of classifying the comments is achieved more quickly and accurately.
On the basis of the above embodiments, as an optional embodiment, obtaining information entropy of comment content of each comment, and then further includes:
and S310, for any comment, if the information entropy corresponding to the comment is determined to be larger than a preset threshold value, and the identity information of the communication paste publisher where the comment is located is consistent with the identity information of the comment publisher, determining that the cluster where the comment is located is a top-set cluster.
In the embodiment of the present application, the comment types included in the top cluster may include comments posted by the author, i.e., author comments; high-quality comments marked by operators, namely comments, with high acceptance and high attention; for anonymous communication paste, a user actively selects real-name declaration comments published by a real name when the comments are published, and after operation auditing is passed, the real-name declaration comments are displayed. Because the author comments can more quickly and directly enable the user to know the actual intention or the creation idea of the author to post the communication paste or the article, the comments are added into the top-set cluster, and the comments in the top-set cluster are required to be preferentially displayed.
In this embodiment of the present application, the identity information of the comment on the communication paste issuer and the identity information of the comment issuer take the communication paste as an example, where the comment issuer may include the communication paste issuer and the comment issuer of the comment communication paste, and the comment issuer may include the comment issuer of the comment communication paste and the comment issuer of the comment under the comment communication paste. It should be noted that when there are multiple sub-comments in the comments of the comment interchange paste, the sorting mode of the top cluster in the sub-comments may include, preferentially displaying the comments of the interchange paste publisher; if no comment of the communication paste publisher exists, the comments of the comment communication paste publisher are preferentially displayed, and if the author publishes a plurality of comments, the comments are ordered according to the positive sequence of the comment publishing time of the author; the rest comments are ranked according to the praise amount from high to low, and if the praise amounts are the same, the comments are ranked according to the time reverse order.
It should be noted that if a comment posted by a user is marked as a top comment by a certain communication paste, if the user logs out of an account, the original comment is reserved, part of identity information for matching whether the comment is an author comment is reserved, and data information corresponding to a high-quality comment and identity information of a publisher of the comment are reserved in a comment object comment set when ordering information is generated.
By matching the identity information of the comment promulgator and the comment object, the information promulgated by the creator of the comment object can be quickly selected, and the information can be preferentially displayed, so that a user can know the intention and idea of the creator more quickly when browsing comments, can better publish own ideas, and creates better discussion atmosphere.
On the basis of the above embodiments, as an optional embodiment, obtaining information entropy of comment content of each comment, and then further includes:
s320, for any comment, if the information entropy corresponding to the comment is determined to be larger than a preset threshold value and the comment contains remark information, determining that the cluster in which the comment is located is a top cluster.
It should be noted that comments in the top-set cluster can be marked by operators or authors, the terminal sends the author settings to the server, the server moves the comments from the corresponding cluster to the top-set cluster, sorts the comments in the top-set cluster and displays the results;
if the operator selects a plurality of comments to mark as top-set display comments at the same time, after receiving operator setting data sent by the terminal, the server displays the comments displayed on the selected top-set display preferentially according to the praise amount of the selected comments from high to low, and if the comments with the same praise amount exist, the comments with the same praise amount are ordered according to the reverse order of time;
If the operator selects a plurality of comments to mark as top-set display comments successively, the server can sort the comments displayed on the selected top-set according to the time sequence of the top-set comments set by the operator, or can display the comments according to the praise amount of the comments displayed on the selected top-set from high to low, and the method and the device do not have specific requirements for the comments.
By screening remark information of comments, high-quality comments considered by operators can be quickly selected, and note that, taking an exchange paste comment set as an example, if real-name declaration comments, author comments and comments exist in the comment set at the same time, the comments are displayed according to the sequence of the real-name declaration, the author comments and the comments, and the display sequence can be set according to operators, so that the application is not limited in detail. When the high-quality comments with high liveness, high attention and high discussion are preferentially displayed, a user can browse valuable high-quality comments faster when browsing the comments, the use experience of the user can be improved, the viscosity of the user is maintained, and the time of using the software product by the user is prolonged.
On the basis of the above embodiments, as an optional embodiment, obtaining information entropy of comment content of each comment, and then further includes:
For any comment, if the information entropy corresponding to the comment is determined to be larger than a preset threshold, comment does not contain remark information, and comment point approval of the comment meets a preset condition, determining that a cluster in which the comment is located is an approval cluster.
