Commenting method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a comment method and device, electronic equipment and a storage medium. In response to a comment operation on first target published content, a comment input interface is displayed. Comment information input by a user in the comment input interface is received. The comment information is subjected to sensitive word detection. If there is a first sensitive word in the comment information, the first sensitive word is subjected to code processing to obtain first target comment information. User attributes of the comment information are obtained. A first user score is obtained according to the first sensitive word and the user attributes. A first display order of the first target comment information is determined according to the first target comment information and the first user score. The first target comment information is displayed in a comment display interface according to the first display order. Thus, the sorting effect of the comment can be improved.

Description

Technical Field

[0001] This application relates to the field of computers, and more specifically to a commenting method, apparatus, electronic device, and storage medium. Background Technology

[0002] In recent years, in order to improve the knowledge reserves of employees and meet the needs of training new employees and daily work, companies generally build knowledge sharing platforms to enable employees to share and exchange knowledge.

[0003] However, existing knowledge-sharing platforms currently only sort comments based on the time they were published, resulting in poor sorting performance. Summary of the Invention

[0004] This application provides a commenting method, apparatus, electronic device, and storage medium that can improve the sorting effect of comments.

[0005] In a first aspect, embodiments of this application provide a commenting method, including:

[0006] In response to a comment action on the content posted by the first target, display the comment input interface;

[0007] Receive comment information entered by users in the comment input interface;

[0008] Perform sensitive word detection on comment information;

[0009] If the comment contains a first sensitive word, then the first sensitive word is censored to obtain the first target comment information;

[0010] The user attributes for obtaining comment information include the user's job information and historical comment information;

[0011] The first user rating is obtained based on the most sensitive keywords and user attributes.

[0012] The first display order of the first target comment information is determined based on the first target comment information and the first user rating;

[0013] Based on the first display order, the first target comment information is displayed in the comment display interface.

[0014] In some embodiments, after detecting sensitive words in the comment information, the method further includes:

[0015] If the comment contains a second sensitive word, the comment will be sent to the manual review terminal for manual review.

[0016] Receive the review results sent by the manual review terminal;

[0017] If the review is successful, the second sensitive word will be censored to obtain the second target comment information;

[0018] The user attributes for obtaining comment information include the user's name, job title, and historical comment information.

[0019] A second user rating is obtained based on the second sensitive keyword and user attributes;

[0020] The second display order of the second target comment information is determined based on the second target comment information and the second user rating.

[0021] According to the second display order, the second target comment information is displayed in the comment display interface.

[0022] In some embodiments, after detecting sensitive words in the comment information, the method further includes:

[0023] If a comment contains sensitive words, the comment will be blocked.

[0024] In some embodiments, after detecting sensitive words in the comment information, the method further includes:

[0025] If the comment does not contain any sensitive words, the comment will be displayed in the comment display interface.

[0026] In some embodiments, a first user score is obtained based on a first sensitive word and user attributes, including:

[0027] Perform keyword retrieval on the content published by the primary target to determine the knowledge point tags of the content published by the primary target.

[0028] Based on knowledge point tags and job information, determine the degree of matching between the user and the content published for the primary target;

[0029] Based on historical comments, obtain information on historical sensitive words;

[0030] Determine the occurrence rate of sensitive words based on historical sensitive word information and the first sensitive word;

[0031] The first user score is determined based on the degree of matching and the occurrence rate of sensitive words.

[0032] In some embodiments, after displaying the first target comment information in the comment display interface according to the first display order, the method further includes:

[0033] The first target comment information is processed by second keyword retrieval to obtain at least one knowledge keyword tag in the first target comment information;

[0034] Based on at least one knowledge keyword tag, select the second target published content from the pre-stored database, wherein the second target published content contains all the knowledge keyword tags in the first target comment information;

[0035] Obtain the second address information of the content published by the second target, and display the second address information of the content published by the second target in the comment content of the first target.

[0036] In some embodiments, after determining the second target content to be published in a pre-stored database based on at least one knowledge keyword tag, the method further includes:

[0037] Obtain the first address information of the content published by the first target, and display the first target's comment information and first address information in the comment display interface of the content published by the second target.

