User comment management method and device

The method and device manage user comments by identifying sensitive content and setting quality levels, filtering out inappropriate comments and restricting users, ensuring ethical interaction standards in information filtering systems.

CN113239674BInactive Publication Date: 2024-12-03BANK OF CHINA
View PDF 13 Cites 0 Cited by

Patent Information

Application Number
CN202110663064.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-15
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The challenge of managing user comments to ensure they align with mainstream values and social ethics in the context of information filtering, particularly in financial services, has not been adequately addressed.

Method used

A method and device for managing user comments that involve determining if the comment contains sensitive words, prohibiting its publication, and setting quality levels based on historical comment analysis, with restrictions for users below a threshold.

Benefits of technology

Effectively filters out sensitive comments and manages user participation by preventing their publication and imposing time-based restrictions on users with low quality levels, maintaining ethical standards in user interactions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113239674B_ABST
    Figure CN113239674B_ABST
Patent Text Reader

Abstract

The present application provides a user comment management method and device, the method comprising: responding to the comment information input by the user, obtaining the comment information, taking the comment information as the current comment information, judging whether the current comment information contains sensitive words, if the current comment information contains sensitive words, prohibiting the release of the current comment information, and obtaining the user's historical comment information set; the new historical comment set includes the comment information input by the user; according to the current comment information and the historical comment information set, determining the user's quality level, if the quality level is less than a preset threshold, setting comment restrictions on the user. In this technical solution, if the user's comment information contains sensitive words, the user's comment information will not be released, and when the user's numerical level is less than the preset threshold, the user will be set to comment restrictions, thereby achieving management of user comments.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of information filtering, and in particular to a method and device for managing user comments. Background Art

[0002] Information is an important means for banks to introduce stock trading, fund bond products, and is generally presented to users in the form of text and pictures. Users interact and comment under the information, which not only makes it easier for customers to understand the content of the information, but also increases the activity of information topics and user participation.

[0003] With the explosive growth of comment content, it is inevitable that there will be comments that are inconsistent with mainstream values ​​and violate social ethics. Therefore, how to provide a method for managing user comments is an urgent problem that people in this field need to solve. Summary of the invention

[0004] Based on the above-mentioned deficiencies of the prior art, the present application provides a user comment management method to achieve the management of user comments.

[0005] The present application also provides a user comment management device to ensure the implementation and application of the above method in practice.

[0006] A user comment management method, comprising:

[0007] In response to the comment information input by the user, the comment information is obtained, and the comment information is used as the current comment information;

[0008] Determine whether the current comment information contains sensitive words;

[0009] If the current comment information contains sensitive words, the current comment information is prohibited from being published, and a collection of historical comment information of the user is obtained; the new collection of historical comments includes the comment information historically input by the user;

[0010] Determining the quality level of the user based on the current review information and the historical review information set;

[0011] If the quality level is less than a preset threshold, comment restrictions are set for the user.

[0012] In the above method, optionally, the step of determining whether the current comment information contains sensitive words includes:

[0013] Performing data processing on the current comment information to obtain a data set corresponding to the current comment information; the data set includes multiple data items;

[0014] Determine whether there is a sensitive word matching any data item in the pre-built knowledge base;

[0015] If there is no sensitive word matching any data item in the knowledge base, it is determined that the current comment information does not contain a sensitive word;

[0016] If there is a sensitive word matching any data item in the knowledge base, it is determined that the current comment information contains the sensitive word.

[0017] In the above method, optionally, the data processing of the current comment information to obtain a data set corresponding to the current comment information includes:

[0018] Preprocessing the current comment information;

[0019] Perform word segmentation on the preprocessed current comment information to obtain multiple words;

[0020] Perform pinyin conversion on each word to obtain the pinyin string corresponding to each word;

[0021] Perform word meaning analysis on each word to obtain the meaning of each word;

[0022] Each word, the pinyin string corresponding to each word, and the meaning of each word form a data set corresponding to the current comment information.

[0023] In the above method, optionally, determining the quality level of the user based on the current comment information and the historical comment information set includes:

[0024] Determine the comment information containing sensitive words in the historical comment information set;

[0025] Determine each comment information containing a sensitive word in the historical comment information set and the current comment information as sensitive comment information;

[0026] Counting the probability of sensitive comments; the probability of sensitive comments is used to represent the ratio of the number of sensitive comment information to the total number of comment information;

[0027] According to the preset correspondence between the probability of sensitive comments and the quality level, the quality level corresponding to the probability of sensitive comments is determined.