In this embodiment, after the comment does not satisfy the condition of the worthless cluster and the top cluster, the point-to-volume information of the comment is obtained, and whether the point-to-volume of the comment satisfies a preset point-to-volume condition that the comment needs to satisfy in the preset order cluster is determined, where it is to be noted that the preset condition may be set by an operator, and the preset determination condition may be adjusted for different types of ac patches, by taking the ac patch as an example, where the preset condition may include: judging whether the point praise amount meets the formula that the point praise amount is more than or equal to 2.5+e λ*n Where λ takes a fixed value of 0.25 and n is the ranking of the comment in the praise cluster.
If the comments meet the judgment conditions of the praise clustering clusters, adding the comments into the praise clustering clusters, and arranging the comments in the praise clustering clusters from high to low according to the praise amount, and if the praise amount is the same, arranging the comments according to the order of comment release time and the reverse order. It should be noted that, whenever a new comment satisfies the criterion of the praise cluster and is added to the praise cluster, it is required to determine whether the praise amount of the last comment in the praise cluster still satisfies the criterion of the praise cluster, if not, the praise cluster is removed, and if still satisfied, the praise cluster is not moved.
According to the embodiment of the invention, the praise condition is preset in the praise cluster, so that comments contained in the praise cluster are comments with high approval, namely comments with high praise are taken as examples, and a user can know the attention points of other users and the watching experience of the video more quickly after browsing valuable comments.
On the basis of the above embodiments, as an optional embodiment, obtaining information entropy of comment content of each comment, and then further includes:
for any comment, if the information entropy corresponding to the comment is larger than a preset threshold, comment does not contain remark information, and comment point approval of the comment does not meet a preset condition, determining a cluster in which the comment is located as a time sequence cluster.
In the embodiment of the application, after the comments do not meet the conditions of the worthless cluster, the top cluster and the praise cluster, adding the comments into the time sequence cluster, obtaining the posting time information of the comments, and arranging the comments according to the positive sequence of the posting time, wherein the arranging mode of the comments can comprise arranging the comments according to the reverse sequence of the posting time; the method may further include ranking the comments according to the number of praise and praise from large to small, and ranking the comments according to the positive sequence of comment posting time if the number of praise and praise is the same, which is not particularly limited in the embodiment of the present application.
On the basis of the foregoing embodiments, as an alternative embodiment, as shown in fig. 4, for each cluster, first ranking information of each comment in the cluster is obtained according to the praise amount and the posting time of each comment in the cluster, including:
s410, sorting comments in the cluster from high to low based on the praise amount, and generating first sorting information of each comment in the cluster;
in this embodiment, the manner of generating the first ranking information may include generating score information of a comment, where the score information may be read by a server and corresponds to at least one target value, where the target value is comment content. It should be noted that, if the score information uniquely corresponds to the target value, the server sorts the target value corresponding to the score information according to the size of the score information after obtaining the score information, and displays the sorting result. If the score information corresponds to a plurality of target values, the comment identification information value, such as the comment_id information value, is generated, and after the comment identification information value is generated, the comment is ordered by ordering the size of the identification information value, so that the effect of ordering the comment is achieved. It should be noted that, the target value corresponding to the score information may be comment content or may be an identification information value of the comment, which is not specifically required in the present application.
The specific method for generating the score information is that the score information of the comment is generated by reading the data information of the comment, for example, reading the praise amount of the comment, converting the praise amount information into a preset binary data string, for example, a binary data string, presetting the number of data strings of one score information, complementing the deficiency. For example, the score information corresponding to the first ordering information of a comment is preset to include a 36-bit data string, the comment is a comment with a praise amount of 1 in a time sequence cluster, and the method for generating the comment score information can include judging whether the comment score information is a non-value comment, if the comment score is a non-value comment, the first position is 0, and if the comment score is not a non-value comment, the first position is 1; judging whether the real name statement is true, if true, determining a second position 1, and if not, determining a second position 0; judging whether the comment is an author comment or not, if so, setting a third position 1, and if not, setting a third position 0; judging whether the comment is an audit or not, if the comment is an audit, the fourth position 1 is the fourth position 0, and if the comment is not an audit, because the comment is a comment in a time sequence cluster, according to the judging rule, the first four bits of the score information are 1000, according to the praise quantity 1, the last thirty-two bits of the score information, namely 00000000000000000000000000000001, are generated, the first four bits and the last thirty-two bits are combined to obtain score information corresponding to the comment, 100000000000000000000000000000000001, the comments are ordered through the score information, and it is noted that the number of bits of a data string corresponding to the score information in the embodiment of the present application can be set by an operator, and the embodiment of the present application does not require specific requirements.