[0038] Secondly, embodiments of this application also provide a commenting device, including:

[0039] The first response unit is used to respond to comment operations on the content published by the first target and display the comment input interface;

[0040] The receiving unit is used to receive comment information at the comment input interface;

[0041] The detection unit is used to detect sensitive words in the comment information;

[0042] The censoring unit is used to censor the first sensitive word if it exists in the comment information, so as to obtain the first target comment information;

[0043] The acquisition unit is used to acquire user attributes of comment information, including the user's name, job information, and historical comment information;

[0044] The unit is used to obtain the first user rating based on the first sensitive word and user attributes;

[0045] The display unit is used to determine the first display order of the first target comment information based on the first target comment information and the first user rating;

[0046] The second response unit is used to display the first target comment information in the comment display interface according to the first display order.

[0047] Thirdly, embodiments of this application also provide an electronic device, including a memory storing a plurality of instructions; a processor loading instructions from the memory to execute the steps in any of the comment methods provided in embodiments of this application.

[0048] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to perform steps in any of the comment methods provided in embodiments of this application.

[0049] In this application, sensitive words in comments can be detected. Based on the detection results and the user attributes of the user who posted the comment, the display order of the comment can be determined, thus enabling a better assessment of the quality of each comment. This results in a better comment ranking. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1a This is a schematic diagram illustrating a scenario of the comment method provided in an embodiment of this application;

[0052] Figure 1b This is a flowchart illustrating the commenting method provided in an embodiment of this application;

[0053] Figure 1c This is a flowchart illustrating the method for obtaining a first user rating provided in an embodiment of this application;

[0054] Figure 2 This is a schematic diagram illustrating the application of the comment method provided in this application embodiment in a server scenario;

[0055] Figure 3 This is a schematic diagram of the first structure of the comment device provided in the embodiments of this application;

[0056] Figure 4 This is a schematic diagram of the terminal structure provided in the embodiments of this application. Detailed Implementation

[0057] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0058] This application provides a commenting method, apparatus, electronic device, and storage medium.

[0059] Specifically, the commenting device can be integrated into an electronic device, such as a terminal or server. The terminal can be a mobile phone, tablet, smart Bluetooth device, laptop, or personal computer (PC); the server can be a single server or a server cluster consisting of multiple servers.

[0060] In some embodiments, the commenting device may also be integrated into multiple electronic devices, such as multiple servers, with multiple servers implementing the commenting method of this application.

[0061] In some embodiments, the server may also be implemented as a terminal.

[0062] For example, refer to Figure 1a The electronic device can be a server. In this embodiment, the server is used to respond to a comment operation on the first target published content by displaying a comment input interface; receiving comment information entered by the user in the comment input interface; performing sensitive word detection on the comment information; if a first sensitive word exists in the comment information, then the first sensitive word is masked to obtain the first target comment information; obtaining the user attributes of the comment information, wherein the user attributes include the user's job information and historical comment information; obtaining a first user rating based on the first sensitive word and the user attributes; determining a first display order of the first target comment information based on the first target comment information and the first user rating; and displaying the first target comment information in the comment display interface according to the first display order.

[0063] The following sections provide detailed descriptions of each example. It should be noted that the sequence numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0064] In this embodiment, a commenting method is provided, such as... Figure 1b As shown, this commenting method is applied to the first terminal, and the specific process of this commenting method can be as follows:

[0065] 110. In response to a comment action on the content posted by the first target, display the comment input interface.

[0066] The published content can refer to questions, articles, or other content posted by users on a knowledge-sharing platform. For example, in some embodiments, the published content can be questions posted by users on a knowledge-sharing platform when they encounter problems at work, or knowledge and experience shared by users on a knowledge-sharing platform. For example, a user may publish an article titled "The Past and Present of a Repayment Schedule" on a knowledge-sharing platform.

[0067] A knowledge-sharing platform can be an environment or system that allows individual or organizational knowledge to be shared with other members within or beyond an organization through various communication methods; it is a subsystem of a knowledge management system. In some embodiments, a knowledge-sharing platform can be software installed on an electronic device or a website.

[0068] For example, in this embodiment of the application, when the knowledge sharing platform is an app (application) installed on a mobile phone, and the user needs to publish an article "The Past and Present of a Repayment Schedule", the user can log in to the knowledge sharing platform and then enter the article "The Past and Present of a Repayment Schedule" on the publishing interface used to publish articles or ask questions on the knowledge sharing platform, thereby realizing the operation of publishing content on the knowledge sharing platform.