[0028] The above method may, optionally, after prohibiting the publication of the current comment information, further include:

[0029] Sending a prompt message to a device corresponding to the user; the prompt message is used to prompt that the current comment information contains sensitive words.

[0030] A user comment management device, comprising:

[0031] A first acquisition unit, configured to respond to comment information input by a user, acquire the comment information, and use the comment information as current comment information;

[0032] A judging unit, used to judge whether the current comment information contains sensitive words;

[0033] A second acquisition unit is used to prohibit publishing the current comment information if the current comment information contains sensitive words, and acquire a set of historical comment information of the user; the new set of historical comments includes the comment information historically input by the user;

[0034] A determination unit, configured to determine the quality level of the user based on the current comment information and the historical comment information set;

[0035] A setting unit is used to set comment restrictions for the user if the quality level is less than a preset threshold.

[0036] In the above device, optionally, the judging unit is used to judge whether the current comment information contains sensitive words, including the judging unit being specifically used to:

[0037] Performing data processing on the current comment information to obtain a data set corresponding to the current comment information; the data set includes multiple data items;

[0038] Determine whether there is a sensitive word matching any data item in the pre-built knowledge base;

[0039] If there is no sensitive word matching any data item in the knowledge base, it is determined that the current comment information does not contain a sensitive word;

[0040] If there is a sensitive word matching any data item in the knowledge base, it is determined that the current comment information contains the sensitive word.

[0041] In the above device, optionally, the judgment unit is used to perform data processing on the current comment information to obtain a data set corresponding to the current comment information, including the judgment unit being specifically used to:

[0042] Preprocessing the current comment information;

[0043] Perform word segmentation on the preprocessed current comment information to obtain multiple words;

[0044] Perform pinyin conversion on each word to obtain the pinyin string corresponding to each word;

[0045] Perform word meaning analysis on each word to obtain the meaning of each word;

[0046] Each word, the pinyin string corresponding to each word, and the meaning of each word form a data set corresponding to the current comment information.

[0047] In the above device, optionally, the determining unit is used to determine the quality level of the user based on the current comment information and the historical comment information set, including the determining unit being specifically used to:

[0048] Determine the comment information containing sensitive words in the historical comment information set;

[0049] Determine each comment information containing a sensitive word in the historical comment information set and the current comment information as sensitive comment information;

[0050] Counting the probability of sensitive comments; the probability of sensitive comments is used to represent the ratio of the number of sensitive comment information to the total number of comment information;

[0051] According to the preset correspondence between the probability of sensitive comments and the quality level, the quality level corresponding to the probability of sensitive comments is determined.

[0052] The above device may optionally further include:

[0053] A prompt unit is used to send a prompt message to the device corresponding to the user; the prompt message is used to prompt that the current comment information contains sensitive words.

[0054] A storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned user comment management method.

[0055] An electronic device includes a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to perform the above-mentioned user comment management method.

[0056] Compared with the prior art, this application has the following advantages:

[0057] The present application provides a user comment management method and device, the method comprising: responding to the comment information input by the user, obtaining the comment information, taking the comment information as the current comment information, judging whether the current comment information contains sensitive words, if the current comment information contains sensitive words, prohibiting the release of the current comment information, and obtaining the user's historical comment information set; the new historical comment set includes the comment information input by the user; according to the current comment information and the historical comment information set, determining the user's quality level, if the quality level is less than a preset threshold, setting comment restrictions on the user. In this technical solution, if the user's comment information contains sensitive words, the user's comment information will not be released, and when the user's numerical level is less than the preset threshold, the user will be set to comment restrictions, thereby achieving management of user comments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0059] Figure 1 A method flow chart of a user comment management method provided for this application;

[0060] Figure 2 Another method flow chart of a user comment management method provided by this application;

[0061] Figure 3 Another method flow chart of a user comment management method provided by this application;

[0062] Figure 4 A flowchart of another method for managing user comments provided in this application;

[0063] Figure 5 A schematic diagram of the structure of a user comment management device provided in this application;

[0064] Figure 6 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0066] The present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or equipment, etc.

[0067] The embodiment of the present invention provides a user comment management method, which can be applied to various system platforms, and its execution subject can be a processor of a computer terminal or various mobile devices. The method flow chart of the method is as follows: Figure 1 As shown, specifically including:

[0068] S101. Respond to comment information input by a user, obtain the comment information, and use the comment information as current comment information.

[0069] When the user wants to post a comment, the comment information is input, and in response to the comment information input by the user, the comment information is obtained.

