Text recognition method applied to text detection system and text detection system

Abstract

The application relates to the technical field of data recognition, and discloses a text recognition method applied to a text detection system and the text detection system, the method comprising the following steps: extracting a keyword set from text information through the text detection system, and performing sensitive word recognition on the keyword set according to a sensitive word set to obtain a sensitive word recognition result corresponding to the keyword set; when the sensitive word recognition result indicates that at least one target keyword in the keyword set matches the sensitive word set, the text detection system generates prompt information of each target keyword and sends the prompt information of each target keyword to an operation and management end of a target game. It can be seen that the application can improve the comprehensiveness and accuracy of sensitive information recognition, reduce the probability of sensitive words appearing in game text, improve the health degree and safety of the game, reduce the probability of inappropriate remarks appearing when players chat in the game, standardize the chatting behavior of players in the game, and improve the health of the game.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data recognition, and in particular to a text recognition method applied to a text detection system and the text detection system. BACKGROUND

[0002] With the rapid development of Internet technology, online games have become one of the important ways for people to relax and entertain. In the game, players not only can experience rich plots, but also can communicate with other players in real time through the chat system. However, this open communication environment also brings a series of problems, such as the spread of bad information and the spread of malicious remarks, which may have a negative impact on the healthy operation of the game and the game experience of the players.

[0003] In order to effectively monitor the text information in the game and ensure the healthy and civilized operation of the game, a text detection system emerges as the times require. However, the detection accuracy and comprehensiveness of sensitive words in the existing text detection system are low. Therefore, it is particularly important to propose a technical solution that can improve the detection accuracy and comprehensiveness of sensitive words in the game text. SUMMARY

[0004] The present application provides a text recognition method applied to a text detection system and the text detection system, which can improve the detection accuracy and comprehensiveness of sensitive words in the game text.

[0005] In order to solve the above technical problems, the first aspect of the present application discloses a text recognition method applied to a text detection system, which comprises:

[0006] The text detection system obtains the text information of a target game and extracts a keyword set from the text information, wherein the text information includes game content text information and / or user chat text information;

[0007] The text detection system obtains a preset sensitive word set and performs sensitive word recognition on the keyword set according to the sensitive word set to obtain a sensitive word recognition result corresponding to the keyword set;

[0008] The text detection system analyzes the sensitive word recognition result, and when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates a prompt information of each target keyword and sends the prompt information of each target keyword to an operation and management end of the target game.

[0009] As an optional implementation manner, in the first aspect of the present application, the sensitive word recognition result includes a first sub-recognition result and a second sub-recognition result;

[0010] The text detection system performs sensitive word recognition on the keyword set according to the sensitive word set, to obtain a sensitive word recognition result corresponding to the keyword set, including:

[0011] The text detection system performs sensitive word recognition on each keyword in the keyword set according to the sensitive word set, to obtain the first sub-recognition result corresponding to the keyword set;

[0012] The text detection system determines keyword information of each keyword in the keyword set, and divides the keyword set according to the keyword information of each keyword, to obtain at least two sub-keyword sets;

[0013] The text detection system determines semantic features corresponding to each sub-keyword set, and performs sensitive semantic recognition on the semantic features corresponding to each sub-keyword set according to the sensitive word set, to obtain the second sub-recognition result corresponding to the keyword set.

[0014] As an optional implementation form, in the first aspect of the present application, the text detection system determines keyword information of each keyword in the keyword set, including:

[0015] The text detection system determines target information of each keyword in the keyword set, and the target information includes keyword frequency information and keyword meaning information;

[0016] The text detection system calculates a keyword score corresponding to each keyword according to the target information corresponding to each keyword;

[0017] The text detection system calculates a string distance between each keyword in the keyword set;

[0018] The text detection system determines keyword information of each keyword according to the keyword score corresponding to each keyword and the string distance between each keyword.