[0069] The target published content can refer to the content that a user selects from multiple published content based on their search needs. For example, in some embodiments, a user needs to understand the knowledge content of a repayment schedule. After logging into a knowledge-sharing platform, the user finds the article "The Past and Present of Repayment Schedules" among the multiple published content on the platform; this article is the target published content. For example, in the embodiments of this application, users can quickly find the target published content through fuzzy search.

[0070] The commenting function allows users to send comment signals to the knowledge-sharing platform when they need to answer questions, ask questions, or share their experiences based on the content posted by the target. This enables users to comment on the content posted by the target.

[0071] For example, in some embodiments, the interface displaying the target published content may include a "comment" button, which allows users to enter a comment input interface and leave a comment by clicking the "comment" button.

[0072] A comment input interface can be used by users to enter comment content. For example, in some embodiments, the comment input interface may include a comment input box where users can enter comments.

[0073] 120. Receive comment information entered by users in the comment input interface.

[0074] Comment information refers to the content entered by the user in the comment input interface. For example, in some embodiments, when a user finishes browsing the article "The Past and Present of Repayment Schedule" in the app of the knowledge sharing platform, they can click the "Comment" button on the interface displaying the article to enter the comment input interface. In the comment input box of the comment input interface, they can enter their views or questions about the article and then click "Publish". The published content can be sent to the server of the knowledge sharing platform.

[0075] Receiving comment information can refer to the knowledge-sharing platform's server receiving comment information sent by users on the platform's app via a wireless gateway.

[0076] In some embodiments, the server of the knowledge-sharing platform can receive the content of the comment information in real time. That is, the server can receive the user's input of a single word or a paragraph, or it can receive all the content of the comment information after the user has finished entering it.

[0077] 130. Perform sensitive word detection on comment information.

[0078] Sensitive words can refer to words or uncivilized language in comments that contain sensitive political leanings, violent tendencies, unhealthy connotations, or other inappropriate language. They can also be special sensitive words set according to the platform's own specific circumstances. For example, in some implementations, content involving intellectual property infringement can be set as special sensitive words.

[0079] Sensitive word detection can refer to a method for detecting sensitive words in comment information. In some embodiments, the sensitive word detection method may include: determining the text information in the comment information, comparing the text information in the comment information with sensitive words pre-stored in a preset database, and indicating that there are sensitive words in the comment information when there are text or fields in the comment information that match the sensitive words pre-stored in the preset database, and indicating that there are no sensitive words in the comment information when there are no text or fields in the comment information that match the sensitive words pre-stored in the preset database.

[0080] In some embodiments, the text information in the comment is compared with sensitive words pre-stored in a preset database. Besides comparing the text itself, the first letter of the sensitive words or the spaces between them can also be compared. For example, the sensitive words pre-stored in the preset database could be "X_Y". During the comparison, if "XZY" is present in the comment, it is determined that the comment contains a sensitive word.

[0081] 140. If the comment contains a first sensitive word, then the first sensitive word is censored to obtain the first target comment information.

[0082] In this context, "masking" can refer to blurring or obscuring, which involves masking the target content using mosaic or other special characters. When the target content is an image, mosaicking can be used, where mosaicking involves degrading the color gradation details of a specific area and creating a scrambled color block effect. When the target content is text, it can be masked by replacing the target content with other special characters.

[0083] For example, in some embodiments, when the comment information is "The Past and Present of the Repayment Schedule" and the sensitive word is "schedule", after detecting that the sensitive word "schedule" exists in "The Past and Present of the Repayment Schedule", the word "schedule" is masked. After masking, the target comment information can be "The Past and Present of Repayment XXX".

[0084] 150. Obtain user attributes for comment information, including the user's job information and historical comment information.

[0085] User attributes refer to information related to users, which may include user job information and historical comment information.

[0086] The job information can be the user's job position within a company; for example, in some embodiments, the user's job information could be "department AA, department BB". The job information can also be the user's job information on a knowledge-sharing platform; for example, in some embodiments, the user's job information can be used to characterize the user's activity level or ability to answer questions in a target domain.

[0087] Historical comment information can be the historical comment information of users who have commented or posted content on knowledge-sharing platforms.

[0088] In some embodiments, a user's job information and historical comment information may be stored in the user's account file. The method for obtaining user attributes of comment information may include searching for the user file of comment information in the knowledge sharing platform's storage by determining the ID (IdentityDocument) of the comment information, and retrieving the user's job information and historical comment information from the user file.

[0089] 160. Based on the first sensitive word and user attributes, obtain the first user rating.

