Method and apparatus for displaying comments based on likes of internet community comments

Abstract

The application relates to a comment display method and device based on Internet community comment likes, which comprises the following steps: when receiving a like operation of a user on any comment in an Internet community, searching for and identifying a keyword in the comment; when the keyword is identified in the comment, determining whether the keyword is in a search flow keyword blacklist; when the keyword is not in the search flow keyword blacklist, determining whether the number of posts in an Internet community search result corresponding to the keyword is greater than or equal to a preset threshold; when the number of posts is greater than or equal to the preset threshold, obtaining an Internet community search result page URL corresponding to the keyword, and associating the Internet community search result page URL with the keyword; and highlighting the keyword in the comment. Through the technical scheme, small and special interest topics in a community can find users who are really interested in the topics, and the content transmission efficiency of the community platform is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet data processing, and in particular to a comment display method and device based on Internet community comment likes. BACKGROUND

[0002] A community APP has a search entry, and a user actively inputs a search keyword in a search box to complete the search of related content in the community. The active search traffic of the community is not high, and in fact, the community APP user has a large amount of potential search demand. Only the user does not know what kind of keyword to use to search in the community, and does not know what kind of keyword can search out good related results in the community content. SUMMARY

[0003] To overcome the problems in the related art, the present application provides a comment display method and device based on Internet community comment likes, so as to facilitate interested users to further expand the browsing of related content, bring user value, greatly increase the probability of effective reaching of the real interested population of long-tail small post and historical high-quality old post, and improve the efficiency of community platform content dissemination.

[0004] According to a first aspect of an embodiment of the present application, a comment display method based on Internet community comment likes is provided, and the method comprises:

[0005] When a like operation of a user on any comment in an Internet community is received, a search keyword in the comment is identified;

[0006] When it is identified that the search keyword is contained in the comment, it is determined whether the search keyword is in a search flow keyword blacklist;

[0007] When the search keyword is not in the search flow keyword blacklist, it is determined whether the number of posts in an Internet community search result corresponding to the search keyword is greater than or equal to a preset threshold;

[0008] When the number of posts is greater than or equal to the preset threshold, an Internet community search result page URL corresponding to the search keyword is obtained, and the Internet community search result page URL is associated with the search keyword in the URL;

[0009] The search keyword in the comment is highlighted.

[0010] In an embodiment, preferably, the method further comprises:

[0011] A selection or click command on the search keyword is received, and the display content is jumped to a page corresponding to the Internet community search result page URL according to the selection or click command.

[0012] In one embodiment, preferably, the search keyword recognition on the comment comprises:

[0013] The search keyword recognition on the comment is performed by a pre-trained search keyword extraction model.

[0014] In one embodiment, preferably, the method further comprises:

[0015] Selecting a target topic name with a post quantity greater than a preset quantity in an Internet community according to a preset time interval;

[0016] Determining a search keyword set according to the target topic name;

[0017] Adding the search keyword set into a user-defined word library of Chinese word segmentation;

[0018] Performing Chinese word segmentation operation on a target comment meeting a preset condition in the Internet community using the user-defined word library to obtain a Chinese word segmentation result;

[0019] Performing BIO tagging on each target comment according to the search keyword set and the Chinese word segmentation result to obtain tagged training data;

[0020] Performing deep learning training using the tagged training data and a BERT training model to obtain the search keyword extraction model.

[0021] In one embodiment, preferably, the preset condition comprises:

[0022] A historical like quantity of the comment is greater than a preset like quantity.

[0023] In one embodiment, preferably, performing BIO tagging on each target comment according to the search keyword set and the Chinese word segmentation result to obtain tagged training data comprises:

[0024] Comparing each word in the Chinese word segmentation result with words in the search keyword set in turn;

[0025] When the word in the Chinese word segmentation result is the same as the word in the search keyword set, the word is tagged as a keyword, otherwise, the word is tagged as a non-keyword.

[0026] In one embodiment, preferably, the method further comprises:

[0027] Monitoring and counting a search result satisfaction degree of all search keywords according to a preset time period;

[0028] Adding a search keyword with a search result satisfaction degree lower than a preset satisfaction degree to a search keyword blacklist.