[0070] It should be noted that, in this embodiment, the comment information input by the user is responded to in real time, that is, as long as the user inputs the comment information, the comment information input by the user is responded to immediately.

[0071] In this embodiment, the comment information is used as the current comment information.

[0072] S102: Determine whether the current comment information contains sensitive words. If not, execute step S103; if so, execute step S104.

[0073] In this embodiment, sensitive word recognition is performed on the current comment information to determine whether the current comment information contains sensitive words.

[0074] See also Figure 2 , the process of judging whether the current comment information contains sensitive words specifically includes the following steps:

[0075] S201: Perform data processing on the current comment information to obtain a data set corresponding to the current comment information.

[0076] In this embodiment, data processing is performed on the current comment information to divide the current comment information into multiple data items, and the individual data items are combined into a data set corresponding to the current comment information, that is, the data set includes multiple data items.

[0077] See also Figure 3 , the process of processing the current comment information to obtain the data set corresponding to the current comment information specifically includes the following steps:

[0078] S301, pre-processing the current comment information.

[0079] In this embodiment, the current comment information is preprocessed to delete irrelevant words in the current comment information, where the irrelevant words include but are not limited to modal particles and stop words.

[0080] S302: Perform word segmentation processing on the preprocessed current comment information to obtain multiple words.

[0081] In this embodiment, the preprocessed current comment information is segmented to achieve the purpose of dividing the preprocessed current comment information into multiple words.

[0082] In this embodiment, natural language processing (NLP) technology may be used to perform word segmentation processing on the pre-processed current comment information to obtain a plurality of words.

[0083] S303: Perform pinyin conversion on each word to obtain the pinyin string corresponding to each word.

[0084] In this embodiment, each word is subjected to pinyin conversion processing to obtain a pinyin string corresponding to each word.

[0085] S304: Analyze the meaning of each word to obtain the meaning of each word.

[0086] In this embodiment, the existing word meaning analysis strategy is adopted to perform word analysis on each word, so as to obtain the meaning of each word.

[0087] S305: Each word, the pinyin string corresponding to each word, and the meaning of each word are combined into a data set corresponding to the current comment information.

[0088] In this embodiment, each word, the pinyin string corresponding to each word, and the meaning of each word are combined into a data set corresponding to the current comment information.

[0089] In this implementation, by obtaining each word of the preprocessed current comment information, the meaning and pinyin string corresponding to each word, a more comprehensive vocabulary corresponding to the current comment information is obtained.

[0090] S202: Determine whether there is a sensitive word matching any data item in the pre-built knowledge base. If so, execute step S203; if not, execute step S204.

[0091] In this embodiment, a knowledge base is pre-built, and the knowledge base includes a plurality of sensitive words.

[0092] Each data item included in the data set is matched with each sensitive word in the knowledge base to determine whether there is a sensitive word matching any data item in the knowledge base.

[0093] S203: Determine that the current comment information contains sensitive words.

[0094] S204: Determine that the current comment information does not contain sensitive words.

[0095] In the method provided in the embodiment of the present application, a pre-built knowledge base is used to identify sensitive words in the current comment information to determine whether the current comment information includes sensitive words.

[0096] S103, publish current comment information.

[0097] In this embodiment, if it is determined that the current comment information does not contain sensitive words, the current comment information is directly published.

[0098] In this embodiment, the current comment information and the marking information corresponding to the current comment information are stored in association, wherein the marking information corresponding to the current comment information is used to indicate that the current comment information does not contain sensitive words.

[0099] S104: prohibit the release of current comment information, and obtain the user's historical comment information collection.

[0100] In this embodiment, if it is determined that the current comment information contains sensitive words, the current comment information is prohibited from being published.

[0101] In this embodiment, the current comment information and the marking information corresponding to the current comment information are stored in association, wherein the marking information corresponding to the current comment information is used to indicate that the current comment information contains sensitive words.

[0102] In this embodiment, a historical comment information set of the user is obtained, wherein the historical comment information set includes comment information historically input by the user.

[0103] S105. Determine the user's quality level based on the current comment information and the historical comment information set.

[0104] In this embodiment, the comment information containing sensitive words in the current comment information and the historical comment information set is counted, and the user's quality level is determined based on the comment information containing sensitive words.

[0105] See also Figure 4 ,The process of determining the user's quality level based on the current comment information and the historical comment information set specifically includes the following steps:

[0106] S401: Determine the comment information containing sensitive words in the historical comment information set.