[0090] The first user rating is used to represent a user's historical performance when making comments. A higher first user rating indicates better historical performance when making comments, and a lower first user rating indicates worse historical performance when making comments.

[0091] In the embodiments of this application, such as Figure 1c As shown, the methods for obtaining the first user rating based on the first sensitive word and user attributes include:

[0092] 161. Perform keyword retrieval on the content published for the first target to determine the knowledge point tags of the content published for the first target.

[0093] Keyword retrieval processing can refer to traversing the text within the target published content to extract knowledge point feature words and record these feature words as knowledge point tags. For example, in some embodiments, the knowledge points involved in the target published content can be determined through a pre-stored knowledge database; alternatively, the knowledge points involved in the target published content can be determined by comparing the pre-stored knowledge database with the publisher's knowledge point annotations.

[0094] For example, in some embodiments, when the target published content includes "accrued interest," the target published content is compared with a pre-stored knowledge database to determine if the knowledge point includes interest accrual, thereby obtaining the knowledge point tag "accrued interest" for the target published content. The pre-stored knowledge database can be a third-party knowledge database.

[0095] 162. Based on knowledge point tags and job information, determine the degree of matching between the user and the content published by the primary target.

[0096] Among them, job information is used to characterize the user's job function in the company. By identifying the user's job function, the user's work content and the knowledge points involved can be determined. Thus, by combining knowledge point tags and job information, the degree of match between the commenting user and the content posted by the primary target can be determined.

[0097] Specifically, a pre-stored association table can be used to determine the connection between a user's job function and knowledge points. For example, if the knowledge point tag for the content published by the first target is "the occurrence and settlement of claims and debts," and the user's job information is "accountant," then the user's matching degree with the content published by the first target is high; if the knowledge point tag for the content published by the first target is "the occurrence and settlement of claims and debts," and the user's job information is "product manager," then the matching degree with the content published by the first target is low.

[0098] 163. Obtain information on sensitive words in historical comments.

[0099] Among them, the information on sensitive words in history can refer to which information in a user's historical comments contained the first sensitive word.

[0100] 164. Determine the occurrence rate of sensitive words based on historical sensitive word information and the first sensitive word.

[0101] The sensitive word occurrence rate refers to the ratio of comments containing the first sensitive word to all comments. For example, in some embodiments, when there are 10 comments and 3 comments contain the sensitive word, the sensitive word occurrence rate is 30%.

[0102] 165. The first user score is obtained based on the matching degree and the occurrence rate of sensitive words.

[0103] User ratings are used to represent the priority of user reviews in the ranking process. For example, if the first user has a high rating, then the user review has a high priority in the ranking process.

[0104] In this application embodiment, user scores can be obtained based on the matching degree and the occurrence rate of sensitive words. For example, in some embodiments, when the matching degree is high and the occurrence rate of sensitive words is low, the first user score is high; when the matching degree is low and the occurrence rate of sensitive words is low, the first user score is relatively high; when the matching degree is high and the occurrence rate of sensitive words is high, the first user score is medium; when the matching degree is low and the occurrence rate of sensitive words is low, the first user score is relatively low; and when the matching degree is low and the occurrence rate of sensitive words is high, the first user score is low.

[0105] In this embodiment of the application, a first user score can also be obtained based on the weight of the matching degree and the occurrence rate of sensitive words. For example, in some embodiments, the user score can be obtained by "matching degree * first weight + occurrence rate of sensitive words * second weight", where the matching degree of high, medium and low can represent scores of 1, 0.5 and 0 respectively, the first weight can be 0.6 and the second weight can be 0.4.

[0106] 170. Determine the first display order of the first target comment information based on the first target comment information and the first user rating.

[0107] The first display order can refer to the order in which comment information containing sensitive words is displayed. In some embodiments, comment information containing sensitive words and comment information not containing sensitive words can be sorted, wherein comment information not containing sensitive words can be displayed first. The first display order of comment information containing sensitive words can be determined based on a first user rating.

[0108] The higher the first user rating, the higher the ranking of the first target review information. In this embodiment, when there are three original target reviews, where the first original target review has a user rating of 0.8, the second original target review has a user rating of 0.76, the third original target review has a user rating of 0.6, and the first target review has a first user rating of 0.79, then the first display order of the first target review information is between the first and second original target reviews.

[0109] 180. Based on the first display order, display the first target comment information in the comment display interface.