[0029] According to a second aspect of the embodiments of the present application, a comment display device based on Internet community comment likes is provided, and the device comprises:

[0030] An identification module is configured to perform search keyword identification on a comment in an Internet community when receiving a like operation of a user on the comment;

[0031] A first determination module is configured to determine whether a search keyword is in a search flow keyword blacklist when the search keyword is identified in the comment;

[0032] A second determination module is configured to determine whether a post quantity in an Internet community search result corresponding to the search keyword is greater than or equal to a preset threshold when the search keyword is not in the search flow keyword blacklist;

[0033] An association module is configured to obtain an Internet community search result page URL corresponding to the search keyword and associate the Internet community search result page URL with the search keyword in terms of a website address when the post quantity is greater than or equal to the preset threshold;

[0034] A display module is configured to highlight the search keyword in the comment.

[0035] In an embodiment, preferably, the device further comprises:

[0036] A jump module is configured to receive a selection or click command on the search keyword and jump display content to a page corresponding to the Internet community search result page URL according to the selection or click command.

[0037] In an embodiment, preferably, the identification module is configured to:

[0038] Perform search keyword identification on the comment by using a pre-trained search keyword extraction model.

[0039] In an embodiment, preferably, the device further comprises:

[0040] A selection module is configured to select a target topic name in an Internet community according to a preset time interval, wherein a post quantity of the target topic name is greater than a preset quantity;

[0041] A third determination module is configured to determine a search keyword set according to the target topic name;

[0042] An addition module is configured to add the search keyword set to a user-defined word library of Chinese word segmentation;

[0043] The word segmentation module is used to perform Chinese word segmentation on target comments in the Internet community that meet preset conditions using the user-defined dictionary, and obtain Chinese word segmentation results.

[0044] The annotation module is used to perform BIO annotation on each target comment based on the search keyword set and the Chinese word segmentation results to obtain annotated training data;

[0045] The training module is used to perform deep learning training using the labeled training data and the BERT training model to obtain the search keyword extraction model.

[0046] In one embodiment, preferably, the preset conditions include:

[0047] The comment has a greater historical number of likes than the preset number of likes.

[0048] In one embodiment, preferably, the annotation module is used for:

[0049] Each word in the Chinese word segmentation result is compared sequentially with the words in the search keyword set;

[0050] When a word in the Chinese word segmentation result is the same as a word in the search keyword set, the word is marked as a keyword; otherwise, it is marked as a non-keyword.

[0051] In one embodiment, preferably, the device further includes:

[0052] The statistics module is used to monitor and analyze the satisfaction level of search results for all search keywords according to a preset time period.

[0053] The processing module is used to add search keywords whose search result satisfaction is lower than the preset satisfaction level to the search traffic keyword blacklist.

[0054] According to a third aspect of the present invention, a comment display device based on internet community comments and likes is provided, the device comprising:

[0055] processor;

[0056] Memory used to store processor-executable instructions;

[0057] The processor is configured as follows:

[0058] When a user likes any comment in an online community, the system identifies search keywords for that comment.

[0059] When a search keyword is identified in the comment, it is determined whether the search keyword is in the blacklist of search terms.

[0060] When the search keyword is not in the blacklist of search traffic terms, determine whether the number of posts in the search results of the Internet community corresponding to the search keyword is greater than or equal to a preset threshold.

[0061] When the number of posts is greater than or equal to a preset threshold, obtain the URL of the Internet community search results page corresponding to the search keyword, and associate the URL of the Internet community search results page with the search keyword.

[0062] The search keywords in the comments will be highlighted.

[0063] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0064] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0065] In this embodiment of the invention, user "likes" trigger the automatic identification of search keywords in comments. These search keywords are designated as "traffic-driving keywords," displaying themselves in a unique format compared to other characters. Clicking on a traffic-driving keyword redirects the user to a list of search results corresponding to that keyword, providing further opportunities for users to explore related content. Furthermore, adding the URL of the corresponding topic as a hyperlink to the search keywords in the comments enables them to drive traffic to that topic. This not only facilitates further exploration of related content by interested users, bringing user value and providing convenient access to expanded content for those who "like" the keyword, but also significantly increases the probability of niche topics effectively reaching genuinely interested users, thereby improving the efficiency of content dissemination on the community platform.

[0066] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0067] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0068] Figure 1 This is a flowchart illustrating a comment display method based on likes and comments in an internet community, according to an exemplary embodiment.