S420, if the comment amounts of any two comments are the same, determining the sequence of the two comments in the cluster based on the sequence of the release time of the two comments.
In this embodiment, if the praise amounts of any two comments are the same, it should be noted that any two comments with the same praise amounts in the same cluster are referred to. The execution mode of ordering is carried out according to the sequence of the posting time of the two comments, which comprises the steps of converting Beijing standard time into 11-bit Greenwich standard time, and obtaining ordering results of comment time dimension by comparing the converted 11-bit Greenwich standard time; the method specifically can further comprise the step of generating identification information of the comments, and the comments are ordered according to the size of the identification information, wherein the identification information of the comments can comprise time information and the like, and specific requirements are not required for the comments in the embodiment of the application.
The first identification information of the comments is generated in a mode of combining the score information and the comment identification information, and the comments are ordered according to the value of the first identification information, so that the comments can be ordered from multiple dimensions, the beneficial effects that the comments browsed by a user are valuable comments are guaranteed, the realizability of the comments is guaranteed, and the technical effects that the ordering mode can be set according to requirements according to the content and the characteristics of products are also guaranteed.
On the basis of the foregoing embodiments, as an alternative embodiment, as shown in fig. 5, for each comment, obtaining second ranking information of the comment in the comment set according to a cluster type of a cluster in which the comment is located and the first ranking information, including:
s810, determining third ordering information of each cluster in the comment set based on a predetermined ordering rule of each cluster;
s820, for each comment, obtaining second ordering information of the comment in the comment set according to the third ordering information of the cluster in which the comment is located and the first ordering information of the comment.
In this embodiment of the present application, setting the ranking rule of each cluster may include, for example, setting a top cluster to display preferentially, and then displaying the clusters in order of the top cluster, the time sequence cluster and the worthless cluster, where the preferential display of the clusters may be understood as preferentially displaying all comments in the cluster, and displaying all comments in the next cluster after displaying the comments in the cluster according to the first ranking information in the cluster, where it is noted that the preset ranking rule of the cluster may be adjusted according to the characteristics of the object to be commented.
The third ordering information is the ordering mode of different clusters, namely the third ordering information is generated according to the cluster where the comment is located. Taking the data string corresponding to the generated preset score information as an example, assuming a data string with the third preset information length of 40 bits, if a comment bit is in a time Xu Julei cluster, counting comments with a comment bit of 1, if the comment is a comment in a top cluster, setting a first position of 1, and if the comment is not in the top cluster, setting a first position of 0; if the comments are comments in the praise cluster, the second position 1 is the comment, and if the comments are not in the praise cluster, the second position 0 is the comment; if the comment is a comment in the time sequence cluster, the third position 1 is the comment, and if the comment is not the comment in the time sequence cluster, the third position 0 is the comment; if the comment is a comment in the non-valued cluster, the fourth position 1 is the comment, if the comment is not the comment in the non-valued cluster, the fourth position 0 is the comment, and if the comment is known to be the comment in the time sequence cluster, the score information corresponding to the third preset information of the comment is 0010000000000000000000000000000000000000. And if the praise amount of the comment is 1, the first preset information of the comment is 100000000000000000000000000000000001, the third information is combined with the first information to obtain the second preset information of the comment, namely a 40-bit score information data string corresponding to the comment, and the comments are ordered 0010100000000000000000000000000000000001 through the generated second preset information.
The second preset information of the comments is generated in a mode of combining the first preset information and the third preset information, the comments are ordered according to the value of the second preset information, the display sequence among the cluster clusters is guaranteed through the third preset information, the display sequence of the comments in different cluster clusters is guaranteed through the first preset information, the second preset information for finally ordering the comments in the comment set is obtained, the comments can be ordered from multiple dimensions, and the comments browsed by a user are guaranteed to be valuable comments.
The embodiment of the application provides a comment ordering device, as shown in fig. 6, the comment ordering device may include: a data information acquisition module 101, a cluster determination module 102, a first ranking information generation module 103, a second ranking information generation module 104, and a ranking result display module 105, wherein,
the data information acquisition module 101 is configured to acquire data information of each comment in a set of comments to be displayed, where the data information includes comment content, posting time, praise amount of the comment, and identity information of a communication post publisher where the comment is located and a comment publisher;
the cluster determining module 102 is configured to classify the comment set according to the comment data information, and obtain a plurality of clusters, where each cluster corresponds to a different cluster type;
The first ranking information generating module 103 is configured to obtain, for each cluster, first ranking information of each comment in the cluster according to the praise amount and the release time of each comment in the cluster;
the second ranking information generating module 104 is configured to obtain, for each comment, second ranking information of the comment in the comment set according to a cluster type of a cluster in which the comment is located and the first ranking information;
and the ranking result display module 105 is used for displaying the comment set according to the second ranking information of each comment.