[0107] Determine the comment information containing sensitive words in the historical comment information set. Specifically, determine the comment information containing sensitive words in the historical comment information set based on identification information of each comment information included in the historical comment information set.

[0108] S402: Determine each comment information containing sensitive words in the historical comment information set and the current comment information as sensitive comment information.

[0109] S403. Count the probability of sensitive comments. The probability of sensitive comments is used to represent the ratio of the number of sensitive comment information to the total number of comment information.

[0110] In this embodiment, the probability of sensitive comments is calculated. Specifically, the number of sensitive comment information is divided by the total number of comment information to obtain the probability of sensitive comments, wherein the total number of comment information is the number of comment information included in the historical comment information set plus one.

[0111] Among them, the sensitive comment probability is used to represent the ratio of the number of sensitive comment information to the total number of comment information.

[0112] S404. Determine the quality level corresponding to the sensitive comment probability based on the preset correspondence between the sensitive comment probability and the quality level.

[0113] In this embodiment, a correspondence between the probability of sensitive comments and the quality level is preset, that is, different sensitive comment probability ranges are preset to correspond to different quality levels.

[0114] Based on the calculated probability of sensitive comments, determine the sensitive probability range to which it belongs, and then determine the quality level corresponding to the sensitive comment probability.

[0115] S106, determine whether the user's quality level is less than a preset threshold, if so, execute step S107, if not, execute step S108.

[0116] S107, setting comment restrictions for users.

[0117] If the user's quality level is less than a preset threshold, a comment restriction is set for the user, prohibiting the user from entering comment information within a target time period. Optionally, the target time period can be set to one week, which means that the user is restricted from entering comment information from the current time to the next week.

[0118] Optionally, first prompt information for prompting the user to refrain from inputting comment information during the target time period may also be output.

[0119] It should be noted that users can continue to enter comment information only after the restrictions are lifted.

[0120] S108. Do not set comment restrictions on users.

[0121] If the user's quality level is not less than the preset threshold, no comment restriction will be set for the user.

[0122] The user comment management method provided in the embodiment of the present application responds to the comment information input by the user, obtains the comment information, takes the comment information as the current comment information, determines whether the current comment information contains sensitive words, and if the current comment information contains sensitive words, prohibits the current comment information from being published, and obtains the user's historical comment information set; the new historical comment set includes the comment information historically input by the user; the user's quality level is determined based on the current comment information and the historical comment information set, and if the quality level is less than a preset threshold, comment restrictions are set for the user. Applying the user comment management method provided in the embodiment of the present application, if the user's comment information includes sensitive words, the user's comment information will not be published, and when the user's numerical level is less than a preset threshold, comment restrictions are set for the user, thereby achieving management of user comments.

[0123] The user comment management method provided in the embodiment of the present application may further include, after prohibiting the publication of the current comment information mentioned in step S104:

[0124] A prompt message is sent to the device corresponding to the user; the prompt message is used to indicate that the current comment information contains sensitive words.

[0125] The user comment management method provided in the embodiment of the present application can also send a prompt message to the device corresponding to the user to prompt the user that the current comment information contains sensitive words.

[0126] and Figure 1 Corresponding to the method described above, the embodiment of the present application also provides a user comment management device for Figure 1 The specific implementation of the method is shown in the following diagram: Figure 5 As shown, specifically including:

[0127] The first acquisition unit 501 is used to respond to the comment information input by the user, acquire the comment information, and use the comment information as the current comment information;

[0128] The judging unit 502 is used to judge whether the current comment information contains sensitive words;

[0129] The second acquisition unit 503 is used to prohibit the release of the current comment information if the current comment information contains sensitive words, and acquire a set of historical comment information of the user; the new set of historical comments includes the comment information historically input by the user;

[0130] A determination unit 504, configured to determine the quality level of the user based on the current comment information and the historical comment information set;

[0131] The setting unit 505 is used to set comment restrictions for the user if the quality level is less than a preset threshold.

[0132] The user comment management device provided in the embodiment of the present application responds to the comment information input by the user, obtains the comment information, takes the comment information as the current comment information, determines whether the current comment information contains sensitive words, and if the current comment information contains sensitive words, prohibits the current comment information from being published, and obtains the user's historical comment information set; the new historical comment set includes the comment information historically input by the user; the user's quality level is determined based on the current comment information and the historical comment information set, and if the quality level is less than a preset threshold, comment restrictions are set for the user. Using the user comment management device provided in the embodiment of the present application, if the user's comment information includes sensitive words, the user's comment information will not be published, and when the user's numerical level is less than a preset threshold, comment restrictions are set for the user, thereby achieving management of user comments.