[0069] Figure 2 This is a screenshot of an interface for displaying comment text, according to an exemplary embodiment.

[0070] Figure 3 This is a screenshot of an interface showing another comment text display according to an exemplary embodiment.

[0071] Figure 4 This is a flowchart illustrating another method for displaying comments based on likes and comments in an internet community, according to an exemplary embodiment.

[0072] Figure 5 This is a screenshot of another interface displaying comment text, as illustrated in an exemplary embodiment.

[0073] Figure 6 This is a flowchart illustrating yet another method for displaying comments based on likes and comments in an internet community, according to an exemplary embodiment.

[0074] Figure 7 This is a block diagram illustrating yet another comment display device based on internet community comment likes, according to an exemplary embodiment.

[0075] Figure 8 This is a block diagram illustrating yet another comment display device based on internet community comment likes, according to an exemplary embodiment.

[0076] Figure 9 This is a block diagram illustrating yet another comment display device based on internet community comment likes, according to an exemplary embodiment. Detailed Implementation

[0077] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0078] Figure 1 This is a flowchart illustrating a comment display method based on likes and comments in an internet community, according to an exemplary embodiment.

[0079] like Figure 1 As shown, according to a first aspect of the present invention, a method for displaying comments based on likes and comments in an internet community is provided, the method comprising:

[0080] Step S101: When a user's "like" action is received for any comment in the Internet community, the comment is searched for keywords.

[0081] Step S102: When it is identified that the comment contains search keywords, determine whether the search keywords are in the blacklist of search traffic keywords;

[0082] If the search results contain "search keywords," check if the identified "search keywords" are in the latest "search keyword blacklist." If they are, it means that this "search keyword" is not suitable for driving traffic to community searches, and it should be discarded; if it is not in the blacklist, you can proceed to the next step.

[0083] Step S103: When the search keyword is not in the blacklist of search traffic terms, determine whether the number of posts in the search results of the Internet community corresponding to the search keyword is greater than or equal to a preset threshold.

[0084] If the judgment result indicates that the "search keyword" identified in the comments is not in the "search keyword blacklist," then the number of posts in the corresponding community search results is further checked to prevent a poor user experience due to too few posts in the corresponding community search results. For example, it is determined whether the number of posts in the community search results is greater than N (N=5). If the number of posts in the community search results is extremely small, it means that the search results for this keyword lack relevant content, and community search keyword traffic will not be used. If the judgment result indicates that the number of posts in the corresponding community search results meets the standard, it means that the community search results for this search keyword have some relevant content, and community search traffic can be further driven through comment keywords to expand the browsing of relevant content for genuinely interested users.

[0085] Step S104: When the number of posts is greater than or equal to a preset threshold, obtain the URL of the Internet community search results page corresponding to the search keyword, and associate the URL of the Internet community search results page with the search keyword.

[0086] If the recognition result shows that the number of hot posts for the corresponding topic meets the standard, the backend obtains the URL of the corresponding community search results page and uses it as a hyperlink for the search keywords in the comments.

[0087] Step S105: Highlight the search keywords in the comments.

[0088] Highlighting search keywords can be done by underlining, highlighting, bolding, boxing, separating them with special symbols, or using stylized artistic fonts, etc., to attract users' visual attention and increase the probability of users actively clicking on the keywords.

[0089] Specifically, when a user likes a comment, the backend is triggered to begin identifying "search keywords" within the comment. For example... Figure 2As shown, the comment reads, "It's a fireball, and very likely a meteorite," with a "like" button in the bottom right corner. When a user likes the comment, it changes to something like this. Figure 3 As shown, "meteorite" is specially marked on the front display, such as by adding an underline.

[0090] Figure 4 This is a flowchart illustrating another method for displaying comments based on likes and comments in an internet community, according to an exemplary embodiment.

[0091] like Figure 4 As shown, in one embodiment, preferably, the method further includes:

[0092] Step S401: Receive a selection or click command for the search keyword, and redirect the displayed content to the page corresponding to the URL of the Internet community search results page according to the selection or click command.

[0093] like Figure 5 As shown, when a user clicks on the search keyword "meteorite" in the comments, the page redirects to the search results page corresponding to the search keyword.