[0110] The comment display interface can be an interface used to display comments. Displaying the first target comment information in the comment display interface, according to the first display order, can mean displaying the first target comment information at a target location within the comment display interface, where the target location can be determined based on the first display order.

[0111] In this embodiment of the application, after detecting sensitive words in the comment information, the commenting method may further include:

[0112] If the comment contains a second sensitive word, the comment will be sent to the manual review terminal for manual review.

[0113] Receive the review results sent by the manual review terminal;

[0114] If the review is successful, the second sensitive word will be censored to obtain the second target comment information;

[0115] The user attributes for obtaining comment information include user, job information, and historical comment information;

[0116] A second user rating is obtained based on the second sensitive keyword and user attributes;

[0117] The second display order of the second target comment information is determined based on the second target comment information and the second user rating.

[0118] According to the second display order, the second target comment information is displayed in the comment display interface.

[0119] The second sensitive word can be a sensitive word with a higher sensitivity than the first sensitive word. The sensitivity of the sensitive word can be set manually. For example, in some embodiments, the first sensitive word can be a word with violent tendencies, unhealthy connotations, or uncivilized language, and the second sensitive word can be a word with violent tendencies or uncivilized language.

[0120] The manual review terminal refers to a mobile phone or computer equipped with approval software. Reviewers use the approval software to examine the second sensitive word. If the second sensitive word is ambiguous, for example, a sensitive word caused by punctuation issues, it can be censored to obtain the second target comment information.

[0121] The second user rating can be obtained from the second target comment information and user attributes. The second user rating can be used to determine the second display order, that is, to sort the second target comment information containing the second sensitive words.

[0122] In this embodiment, when sorting comment information, if the comment information does not contain any sensitive words, it is displayed first. If the comment information contains a first sensitive word, it is displayed after the comment information without sensitive words. If the comment information contains a second sensitive word, it is displayed after the comment information without sensitive words. When both a first and second sensitive word are present in the comment information, both words can be censored, and the order can be based on the second sensitive word and user attributes.

[0123] In this embodiment of the application, after detecting sensitive words in the comment information, the comment method further includes:

[0124] If a comment contains sensitive words, the comment will be blocked.

[0125] Among them, the third sensitive word can be a sensitive word with a higher sensitivity than the first and second sensitive words. The sensitivity of the sensitive words can be set manually. For example, in some embodiments, the first sensitive word can be a word with violent tendencies or uncivilized language, the second sensitive word can be a word with unhealthy connotations or uncivilized language, and the third sensitive word can be a word with violent tendencies or uncivilized language.

[0126] Blocking can mean not displaying comments and disabling the comment function for that user.

[0127] In this embodiment of the application, after detecting sensitive words in the comment information, the method further includes:

[0128] If the comment information does not contain any sensitive words, the comment information will be displayed on the comment display interface. In this embodiment, after displaying the first target comment information on the comment display interface according to the first display order, the commenting method further includes:

[0129] The first target comment information is processed by second keyword retrieval to obtain at least one knowledge keyword tag in the first target comment information;

[0130] Based on at least one knowledge keyword tag, select the second target published content from the pre-stored database, wherein the second target published content contains all the knowledge keyword tags in the first target comment information;

[0131] Obtain the second address information of the content published by the second target, and display the second address information of the content published by the second target in the comment content of the first target.

[0132] The second keyword retrieval process refers to searching for knowledge point keywords in the first target comment information to obtain knowledge keyword tags. For example, in some embodiments, when the first target comment information is "debt refers to the obligation of a debtor to perform or refrain from performing certain acts in accordance with the law to a creditor in a debt legal relationship," the knowledge keyword tag for the first target comment information can be "debt" through a pre-stored knowledge point database and field matching. The pre-stored knowledge point database can be an encyclopedia database.

[0133] The second address information can be a link address. When a user clicks the link address, they can enter the interface of the content published by the second target.

[0134] Displaying the second address information of the second target's published content within the first target's comment content can mean displaying the second address information together with the first target's comment content in the comment display interface.

[0135] In this embodiment of the application, after determining the second target publication content in a pre-stored database based on at least one knowledge keyword tag, the method further includes:

[0136] Obtain the first address information of the content published by the first target, and display the first target's comment information and first address information in the comment display interface of the content published by the second target.

[0137] The first address information can be a link address. When a user clicks the link address, they can enter the interface of the content published by the first target.