[0133] In one embodiment of the present application, based on the above solution, the judging unit 502 is used to judge whether the current comment information contains sensitive words, including the judging unit 502 is specifically used to:

[0134] Performing data processing on the current comment information to obtain a data set corresponding to the current comment information; the data set includes multiple data items;

[0135] Determine whether there is a sensitive word matching any data item in the pre-built knowledge base;

[0136] If there is no sensitive word matching any data item in the knowledge base, it is determined that the current comment information does not contain a sensitive word;

[0137] If there is a sensitive word matching any data item in the knowledge base, it is determined that the current comment information contains the sensitive word.

[0138] In one embodiment of the present application, based on the above solution, the judgment unit 502 is used to perform data processing on the current comment information to obtain a data set corresponding to the current comment information, including the judgment unit 502 being specifically used to:

[0139] Preprocessing the current comment information;

[0140] Perform word segmentation on the preprocessed current comment information to obtain multiple words;

[0141] Perform pinyin conversion on each word to obtain the pinyin string corresponding to each word;

[0142] Perform word meaning analysis on each word to obtain the meaning of each word;

[0143] Each word, the pinyin string corresponding to each word, and the meaning of each word form a data set corresponding to the current comment information.

[0144] In one embodiment of the present application, based on the above solution, the determination unit 504 is used to determine the quality level of the user according to the current comment information and the historical comment information set, including the determination unit 504 being specifically used to:

[0145] Determine the comment information containing sensitive words in the historical comment information set;

[0146] Determine each comment information containing a sensitive word in the historical comment information set and the current comment information as sensitive comment information;

[0147] Counting the probability of sensitive comments; the probability of sensitive comments is used to represent the ratio of the number of sensitive comment information to the total number of comment information;

[0148] According to the preset correspondence between the probability of sensitive comments and the quality level, the quality level corresponding to the probability of sensitive comments is determined.

[0149] In one embodiment of the present application, based on the above solution, it can also be configured as follows:

[0150] A prompt unit is used to send a prompt message to the device corresponding to the user; the prompt message is used to prompt that the current comment information contains sensitive words.

[0151] The embodiment of the present application further provides a storage medium, wherein the storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to perform the following operations:

[0152] In response to the comment information input by the user, the comment information is obtained, and the comment information is used as the current comment information;

[0153] Determine whether the current comment information contains sensitive words;

[0154] If the current comment information contains sensitive words, the current comment information is prohibited from being published, and a collection of historical comment information of the user is obtained; the new collection of historical comments includes the comment information historically input by the user;

[0155] Determining the quality level of the user based on the current review information and the historical review information set;

[0156] If the quality level is less than a preset threshold, comment restrictions are set for the user.

[0157] The present application also provides an electronic device, whose structural diagram is as follows: Figure 6 As shown, it specifically includes a memory 601 and one or more instructions 602, wherein the one or more instructions 602 are stored in the memory 601 and are configured to be executed by one or more processors 603 to perform the following operations:

[0158] In response to the comment information input by the user, the comment information is obtained, and the comment information is used as the current comment information;

[0159] Determine whether the current comment information contains sensitive words;

[0160] If the current comment information contains sensitive words, the current comment information is prohibited from being published, and a collection of historical comment information of the user is obtained; the new collection of historical comments includes the comment information historically input by the user;

[0161] Determining the quality level of the user based on the current review information and the historical review information set;

[0162] If the quality level is less than a preset threshold, comment restrictions are set for the user.

[0163] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0164] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0165] For the convenience of description, the above system is described by dividing it into various units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0166] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0167] The above is a detailed introduction to a user comment management method and device provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A user comment management method, characterized in that: include: In response to the comment information input by the user, the comment information is obtained, and the comment information is used as the current comment information; Determine whether the current comment information contains sensitive words; If the current comment information contains sensitive words, the current comment information is prohibited from being published, and a collection of historical comment information of the user is obtained; the collection of historical comment information includes the comment information historically input by the user; storing the current comment information and the tag information corresponding to the current comment information in association with each other, wherein the tag information is used to indicate that the current comment information contains sensitive words; Determining, based on identification information of each comment information included in the historical comment information set, comment information containing sensitive words in the historical comment information set; Determine each comment information containing a sensitive word in the historical comment information set and the current comment information as sensitive comment information; The sensitive comment probability is obtained by dividing the number of sensitive comment information by the total number of comment information, where the total number of comment information is the number of comment information included in the historical comment information set plus one; the sensitive comment probability is used to represent the ratio of the number of sensitive comment information to the total number of comment information; According to the preset correspondence between the probability of sensitive comments and the quality level, determine the quality level corresponding to the probability of sensitive comments; If the quality level is less than a preset threshold, comment restrictions are set for the user.