[0019] As an optional implementation form, in the first aspect of the present application, the text detection system divides the keyword set according to the keyword information of each keyword, to obtain at least two sub-keyword sets, including:

[0020] The text detection system obtains a preset weight allocation rule, and determines a keyword score weight corresponding to each keyword and a string distance weight between each keyword according to the weight allocation rule;

[0021] The text detection system calculates an association parameter between each of the keywords according to the keyword score corresponding to each of the keywords, the keyword score weight, a string distance between each of the keywords, and the string distance weight;

[0022] The text detection system divides the keyword set according to a preset association parameter threshold and the association parameter between each of the keywords, to obtain at least two sub-keyword sets;

[0023] Each of the sub-keyword sets includes at least two associated keywords, and the association parameter between each of the associated keywords in each of the sub-keyword sets is greater than the association parameter threshold.

[0024] As an optional implementation form, in the first aspect of the present application, the text detection system determines the semantic feature corresponding to each of the sub-keyword sets, including:

[0025] For each of the sub-keyword sets, the text detection system determines the expansion word information of each of the associated keywords in the sub-keyword set according to the keyword meaning of each of the associated keywords in the sub-keyword set, and the expansion word information includes synonym expansion word information and / or antonym expansion word information;

[0026] For each of the sub-keyword sets, the text detection system determines the context semantic information of each of the associated keywords in the sub-keyword set;

[0027] For each of the sub-keyword sets, the text detection system determines a first coefficient corresponding to the expansion word information of each of the associated keywords in the sub-keyword set and a second coefficient corresponding to the context semantic information;

[0028] For each of the sub-keyword sets, the text detection system randomly combines each of the associated keywords in the sub-keyword set to obtain at least one keyword combination, and each of the keyword combinations includes at least two associated keywords;

[0029] For each of the sub-keyword sets, for each of the keyword combinations, the text detection system determines a combination semantic feature corresponding to the keyword combination according to the expansion word information, the first coefficient, the context semantic information, and the second coefficient corresponding to the keyword combination;

[0030] For each of the sub-keyword sets, the text detection system determines the semantic feature corresponding to the sub-keyword set according to the combination semantic feature corresponding to each of the keyword combinations in the sub-keyword set.

[0031] As an optional implementation, in the first aspect of the present application, the method further comprises:

[0032] The text detection system acquires a set of ignored words for the target game, and updates the set of sensitive words according to the set of ignored words;

[0033] In addition, the text detection system performs sensitive word recognition on each keyword in the set of keywords according to the set of sensitive words, to obtain the first sub-recognition result corresponding to the set of keywords, which comprises:

[0034] The text detection system performs sensitive word recognition on the set of keywords according to the set of sensitive words and the set of ignored words, to obtain the first target recognition result corresponding to the set of keywords;

[0035] The text detection system screens a set of related words corresponding to the first target recognition result from the set of keywords, wherein the set of related words comprises at least one of the following: synonyms, antonyms, and the like of the first target recognition result;

[0036] The text detection system performs sensitive word recognition on the set of related words according to the set of sensitive words and the set of ignored words, to obtain the second target recognition result corresponding to the set of keywords;

[0037] The text detection system determines the first sub-recognition result corresponding to the set of keywords according to the first target recognition result and the second target recognition result.

[0038] As an optional implementation, in the first aspect of the present application, when the sensitive word recognition result indicates that there is at least one target keyword in the set of keywords that matches the set of sensitive words, the method further comprises:

[0039] The text detection system determines feature information of each keyword in the set of keywords, wherein the feature information comprises attribute label features and / or fine-grained features;

[0040] For each keyword, the text detection system classifies and stores the keyword into a preset feature library according to the feature information of the keyword;

[0041] In addition, the method further comprises:

[0042] When the text detection system receives a sensitive word recognition range and a sensitive word configuration requirement sent by the operation and management end, the text detection system configures a set of sensitive words based on the feature library according to the sensitive word recognition range and the sensitive word configuration requirement.

[0043] The second aspect of the present application discloses a text detection system, comprising:

[0044] An acquisition module is configured to acquire text information of a target game, and extract a keyword set from the text information, wherein the text information comprises game content text information and / or user chat text information;

[0045] The acquisition module is further configured to acquire a preset sensitive word set, and perform sensitive word identification on the keyword set according to the sensitive word set, to obtain a sensitive word identification result corresponding to the keyword set;

[0046] An analysis module is configured to analyze the sensitive word identification result, and when the sensitive word identification result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, generate prompt information of each target keyword, and send the prompt information of each target keyword to an operation and management end of the target game.