[0094] In one embodiment, preferably, the search keyword identification for the comments includes:

[0095] The search keywords in the comments are identified using a pre-trained search keyword extraction model.

[0096] Figure 6 This is a flowchart illustrating yet another method for displaying comments based on likes and comments in an internet community, according to an exemplary embodiment.

[0097] like Figure 6 As shown, in one embodiment, preferably, the method further includes:

[0098] Step S601: Select target topic names in the Internet community whose number of posts exceeds a preset number according to a preset time interval;

[0099] Compile a set of search keywords, selecting topic names from the community that have a certain number of posts in the past; this set of search keywords can be updated daily.

[0100] Step S602: Determine the set of search keywords based on the target topic name;

[0101] Step S603: Add the set of search keywords to the user-defined thesaurus for Chinese word segmentation;

[0102] The compiled set of search keywords is added to the user-defined thesaurus for Chinese word segmentation to ensure that the Chinese word segmentation results can segment all words in the set of search keywords into one word.

[0103] Step S604: Use the user-defined dictionary to perform Chinese word segmentation on target comments in the Internet community that meet the preset conditions to obtain Chinese word segmentation results;

[0104] In one embodiment, preferably, the preset conditions include:

[0105] The comment has a greater historical number of likes than the preset number of likes.

[0106] Of course, the preset conditions can also be other rules to select high-quality user comments, such as comments that exceed the preset word count, are clearly expressed, and contain a lot of information.

[0107] Step S605: Perform BIO annotation on each target comment based on the search keyword set and the Chinese word segmentation results to obtain annotated training data;

[0108] Each word in the Chinese word segmentation results is compared sequentially with the search keyword set. If it is in the search keyword set, it is marked as a keyword; otherwise, it is marked as a non-keyword. That is, if the word segmentation results match the topic words in the search keyword set, the search keyword is automatically marked using the BIO annotation method. For example, in the comment: "When it comes to the acting skills of villains, I only admire Gao Mingyuan in the TV series 'Sweeping Storm'", "Sweeping Storm" is a topic name with many popular posts discussing the plot. The corresponding BIO annotation would be: "OOOOOOOOOOOOOBIIIOOOO O", where "Sweeping Storm" is marked as a keyword. If the word segmentation results of the comment do not contain the search keyword 101, then each character is automatically marked as "O".

[0109] Step S606: Use the labeled training data and the BERT training model to perform deep learning training to obtain the search keyword extraction model.

[0110] In one embodiment, preferably, each target comment is BIO-labeled based on the search keyword set and the Chinese word segmentation results to obtain labeled training data, including:

[0111] Each word in the Chinese word segmentation result is compared sequentially with the words in the search keyword set;

[0112] When a word in the Chinese word segmentation result is the same as a word in the search keyword set, the word is marked as a keyword; otherwise, it is marked as a non-keyword.

[0113] In one embodiment, preferably, the method further includes:

[0114] Monitor and analyze the satisfaction level of search results for all search keywords according to a preset time period;

[0115] Specifically, search result satisfaction can include the click-through rate of the first search result, the click-through rate of the top three search results, and the average time users spend on search results.

[0116] Add search keywords whose search result satisfaction is lower than the preset satisfaction level to the search term blacklist.

[0117] For search terms with low satisfaction in community search results, such as those with a click-through rate below a certain threshold for the top three search results, add them to the "search term blacklist" to prevent these terms from causing a poor community search experience for users.

[0118] Figure 7 This is a block diagram illustrating yet another comment display device based on internet community comment likes, according to an exemplary embodiment.

[0119] like Figure 7 As shown, according to a second aspect of the present invention, a comment display device based on internet community comments and likes is provided, the device comprising:

[0120] The identification module 71 is used to identify search keywords in a comment when it receives a user's "like" action on any comment in an internet community.

[0121] The first determining module 72 is used to determine whether the search keyword is in the search traffic blacklist when the comment is identified to contain search keywords;

[0122] The second determining module 73 is used to determine whether the number of posts in the search results of the Internet community corresponding to the search keyword is greater than or equal to a preset threshold when the search keyword is not in the blacklist of search traffic terms.

[0123] The association module 74 is used to obtain the URL of the Internet community search results page corresponding to the search keyword when the number of posts is greater than or equal to a preset threshold, and to associate the URL of the Internet community search results page with the search keyword.