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 electronic equipment, 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 comment ordering method, and compared with the related technology, the method can realize the steps of: according to the method and the device, the characteristics of the comments are analyzed, the comments are added into different clusters, the first ordering information is generated in the clusters, the second ordering information is generated according to the type of the clusters and the first ordering information, the comment ordered result is displayed by the comment set according to the second ordering information, the limitation that the comments are ordered according to the release time or the point approval amount in the prior art is broken, users can conveniently view the comments with richer content, the authors comments are viewed faster, the comments with high attention and high interaction amount are viewed faster, and the beneficial effect of bringing better use experience for users is achieved.
In an alternative embodiment, an electronic device is provided, as shown in fig. 7, the electronic device 4000 shown in fig. 7 includes: a processor 4001 and a memory 4003. Wherein the processor 4001 is coupled to the memory 4003, such as via a bus 4002. Optionally, the electronic device 4000 may further comprise a transceiver 4004, the transceiver 4004 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data, etc. It should be noted that, in practical applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 is not limited to the embodiment of the present application.
The processor 4001 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 4001 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
The memory 4003 is used for storing a computer program that executes an embodiment of the present application, and is controlled to be executed by the processor 4001. The processor 4001 is configured to execute a computer program stored in the memory 4003 to realize the steps shown in the foregoing method embodiment.
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.
The terms "first," "second," "third," "fourth," "1," "2," and the like in the description and in the claims of this application and in the above-described figures, if any, 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 where appropriate such that the embodiments of the present application described herein may be implemented in other sequences than those illustrated or otherwise described.
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 (11)
1. A comment ordering method, applied to a server, comprising:
acquiring data information of each comment in a comment set to be displayed, wherein the data information comprises comment content, release time, praise amount, identity information of a communication paste publisher where the comment is located and identity information of the comment publisher;
classifying the comment set according to the data information of the comments to obtain a plurality of cluster clusters, wherein the cluster types corresponding to each cluster are different;
for each cluster, according to the data information of each comment in the cluster, obtaining first ordering information of each comment in the cluster;
for each comment, obtaining second ordering information of the comments in the comment set according to the cluster type of the cluster in which the comment is positioned and the first ordering information;
and displaying the comment set according to the second sorting information of each comment.
2. The comment ordering method of claim 1, wherein the clustering the comments according to the data information of the comments, determining a cluster in which each comment is located, includes:
acquiring information entropy of the comment content of each comment;
And for any comment, if the information entropy corresponding to the comment is smaller than the preset threshold, determining the cluster in which the comment is located as a worthless cluster.
3. The comment ordering method of claim 2, wherein the obtaining information entropy of the comment content of each comment further includes:
and for any comment, if the information entropy corresponding to the comment is determined to be larger than the preset threshold value, and the identity information of the comment publisher is consistent with the identity information of the communication paste publisher where the comment is located, determining that the cluster where the comment is located is a top-set cluster.
4. The comment ordering method of claim 2, wherein the obtaining information entropy of the comment content of each comment further includes:
and for any comment, if the information entropy corresponding to the comment is determined to be larger than the preset threshold value and the comment contains remark information, determining that the cluster where the comment is located is a top-set cluster.
5. The comment ordering method of claim 2, wherein the obtaining information entropy of the comment content of each comment further includes:
And for any comment, if the information entropy corresponding to the comment is determined to be larger than the preset threshold, the comment does not contain remark information, and the comment point praise amount of the comment meets a preset condition, determining that the cluster in which the comment is positioned is a praise cluster.
6. The comment ordering method of claim 2, wherein the obtaining information entropy of the comment content of each comment further includes:
and for any comment, if the information entropy corresponding to the comment is determined to be larger than the preset threshold, the comment does not contain remark information, and the comment point praise amount of the comment does not meet the preset condition, determining the cluster in which the comment is located as a time sequence cluster.