[0047] As an optional implementation, in the second aspect of the present application, the sensitive word identification result comprises a first sub-identification result and a second sub-identification result;

[0048] The acquisition module performs sensitive word identification on the keyword set according to the sensitive word set, to obtain the sensitive word identification result corresponding to the keyword set, and the manner specifically comprises:

[0049] Performing sensitive word identification on each keyword in the keyword set according to the sensitive word set, to obtain the first sub-identification result corresponding to the keyword set;

[0050] Determining keyword information of each keyword in the keyword set, and dividing the keyword set according to the keyword information of each keyword, to obtain at least two sub-keyword sets;

[0051] Determining semantic features corresponding to each sub-keyword set, and performing sensitive semantic identification on the semantic features corresponding to each sub-keyword set according to the sensitive word set, to obtain the second sub-identification result corresponding to the keyword set.

[0052] As an optional implementation, in the second aspect of the present application, the acquisition module determines the keyword information of each keyword in the keyword set in the following manner:

[0053] Determining target information of each keyword in the keyword set, wherein the target information comprises keyword frequency information and keyword meaning information;

[0054] According to the target information corresponding to each keyword, a keyword score corresponding to each keyword is calculated;

[0055] The string distance between each keyword in the keyword set is calculated;

[0056] According to the keyword score corresponding to each keyword and the string distance between each keyword, keyword information of each keyword is determined.

[0057] As an optional implementation, in the second aspect of the present application, the manner in which the acquisition module divides the keyword set according to the keyword information of each keyword to obtain at least two sub-keyword sets specifically includes:

[0058] A preset weight allocation rule is obtained, and according to the weight allocation rule, a keyword score weight corresponding to each keyword and a string distance weight between each keyword are determined;

[0059] According to the keyword score corresponding to each keyword and the keyword score weight, the string distance between each keyword and the string distance weight, an association parameter between each keyword is calculated;

[0060] According to a preset association parameter threshold and the association parameter between each keyword, the keyword set is divided to obtain at least two sub-keyword sets;

[0061] Each sub-keyword set includes at least two associated keywords, and the association parameter between each associated keyword in each sub-keyword set is greater than the association parameter threshold.

[0062] As an optional implementation, in the second aspect of the present application, the manner in which the acquisition module determines the semantic feature corresponding to each sub-keyword set specifically includes:

[0063] For each sub-keyword set, according to the keyword meaning of each associated keyword in the sub-keyword set, the expansion word information of each associated keyword in the sub-keyword set is determined, and the expansion word information includes synonym expansion word information and / or antonym expansion word information;

[0064] For each sub-keyword set, the context semantic information of each associated keyword in the sub-keyword set is determined;

[0065] For each sub-keyword set, a first coefficient corresponding to the expansion word information of each associated keyword in the sub-keyword set and a second coefficient corresponding to the context semantic information are determined;

[0066] For each of the sub-keyword set, randomly combine each of the associated keywords in the sub-keyword set to obtain at least one keyword combination, each of the keyword combination comprising at least two associated keywords;

[0067] For each of the sub-keyword set, for each of the keyword combination, determine a combined semantic feature corresponding to the keyword combination according to the expansion word information corresponding to the keyword combination, the first coefficient, the context semantic information and the second coefficient;

[0068] For each of the sub-keyword set, determine a semantic feature corresponding to the sub-keyword set according to the combined semantic feature corresponding to each of the keyword combination in the sub-keyword set.

[0069] As an optional implementation form, in the second aspect, the acquisition module is further configured to acquire a set of ignored words for the target game, and update the set of sensitive words according to the set of ignored words;

[0070] The acquisition module performs sensitive word identification on each keyword in the set of keywords according to the set of sensitive words to obtain the first sub-identification result corresponding to the set of keywords.

[0071] The acquisition module performs sensitive word identification on each keyword in the set of keywords according to the set of sensitive words to obtain the first sub-identification result corresponding to the set of keywords.