[0124] Display module 75 is used to highlight the search keywords in the comments.

[0125] Figure 8 This is a block diagram illustrating yet another comment display device based on internet community comment likes, according to an exemplary embodiment.

[0126] like Figure 8 As shown, in one embodiment, preferably, the device further includes:

[0127] The jump module 81 is used to receive a selection or click command for the search keyword, and according to the selection or click command, the displayed content is jumped to the page corresponding to the URL of the Internet community search results page.

[0128] In one embodiment, preferably, the identification module is used for:

[0129] The search keywords in the comments are identified using a pre-trained search keyword extraction model.

[0130] Figure 9 This is a block diagram illustrating yet another comment display device based on internet community comment likes, according to an exemplary embodiment.

[0131] like Figure 9 As shown, in one embodiment, preferably, the device further includes:

[0132] Module 91 is used to select target topic names in the Internet community where the number of posts exceeds a preset number at preset time intervals.

[0133] The third determining module 92 is used to determine a set of search keywords based on the target topic name;

[0134] Add module 93 to add the set of search keywords to the user-defined thesaurus for Chinese word segmentation;

[0135] The word segmentation module 94 is used to perform Chinese word segmentation on target comments in the Internet community that meet preset conditions using the user-defined dictionary, and obtain Chinese word segmentation results.

[0136] The annotation module 95 is used to perform BIO annotation on each target comment based on the set of search keywords and the Chinese word segmentation results to obtain annotated training data.

[0137] Training module 96 is used to perform deep learning training using the labeled training data and the BERT training model to obtain the search keyword extraction model.

[0138] In one embodiment, preferably, the preset conditions include:

[0139] The comment has a greater historical number of likes than the preset number of likes.

[0140] In one embodiment, preferably, the annotation module is used for:

[0141] Each word in the Chinese word segmentation result is compared sequentially with the words in the search keyword set;

[0142] When a word in the Chinese word segmentation result is the same as a word in the search keyword set, the word is marked as a keyword; otherwise, it is marked as a non-keyword.

[0143] In one embodiment, preferably, the device further includes:

[0144] The statistics module is used to monitor and analyze the satisfaction level of search results for all search keywords according to a preset time period.

[0145] The processing module is used to add search keywords whose search result satisfaction is lower than the preset satisfaction level to the search traffic keyword blacklist.

[0146] According to a third aspect of the present invention, a comment display device based on internet community comments and likes is provided, the device comprising:

[0147] processor;

[0148] Memory used to store processor-executable instructions;

[0149] The processor is configured as follows:

[0150] When a user likes any comment in an online community, the system identifies search keywords for that comment.

[0151] When a search keyword is identified in the comment, it is determined whether the search keyword is in the blacklist of search terms.

[0152] When the search keyword is not in the blacklist of search traffic terms, determine whether the number of posts in the search results of the Internet community corresponding to the search keyword is greater than or equal to a preset threshold.

[0153] When the number of posts is greater than or equal to a preset threshold, obtain the URL of the Internet community search results page corresponding to the search keyword, and associate the URL of the Internet community search results page with the search keyword.

[0154] The search keywords in the comments will be highlighted.

[0155] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0156] Furthermore, it can be understood that in this invention, "multiple" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. The singular forms "a," "the," and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0157] It is further understood that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this invention, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0158] It is further understood that although the operations are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all the operations shown to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0159] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0160] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for displaying comments based on likes and comments in an internet community, characterized in that, The method includes: When a user likes any comment in an online community, the system identifies search keywords for that comment. When a search keyword is identified in the comment, it is determined whether the search keyword is in the blacklist of search terms used for attracting traffic. When the search keyword is not in the blacklist of search traffic terms, determine whether the number of posts in the search results of the Internet community corresponding to the search keyword is greater than or equal to a preset threshold. When the number of posts is greater than or equal to a preset threshold, obtain the URL of the Internet community search results page corresponding to the search keyword, and associate the URL of the Internet community search results page with the search keyword. Highlight the search keywords in the comments; The process of identifying search keywords for the comments includes: The search keywords in the comments are identified using a pre-trained search keyword extraction model. Also includes: Select target topic names in the internet community whose number of posts exceeds a preset number at preset time intervals; Determine the set of search keywords based on the target topic name; Add the aforementioned set of search keywords to the user-defined thesaurus for Chinese word segmentation; The user-defined dictionary is used to perform Chinese word segmentation on target comments in the Internet community that meet preset conditions, and the Chinese word segmentation results are obtained. Based on the set of search keywords and the Chinese word segmentation results, each target comment is labeled using BIO to obtain labeled training data; The search keyword extraction model is obtained by using the labeled training data and the BERT training model for deep learning training.