2. The method according to claim 1, characterized in that The determining whether the current comment information contains sensitive words includes: Performing data processing on the current comment information to obtain a data set corresponding to the current comment information; the data set includes multiple data items; Determine whether there is a sensitive word matching any data item in the pre-built knowledge base; If there is no sensitive word matching any data item in the knowledge base, it is determined that the current comment information does not contain a sensitive word; If there is a sensitive word matching any data item in the knowledge base, it is determined that the current comment information contains the sensitive word.

3. The method according to claim 2, characterized in that The data processing of the current comment information to obtain a data set corresponding to the current comment information includes: Preprocessing the current comment information; Perform word segmentation on the preprocessed current comment information to obtain multiple words; Perform pinyin conversion on each word to obtain the pinyin string corresponding to each word; Perform word meaning analysis on each word to obtain the meaning of each word; Each word, the pinyin string corresponding to each word, and the meaning of each word form a data set corresponding to the current comment information.

4. The method according to claim 1, characterized in that After prohibiting the release of the current comment information, the method further includes: Sending a prompt message to a device corresponding to the user; the prompt message is used to prompt that the current comment information contains sensitive words.

5. A user comment management device, characterized in that: include: A first acquisition unit, configured to respond to comment information input by a user, acquire the comment information, and use the comment information as current comment information; A judging unit, used to judge whether the current comment information contains sensitive words; A second acquisition unit is used to prohibit publishing the current comment information if the current comment information contains sensitive words, and acquire a set of historical comment information of the user; the set of historical comment information includes the comment information historically input by the user; storing the current comment information and the tag information corresponding to the current comment information in association with each other, wherein the tag information is used to indicate that the current comment information contains sensitive words; A determination unit, configured to determine the quality level of the user based on the current comment information and the historical comment information set; A setting unit, configured to set comment restrictions on the user if the quality level is less than a preset threshold; The determining unit is used to determine the quality level of the user according to the current comment information and the historical comment information set, including the determining unit being specifically used to: Determining, based on identification information of each comment information included in the historical comment information set, comment information containing sensitive words in the historical comment information set; Determine each comment information containing a sensitive word in the historical comment information set and the current comment information as sensitive comment information; The sensitive comment probability is obtained by dividing the number of sensitive comment information by the total number of comment information, where the total number of comment information is the number of comment information included in the historical comment information set plus one; the sensitive comment probability is used to represent the ratio of the number of sensitive comment information to the total number of comment information; According to the preset correspondence between the probability of sensitive comments and the quality level, the quality level corresponding to the probability of sensitive comments is determined.

6. The device according to claim 5, characterized in that The judging unit is used to judge whether the current comment information contains sensitive words, including the judging unit being specifically used to: Performing data processing on the current comment information to obtain a data set corresponding to the current comment information; the data set includes multiple data items; Determine whether there is a sensitive word matching any data item in the pre-built knowledge base; If there is no sensitive word matching any data item in the knowledge base, it is determined that the current comment information does not contain a sensitive word; If there is a sensitive word matching any data item in the knowledge base, it is determined that the current comment information contains the sensitive word.

7. The device according to claim 6, characterized in that The judging unit is used to perform data processing on the current comment information to obtain a data set corresponding to the current comment information, including the judging unit being specifically used to: Preprocessing the current comment information; Perform word segmentation on the preprocessed current comment information to obtain multiple words; Perform pinyin conversion on each word to obtain the pinyin string corresponding to each word; Perform word meaning analysis on each word to obtain the meaning of each word; Each word, the pinyin string corresponding to each word, and the meaning of each word form a data set corresponding to the current comment information.

8. The device according to claim 5, characterized in that Also includes: A prompt unit, used to send prompt information to a device corresponding to the user; The prompt information is used to prompt that the current comment information contains sensitive words.

Citation Information

Patent Citations

  • Account management method and apparatus

    CN108768840A

  • A method and a system for automatically identifying network paid posters

    CN109213858A

  • Malicious comment information identification method and device

    CN109977403A

  • Comment recognition method and device, computer readable storage medium and computer equipment

    CN110209795A

  • Sensitive account detection method, storage medium and computer equipment

    CN111079029A