[0072] The acquisition module performs sensitive word identification on each keyword in the set of keywords according to the set of sensitive words to obtain the first sub-identification result corresponding to the set of keywords.

[0073] The acquisition module performs sensitive word identification on each keyword in the set of keywords according to the set of sensitive words to obtain the first sub-identification result corresponding to the set of keywords.

[0074] The acquisition module performs sensitive word identification on each keyword in the set of keywords according to the set of sensitive words to obtain the first sub-identification result corresponding to the set of keywords.

[0075] As an optional implementation form, in the second aspect, the text detection system further comprises:

[0076] The determination module is configured to determine feature information of each keyword in the set of keywords when the sensitive word identification result indicates that there is at least one target keyword in the set of keywords that matches the set of sensitive words, the feature information comprising attribute label features and / or fine-grained features.

[0077] a storage module, configured to store each of the keywords into a preset feature keyword library according to feature information of the keyword;

[0078] In addition, the text detection system further comprises:

[0079] a configuration module, configured to configure a sensitive word set based on the feature keyword library according to the sensitive word recognition range and the sensitive word configuration requirement when receiving the sensitive word recognition range and the sensitive word configuration requirement sent by the operation management end.

[0080] The third aspect of the present application discloses a text recognition device applied to a text detection system, and the device comprises:

[0081] a memory storing executable program codes;

[0082] a processor coupled with the memory;

[0083] The processor invokes the executable program codes stored in the memory to execute the text recognition method applied to the text detection system disclosed in the first aspect of the present application.

[0084] The fourth aspect of the present application discloses a computer storage medium storing computer instructions, and the computer instructions are used to execute the text recognition method applied to the text detection system disclosed in the first aspect of the present application when invoked.

[0085] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0086] In the embodiment of the present application, the text information of the target game can be obtained through the text detection system, the keyword set is extracted from the text information, the preset sensitive word set is obtained, the sensitive word recognition is performed on the keyword set according to the sensitive word set, the sensitive word recognition result corresponding to the keyword set is obtained, the sensitive word recognition result is analyzed, and when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set matching the sensitive word set, the text detection system generates the prompt information of each target keyword and sends the prompt information of each target keyword to the operation management end of the target game. It can be seen that the sensitive words in the game text can be recognized based on the text detection system, and the sensitive word prompt can be performed by implementing the present application, which improves the comprehensiveness and accuracy of recognizing sensitive information, reduces the probability of sensitive words appearing in the game text in the game development process, improves the health degree and safety of the game, reduces the game research and maintenance cost, reduces the probability of inappropriate remarks appearing when the players chat in the game, standardizes the chatting behavior of the players in the game, and improves the health of the game operation. BRIEF DESCRIPTION OF DRAWINGS

[0087] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and all other embodiments obtained by those of ordinary skill in the art without any creative work on the basis of these drawings are within the protection scope of the present application.

[0088] Figure 1 is a flow diagram of a text recognition method applied to a text detection system according to an embodiment of the present application;

[0089] Figure 2 is a structural diagram of a text detection system according to an embodiment of the present application;

[0090] Figure 3 is a flow diagram of another text recognition method applied to a text detection system according to an embodiment of the present application;

[0091] Figure 4 is a structural diagram of another text detection system according to an embodiment of the present application;

[0092] Figure 5 is a structural diagram of still another text detection system according to an embodiment of the present application;

[0093] Figure 6 is a structural diagram of a text recognition device applied to a text detection system according to an embodiment of the present application. DETAILED DESCRIPTION

[0094] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and all other embodiments obtained by those of ordinary skill in the art without any creative work on the basis of these drawings are within the protection scope of the present application.

[0095] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned accompanying drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or end.

[0096] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase that an "embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive or alternative embodiments. It is expressly understood that the embodiments described herein are merely example embodiments and that a substantial number of specific structures, features, configurations, materials, and components have been described in merely exemplary terms and are intended to be included in at least one embodiment of the application. A person skilled in the art will readily recognize from the disclosure herein, given wide deference, the application of the teachings, or the reasons that would result from the teaching to numerous applications and the scope of the application is not limited to the contents of the summary or the claims.