2. The method according to claim 1, characterized in that, The method further includes: The system receives a command to select or click the search keyword, and redirects the displayed content to the page corresponding to the URL of the Internet community search results page based on the selected or clicked command.

3. The method according to claim 1, characterized in that, The preset conditions include: The comment has a greater historical number of likes than the preset number of likes.

4. The method according to claim 1, characterized in that, Based on the search keyword set and the Chinese word segmentation results, each target comment is BIO-labeled to obtain labeled training data, including: Each word in the Chinese word segmentation result is compared sequentially with the words in the search keyword set; When a word in the Chinese word segmentation result is the same as a word in the search keyword set, the word is marked as a keyword; otherwise, it is marked as a non-keyword.

5. The method according to claim 1, characterized in that, The method further includes: Monitor and analyze the satisfaction level of search results for all search keywords according to a preset time period; Add search keywords whose search result satisfaction is lower than the preset satisfaction level to the search term blacklist.

6. A comment display device based on internet community comments and likes, characterized in that, The device includes: The identification module is used to identify search keywords in a comment when it receives a user's "like" action on any comment in an internet community. The first determining module is used to determine whether the search keywords are in the blacklist of search terms when the comments are found to contain search keywords; The second determining module is used to determine whether the number of posts in the search results of the Internet community corresponding to the search keyword is greater than or equal to a preset threshold when the search keyword is not in the blacklist of search traffic terms. The association module is used to obtain the URL of the Internet community search results page corresponding to the search keyword when the number of posts is greater than or equal to a preset threshold, and to associate the URL of the Internet community search results page with the search keyword. The display module is used to highlight the search keywords in the comments; The process of identifying search keywords for the comments includes: The search keywords in the comments are identified using a pre-trained search keyword extraction model. Also includes: Select target topic names in the internet community whose number of posts exceeds a preset number at preset time intervals; Determine the set of search keywords based on the target topic name; Add the aforementioned set of search keywords to the user-defined thesaurus for Chinese word segmentation; The user-defined dictionary is used to perform Chinese word segmentation on target comments in the Internet community that meet preset conditions, and the Chinese word segmentation results are obtained. Based on the set of search keywords and the Chinese word segmentation results, each target comment is labeled using BIO to obtain labeled training data; The search keyword extraction model is obtained by using the labeled training data and the BERT training model for deep learning training.

7. A comment display device based on internet community comments and likes, characterized in that, The device includes: processor; Memory used to store processor-executable instructions; The processor is configured as follows: When a user likes any comment in an online community, the system identifies search keywords for that comment. When a search keyword is identified in the comment, it is determined whether the search keyword is in the blacklist of search terms used for attracting traffic. When the search keyword is not in the blacklist of search traffic terms, determine whether the number of posts in the search results of the Internet community corresponding to the search keyword is greater than or equal to a preset threshold. When the number of posts is greater than or equal to a preset threshold, obtain the URL of the Internet community search results page corresponding to the search keyword, and associate the URL of the Internet community search results page with the search keyword. Highlighting the search keywords in the comments; wherein, identifying the search keywords in the comments includes: The search keywords in the comments are identified using a pre-trained search keyword extraction model. Also includes: Select target topic names in the internet community whose number of posts exceeds a preset number at preset time intervals; Determine the set of search keywords based on the target topic name; Add the aforementioned set of search keywords to the user-defined thesaurus for Chinese word segmentation; The user-defined dictionary is used to perform Chinese word segmentation on target comments in the Internet community that meet preset conditions, and the Chinese word segmentation results are obtained. Based on the set of search keywords and the Chinese word segmentation results, each target comment is labeled using BIO to obtain labeled training data; The search keyword extraction model is obtained by using the labeled training data and the BERT training model for deep learning training.

8. A computer-readable storage medium storing computer instructions thereon, characterized in that, When executed by the processor, this instruction implements the steps of the method described in any one of claims 1-5.

Images