[0138] The method provided in this application embodiment can respond to a comment operation on a first target published content by displaying a comment input interface; receiving comment information entered by the user in the comment input interface; performing sensitive word detection on the comment information; if a first sensitive word exists in the comment information, the first sensitive word is masked to obtain the first target comment information; obtaining the user attributes of the comment information, wherein the user attributes include the user's job information and historical comment information; obtaining a first user rating based on the first sensitive word and the user attributes; determining a first display order of the first target comment information based on the first target comment information and the first user rating; and displaying the first target comment information in the comment display interface according to the first display order. As can be seen from the above, this application embodiment, by detecting sensitive words in the comments and determining the display order of the user's comments based on the detection results and the user attributes of the user who posted the comment, can better determine the quality of each comment. Therefore, the comment ranking results are better.

[0139] The method described in the above embodiments will be further described in detail below.

[0140] like Figure 2 As shown, the specific process of one commenting method is as follows:

[0141] 201. In response to comments on published content, display the comment input interface;

[0142] 202. Receive comment information entered by users on the comment input interface;

[0143] 203. Perform sensitive word detection on comment information;

[0144] 204. If there are no sensitive words in the comment information, the comment information will be displayed in the comment display interface according to the preset priority display rules;

[0145] 205. If the comment information contains first-level sensitive words, the first-level sensitive words will be blocked to obtain the first target comment information, and the first target comment information will be displayed in the comment display interface according to the preset priority display rules;

[0146] 206. If the comment contains second-level sensitive words, the comment will be sent to the manual review terminal for manual review. If the review is successful, the second sensitive words will be censored to obtain the second target comment information, which will be displayed in the comment display interface according to the preset priority display rules.

[0147] The preset priority display rule can mean that when sorting and displaying comment information, the display priority of comment information without sensitive words is higher than that of comment information with first-level sensitive words, which is higher than that of comment information with second-level sensitive words.

[0148] 207. If the comment contains Level 3 sensitive words, then the Level 3 sensitive words will be blocked.

[0149] To better implement the above methods, embodiments of this application also provide an image processing apparatus, such as... Figure 3 As shown, the commenting device may include:

[0150] The first response unit 301 is used to display a comment input interface in response to a comment operation on the content published by the first target;

[0151] The receiving unit 302 is used to receive comment information entered by the user on the comment input interface;

[0152] Detection unit 303 is used to detect sensitive words in comment information;

[0153] The censoring processing unit 304 is used to censor the first sensitive word if the comment information contains the first sensitive word, so as to obtain the first target comment information;

[0154] The acquisition unit 305 is used to acquire user attributes of the comment information, wherein the user attributes include the user's job information and historical comment information;

[0155] Unit 306 is obtained, which is used to obtain the first user rating based on the first sensitive word and user attributes;

[0156] Display unit 307 is used to determine the first display order of the first target comment information based on the first target comment information and the first user rating;

[0157] The second response unit 308 is used to display the first target comment information in the comment display interface according to the first display order.

[0158] In some embodiments of this application, the coding processing unit 304 is further configured to:

[0159] If the comment contains a second sensitive word, the comment will be sent to the manual review terminal for manual review.

[0160] Receive the review results sent by the manual review terminal;

[0161] If the review is successful, the second sensitive word will be censored to obtain the second target comment information;

[0162] The user attributes for obtaining comment information include the user's job information and historical comment information;

[0163] A second user rating is obtained based on the second sensitive keyword and user attributes;

[0164] The second display order of the second target comment information is determined based on the second target comment information and the second user rating.

[0165] According to the second display order, the second target comment information is displayed in the comment display interface.

[0166] In some embodiments of this application, the coding processing unit 304 is further configured to:

[0167] If a comment contains sensitive words, the comment will be blocked.

[0168] In some embodiments of this application, the coding processing unit 304 is further configured to:

[0169] If the comment does not contain any sensitive words, the comment will be displayed in the comment display interface.

[0170] In some embodiments of this application, the obtaining unit 306 is further used for:

[0171] Perform keyword retrieval on the content published by the primary target to determine the knowledge point tags of the content published by the primary target.

[0172] Based on knowledge point tags and job information, determine the degree of matching between the user and the content published for the primary target;

[0173] Based on historical comments, obtain information on historical sensitive words;

[0174] Determine the occurrence rate of sensitive words based on historical sensitive word information and the first sensitive word;

[0175] The first user score is determined based on the degree of matching and the occurrence rate of sensitive words.