[0097] The application discloses a text recognition method applied to a text detection system and a text detection system.

[0098] Embodiment one

[0099] Please refer to Figure 1 , Figure 1 is a flowchart of a text recognition method applied to a text detection system according to an embodiment of the application. In the text recognition method, Figure 1 The text recognition method applied to the text detection system can be applied to the text detection system, which can include an intelligent server or an intelligent platform for keyword and / or sensitive word recognition and detection of text. The intelligent server includes a local server or a cloud server, and the embodiments of the application are not limited. As shown in Figure 1 The text recognition method applied to the text detection system can include the following operations:

[0100] 101. The text detection system obtains text information of a target game and extracts a keyword set from the text information.

[0101] In the embodiments of the application, optionally, the text detection system can be used to identify keywords or sensitive words in the text, as shown in Figure 2 Figure 2 is a structural diagram of a text detection system according to an embodiment of the application, wherein Figure 2 ​The shown text detection system can include a database layer, a service layer, a gateway layer, an access layer and an early warning layer from bottom to top, the database layer supports master-slave switching and cluster mode deployment, the service layer supports multi-node deployment and eliminates single point of failure, any server can continue to provide services when any server is down, the gateway layer supports Tencent load balancing CLB (Cloud Load Balancer), CLB automatically detects the health status of the connected server, and automatically switches after a certain server is down, the access layer supports a business fuse mechanism, and api timeout is automatically protected, so that even if the service is down, it will not affect the normal process of the game, and the early warning layer includes a complete early warning mechanism: word library failure, response delay, request QPS (Query Per Second), server load, code running exception, etc., to realize minute-level problem discovery and response exception.

[0102] In the embodiment of the application, optionally, the text information of the target game can include game content text information and / or user chat text information, the game content text information can include one or more of game plot text information, game system text information, game description text information, game tutorial text information, game achievement and / or reward text information, and game environment text information, the user chat text information can include chat text information between game players and / or game announcement text information, and extracting the keyword set from the text information can include one or more combinations of game character keywords, game environment keywords, game prop keywords, game task keywords, game plot keywords, and game player behavior keywords, which are not limited by the application.

[0103] 102. The text detection system obtains a preset sensitive word set and performs sensitive word recognition on the keyword set according to the sensitive word set to obtain a sensitive word recognition result corresponding to the keyword set.

[0104] In the embodiment of the application, optionally, the preset sensitive word set can be configured by the game manager on the operation and management end, or the game manager can set a sensitive word condition on the operation and management end and then configure the sensitive word condition in the text detection system according to the sensitive word condition, or the game manager can configure the sensitive word set based on a national sensitive word library on the operation and management end, which is not limited by the application.

[0105] 103. The text detection system analyzes the sensitive word recognition result, and when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates prompt information for each target keyword and sends the prompt information for each target keyword to the operation and management end of the target game.

[0106] In the embodiment of the application, optionally, when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates prompt information of each target keyword, the target keyword being a sensitive word, and the prompt information of each target keyword can include the sensitive word type and the severity corresponding to the target keyword, which is not limited by the application.

[0107] It can be seen that the implementation Figure 1 The described text recognition method applied to the text detection system can obtain text information of a target game through the text detection system, extract a keyword set from the text information, obtain a preset sensitive word set, perform sensitive word recognition on the keyword set according to the sensitive word set, obtain a sensitive word recognition result corresponding to the keyword set, analyze the sensitive word recognition result, and when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates prompt information of each target keyword and sends the prompt information of each target keyword to an operation and management end of the target game. The text detection system can recognize sensitive words in game text and remind sensitive words based on the text detection system, improve the comprehensiveness and accuracy of recognizing sensitive information, reduce the probability of sensitive words appearing in game text during game development, improve the health and safety of the game, reduce the cost of game research and development and maintenance, reduce the probability of inappropriate remarks appearing when players chat in the game, standardize the chat behavior of players in the game, and improve the health of game operation.

[0108] In an optional embodiment, the prompt information of each target keyword includes the sensitive word type and the severity corresponding to the target keyword.