7. The comment ordering method of any one of claims 1-6, wherein for each cluster, obtaining first ordering information of comments in the cluster according to the praise amount and the posting time of the comments in the cluster includes:
ranking the comments in the cluster from high to low based on the comment approval quantity, and generating first ranking information of each comment in the cluster;
If the comment and approval amounts of any two comments are the same, determining the sequence of the two comments in the cluster based on the sequence of the release time of the two comments.
8. The comment ordering method according to any one of claims 1 to 7, wherein the obtaining, for each comment, second ordering information of the comments in the comment set according to a cluster type of a cluster in which the comment is located and the first ordering information includes:
determining third ordering information of each cluster in the comment set based on a predetermined ordering rule of each cluster;
and for each comment, obtaining second ordering information of the comments in the comment set according to the third ordering information of the cluster in which the comments are located and the first ordering information of the comments.
9. A comment sequencing device, characterized by being applied to a server, comprising:
the system comprises a data information acquisition module, a display module and a display module, wherein the data information acquisition module is used for acquiring data information of each comment in a set of comments to be displayed, and the data information comprises comment content, release time, praise amount of the comments, identity information of a communication paste publisher where the comments are located and identity information of the comment publisher;
The cluster determining module is used for classifying the comment set according to the data information of the comments to obtain a plurality of clusters, and the cluster types corresponding to each cluster are different;
the first ordering information generation module is used for obtaining first ordering information of each comment in each cluster according to the data information of each comment in the cluster;
the second ordering information generation module is used for obtaining second ordering information of the comments in the comment set according to the cluster type of the cluster in which the comments are positioned and the first ordering information for each comment;
and the sorting result display module is used for displaying the comment set according to the second sorting information of each comment.
10. An electronic device 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 method according to any one of claims 1-8.
11. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the steps of the comment ordering method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415697.XA CN116150474A (en) | 2022-11-11 | 2022-11-11 | Comment ordering method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415697.XA CN116150474A (en) | 2022-11-11 | 2022-11-11 | Comment ordering method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116150474A true CN116150474A (en) | 2023-05-23 |
Family
ID=86360802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211415697.XA Pending CN116150474A (en) | 2022-11-11 | 2022-11-11 | Comment ordering method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116150474A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663505A (en) * | 2023-07-31 | 2023-08-29 | 厦门起量科技有限公司 | Comment area management method and system based on Internet |
-
2022
- 2022-11-11 CN CN202211415697.XA patent/CN116150474A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663505A (en) * | 2023-07-31 | 2023-08-29 | 厦门起量科技有限公司 | Comment area management method and system based on Internet |
| CN116663505B (en) * | 2023-07-31 | 2023-10-13 | 厦门起量科技有限公司 | Comment area management method and system based on Internet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018177251A1 (en) | Application program processing method, computer device and storage medium | |
| US11875273B2 (en) | Machine learning classification of digital content for mobile devices | |
| CN106708817B (en) | Information searching method and device | |
| WO2019169978A1 (en) | Resource recommendation method and device | |
| CN105187237B (en) | The method and apparatus for searching associated user identifier | |
| CN105787133B (en) | Advertisement information filtering method and device | |
| US20140095308A1 (en) | Advertisement distribution apparatus and advertisement distribution method | |
| CN104901817A (en) | Method and device for pushing target information | |
| CN109377401B (en) | Data processing method, device, system, server and storage medium | |
| CN105045833B (en) | The classification method and device of user's friend relation | |
| CN101901252A (en) | Method for integrating same user data on multiple websites and integration platform | |
| CN110889076B (en) | Comment information publishing method, device, client, server, system and medium | |
| CN112989169A (en) | Target object identification method, information recommendation method, device, equipment and medium | |
| CN111026969B (en) | Content recommendation method and device, storage medium and server | |
| CN111163072A (en) | Method and device for determining characteristic value in machine learning model and electronic equipment | |
| CN103514282A (en) | Method and device for displaying search results of videos | |
| US20230030560A1 (en) | Methods and systems for tagged image generation | |
| CN116150474A (en) | Comment ordering method and device, electronic equipment and readable storage medium | |
| CN113222687A (en) | Deep learning-based recommendation method and device | |
| CN110110197B (en) | Information acquisition method and device | |
| CN110895781A (en) | Dish type recommendation method and device, electronic equipment and storage medium | |
| CN114840743B (en) | Model recommendation method and device, electronic equipment and readable storage medium | |
| EP3923164A2 (en) | Method and apparatus of presenting information, electronic device and storage medium | |
| CN115618120A (en) | Public number information pushing method, system, terminal equipment and storage medium | |
| CN100592300C (en) | Data display method and device |
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 |