[0176] In some embodiments of this application, the second response unit 308 is further configured to:

[0177] The first target comment information is processed by second keyword retrieval to obtain at least one knowledge keyword tag in the first target comment information;

[0178] Based on at least one knowledge keyword tag, select the second target published content from the pre-stored database, wherein the second target published content contains all the knowledge keyword tags in the first target comment information;

[0179] Obtain the second address information of the content published by the second target, and display the second address information of the content published by the second target in the comment content of the first target.

[0180] In some embodiments of this application, the second response unit 308 is further configured to:

[0181] After determining the second target content to be published in a pre-stored database based on at least one knowledge keyword tag, the method further includes:

[0182] Obtain the first address information of the content published by the first target, and display the first target's comment information and first address information in the comment display interface of the content published by the second target.

[0183] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0184] As described above, the comment device in this embodiment comprises a first response unit 301, used to display a comment input interface in response to a comment operation on a first target published content; a receiving unit 302, used to receive comment information input by the user on the comment input interface; a detection unit 303, used to detect sensitive words in the comment information; a masking processing unit 304, used to mask the first sensitive word if it exists in the comment information, to obtain the first target comment information; an acquisition unit 305, used to acquire user attributes of the comment information, wherein the user attributes include the user's job information and historical comment information; an obtaining unit 306, used to obtain a first user rating based on the first sensitive word and user attributes; a display unit 307, used to determine a first display order of the first target comment information based on the first target comment information and the first user rating; and a second response unit 308, used to display the first target comment information in the comment display interface according to the first display order. This embodiment can better determine the quality of each comment by detecting sensitive words in the comments and determining the display order of the user's comments based on the detection results and the user attributes of the user who posted the comment. This results in a better sorting of comments.

[0185] This application also provides an electronic device, which can be a terminal, a server, or other similar device. The terminal can be a mobile phone, tablet computer, smart Bluetooth device, laptop computer, personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers, etc.

[0186] In some embodiments, the commenting device may also be integrated into multiple electronic devices, such as multiple servers, with multiple servers implementing the commenting method of this application.

[0187] In this embodiment, the electronic device will be described in detail as a terminal, for example, such as... Figure 4 As shown, it illustrates the structural diagram of the terminal involved in the embodiments of this application, specifically:

[0188] The terminal may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, an input module 404, and a communication module 405. Those skilled in the art will understand that... Figure 4 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0189] The processor 401 is the control center of the terminal, connecting various parts of the terminal via various interfaces and lines. It executes various functions and processes data by running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402. In some embodiments, the processor 401 may include one or more processing cores; in some embodiments, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 401.

[0190] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0191] The terminal also includes a power supply 403 that supplies power to the various components. In some embodiments, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0192] The terminal may also include an input module 404, which can be used to receive input numeric or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0193] The terminal may also include a communication module 405. In some embodiments, the communication module 405 may include a wireless module, through which the terminal can perform short-range wireless transmission, thereby providing users with wireless broadband internet access. For example, the communication module 405 can be used to help users send and receive emails, browse web pages, and access streaming media.

[0194] Although not shown, the terminal may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the terminal loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, as follows:

[0195] In response to a comment action on the content posted by the first target, display the comment input interface;

[0196] Receive comment information entered by users in the comment input interface;

[0197] Perform sensitive word detection on comment information;

[0198] If the comment contains a first sensitive word, then the first sensitive word is censored to obtain the first target comment information;

[0199] The user attributes for obtaining comment information include the user's job information and historical comment information;

[0200] The first user rating is obtained based on the most sensitive keywords and user attributes.

[0201] The first display order of the first target comment information is determined based on the first target comment information and the first user rating;

[0202] Based on the first display order, the first target comment information is displayed in the comment display interface.

[0203] In some embodiments, a computer program product is also proposed, comprising a computer program or instructions that, when executed by a processor, implement the steps in any of the above-described comment methods.

[0204] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0205] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0206] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to perform the steps in any of the comment methods provided in embodiments of this application.

[0207] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0208] According to one aspect of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium.