[0109] The text recognition method applied to the text detection system can further include the following operations:

[0110] For each target keyword, the operation and management end determines the processing urgency of the target keyword according to the prompt information of the target keyword.

[0111] For each target keyword, the operation and management end determines the original text corresponding to the target keyword, the original text including game content text or user chat text.

[0112] For each target keyword, when the original text corresponding to the target keyword includes game content text, the operation and management end performs a game text processing operation on the target keyword according to the prompt information and the processing urgency of the target keyword.

[0113] For each target keyword, when the original text corresponding to the target keyword includes user chat text, the operation management end determines user information of a game user corresponding to the target keyword, and determines a game specification processing operation for the game user according to the prompt information of the target keyword, the processing urgency of the target keyword, and the user information, and performs a user text operation on the target keyword.

[0114] In the optional embodiment, optionally, the prompt information of each target keyword can include a sensitive word type and a severity corresponding to the target keyword, and the processing urgency of the target keyword can represent a processing priority of the target keyword, and the embodiment is not limited.

[0115] In the optional embodiment, optionally, when the original text corresponding to the target keyword includes game content text, the operation management end can perform a game text processing operation on the target keyword according to the prompt information and the processing urgency of the target keyword, and the game text processing operation can include one or more of deleting, modifying, and shielding the target keyword, when the original text corresponding to the target keyword includes user chat text, the game specification processing operation for the game user can include one or more of prompting, warning, or banning the game user, when the game user has not sent the target keyword, the user text operation on the target keyword can include prohibiting the game user from sending the target keyword, and when the game user has sent the target keyword, the user text operation on the target keyword can include a symbol replacement operation on the target keyword, and the embodiment is not limited.

[0116] It can be seen that by implementing the optional embodiment, the operation management end can determine the processing urgency of the target keyword according to the prompt information of the target keyword, process the target keyword according to the original text corresponding to the target keyword, process the game user according to the game specification, improve the efficiency of the sensitive word early warning processing, reduce the probability of inappropriate remarks appearing in the game player chat, standardize the chat behavior of the game player, and improve the health of the game operation.

[0117] Embodiment Two

[0118] Please refer to Figure 3 , Figure 3 is a flowchart of a text recognition method applied to a text detection system according to an embodiment of the present application. In the flowchart, Figure 3 The text recognition method applied to the text detection system described can be applied to a text detection system, which can include an intelligent server or an intelligent platform for keyword and / or sensitive word recognition and detection of text, and the intelligent server includes a local server or a cloud server, and the embodiment of the present application is not limited. For example,Figure 3 As shown, the text recognition method applied to the text detection system can include the following operations:

[0119] 201. The text detection system obtains text information of a target game and extracts a keyword set from the text information.

[0120] 202. The text detection system obtains a preset sensitive word set, and performs sensitive word recognition on each keyword in the keyword set according to the sensitive word set to obtain a first sub-recognition result corresponding to the keyword set.

[0121] In the embodiments of the present application, optionally, the first sub-recognition result corresponding to the keyword set can include the target keywords in the keyword set that are the same as those in the sensitive word set, that is, the text detection system performs individual comparison and recognition on each keyword in the keyword set according to the sensitive word set, which is not limited by the present application.

[0122] 203. The text detection system determines keyword information of each keyword in the keyword set, and divides the keyword set according to the keyword information of each keyword to obtain at least two sub-keyword sets.

[0123] In the embodiments of the present application, optionally, the keyword information of each keyword in the keyword set can include keyword semantic information, keyword score and string distance between each keyword, and the keyword set can be divided according to the keyword information of each keyword to obtain at least two sub-keyword sets, each sub-keyword set including a plurality of keywords, and the string distance between each keyword in the same sub-keyword set being less than a preset string distance threshold, that is, each keyword in the same sub-keyword set can be a keyword in the same sentence or a keyword in the same paragraph.

[0124] 204. The text detection system determines semantic features corresponding to each sub-keyword set, and performs sensitive semantic recognition on the semantic features corresponding to each sub-keyword set according to the sensitive word set to obtain a second sub-recognition result corresponding to the keyword set.