[0209] Since the instructions stored in the storage medium can execute the steps in any of the comment methods provided in the embodiments of this application, the beneficial effects that any of the comment methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0210] The foregoing has provided a detailed description of a commenting method, apparatus, electronic device, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A commenting method, characterized in that, The method includes: In response to a comment action on the content posted by the first target, display the comment input interface; Receive comment information entered by the user on the comment input interface; Sensitive word detection is performed on the comment information; If the comment information contains a first sensitive word, then the first sensitive word is censored to obtain the first target comment information; Obtain the user attributes of the comment information, wherein the user attributes include the user's job information and historical comment information; Based on the first sensitive word and the user attributes, a first user score is obtained; Based on the first target comment information and the first user rating, determine the first display order of the first target comment information; Based on the first display order, the first target comment information is displayed in the comment display interface; The first target comment information is subjected to a second keyword retrieval process to obtain at least one knowledge keyword tag in the first target comment information; Based on at least one of the knowledge keyword tags, select a second target published content from a pre-stored database, wherein the second target published content contains all of the knowledge keyword tags in the first target comment information; Obtain the second address information of the second target published content, and display the second address information of the second target published content in the first target comment information; The step of obtaining the first user score based on the first sensitive word and the user attribute includes: Perform first keyword retrieval processing on the first target published content to determine the knowledge point tags of the first target published content; Based on the knowledge point tags and the job information, determine the degree of matching between the user and the content published by the first target; Based on the historical comment information, obtain historical sensitive word information; Based on the historical sensitive word information and the first sensitive word, the occurrence rate of the sensitive word is determined; The first user score is obtained based on the matching degree and the occurrence rate of the sensitive words.

2. The method according to claim 1, characterized in that, After detecting sensitive words in the comment information, the method further includes: If the comment contains a second sensitive word, the comment will be sent to a manual review terminal for manual review. The second sensitive word is a sensitive word with a higher sensitivity than the first sensitive word. Receive the review results sent by the manual review terminal; If the review result is approved, the second sensitive word will be censored to obtain the second target comment information; Obtain the user attributes of the comment information, wherein the user attributes include the user's name, job information, and historical comment information; A second user score is obtained based on the second sensitive word and the user attribute; Based on the second target review information and the second user rating, determine the second display order of the second target review information; According to the second display order, the second target comment information is displayed in the comment display interface.

3. The method according to claim 1, characterized in that, After detecting sensitive words in the comment information, the method further includes: If the comment contains any sensitive third-party words, the comment will be blocked.

4. The method according to claim 1, characterized in that, After detecting sensitive words in the comment information, the method further includes: If the comment information does not contain any sensitive words, the comment information will be displayed on the comment display interface.

5. The method according to claim 1, characterized in that, After determining the second target content to be published in a pre-stored database based on at least one of the knowledge keyword tags, the method further includes: Obtain the first address information of the first target published content, and display the first target comment information and the first address information in the comment display interface of the second target published content.

6. A commenting device, characterized in that, include: The first response unit is used to respond to comment operations on the content published by the first target and display the comment input interface; The receiving unit is used to receive comment information entered by the user on the comment input interface; The detection unit is used to detect sensitive words in the comment information; The censoring unit is used to censor the first sensitive word if the comment information contains a first sensitive word, so as to obtain the first target comment information; The acquisition unit is used to acquire user attributes of the comment information, wherein the user attributes include the user's job information and historical comment information; The obtaining unit is used to obtain a first user score based on the first sensitive word and the user attribute; The display unit is configured to determine a first display order of the first target comment information based on the first target comment information and the first user rating; The second response unit is configured to display first target comment information in the comment display interface according to the first display order; The second response unit is further configured to perform second keyword retrieval processing on the first target comment information to obtain at least one knowledge keyword tag in the first target comment information; select second target published content from a pre-stored database according to the at least one knowledge keyword tag, wherein the second target published content contains all the knowledge keyword tags in the first target comment information; obtain the second address information of the second target published content, and display the second address information of the second target published content in the first target comment information; The obtaining unit is further used for: Perform first keyword retrieval processing on the first target published content to determine the knowledge point tags of the first target published content; Based on the knowledge point tags and the job information, determine the degree of matching between the user and the content published by the first target; Based on the historical comment information, obtain historical sensitive word information; Based on the historical sensitive word information and the first sensitive word, the occurrence rate of the sensitive word is determined; The first user score is obtained based on the matching degree and the occurrence rate of the sensitive words.

7. An electronic device, characterized in that, It includes a processor and a memory, the memory storing multiple instructions; the processor loads instructions from the memory to perform the steps in the comment method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to perform the steps of the comment method according to any one of claims 1 to 5.

Images