[0125] In the embodiment of the present application, optionally, the semantic feature corresponding to each sub-keyword set can represent the semantic feature of a combined word obtained by randomly combining the multiple keywords in each sub-keyword set. The sensitive semantic recognition is performed on the semantic feature corresponding to each sub-keyword set according to the sensitive word set, that is, it is judged whether the semantic feature of the combined word obtained by randomly combining the multiple keywords in each sub-keyword set expresses sensitive semantics, that is, it is possible that two or more keywords are not sensitive words themselves, but the semantics expressed when the two or more keywords are combined can be sensitive semantics. A second sub-recognition result corresponding to the keyword set is obtained, and the present application is not limited thereto.

[0126] 205. The text detection system analyzes the sensitive word recognition result. When the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates prompt information for each target keyword and sends the prompt information for each target keyword to the operation and management end of the target game.

[0127] In the embodiment of the present application, for other descriptions of steps 201 and 205, please refer to the detailed description of steps 101 and 103 in Embodiment 1, and the present application will not be repeated here.

[0128] It can be seen that the implementation Figure 3The text recognition method for the text detection system described can obtain text information of a target game through the text detection system, extract a keyword set from the text information, obtain a preset sensitive word set, perform sensitive word recognition on each keyword in the keyword set according to the sensitive word set, obtain a first sub-recognition result corresponding to the keyword set, determine keyword information of each keyword in the keyword set, divide the keyword set according to the keyword information of each keyword, obtain at least two sub-keyword sets, determine semantic features corresponding to each sub-keyword set, perform sensitive semantic recognition on the semantic features corresponding to each sub-keyword set according to the sensitive word set, and obtain a second sub-recognition result corresponding to the keyword set. The text recognition method can perform sensitive recognition on each keyword in the text one by one and sensitive semantic recognition on the combined keywords, improve the comprehensiveness and accuracy of sensitive word recognition, analyze the sensitive word recognition result, and when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates prompt information of each target keyword and sends the prompt information of each target keyword to an operation and management end of the target game. The text detection system can recognize sensitive words in game text based on the text detection system and provide a sensitive word reminder, improve the comprehensiveness and accuracy of sensitive information recognition, reduce the probability of sensitive words appearing in game text during game development, improve the health and safety of games, reduce the probability of inappropriate remarks appearing when players chat in games, regulate the chat behavior of players in games, and improve the health of game operation.

[0129] In an optional embodiment, the text detection system determining keyword information of each keyword in the keyword set can include the following operations:

[0130] The text detection system determines target information of each keyword in the keyword set, and the target information includes keyword frequency information and keyword semantic information.

[0131] The text detection system calculates a keyword score corresponding to each keyword according to the target information corresponding to each keyword.

[0132] The text detection system calculates a string distance between each keyword in the keyword set.

[0133] The text detection system determines keyword information of each keyword according to the keyword score corresponding to each keyword and the string distance between each keyword.

[0134] In the optional embodiment, the target information of each keyword in the keyword set can include keyword frequency information and keyword semantic information, the sensitivity level of the keyword can be determined according to the keyword semantic information of the keyword, and then the keyword score of the keyword can be calculated according to the keyword frequency information of the keyword, the sensitivity level of the keyword, and a preset formula. Optionally, the higher the keyword frequency of the keyword is, the higher the keyword score of the keyword can be. The present embodiment is not limited.

[0135] In the optional embodiment, the text detection system can calculate the string distance between each keyword in the keyword set. The string distance between the keywords can reflect the semantic association degree between the keywords. When the string distance between a plurality of keywords is less than a preset string distance threshold, it can be indicated that the plurality of keywords are in the same sentence or the same paragraph, that is, the probability that the plurality of keywords are in the same context is relatively large. The plurality of keywords can be combined to determine the semantic feature of the plurality of keywords after combination. When the string distance between a plurality of keywords is greater than a preset string distance threshold, the distance between the context before and after the plurality of keywords in the text is relatively large, that is, the probability that the plurality of keywords are in different contexts is relatively large. At this time, the semantic feature of the plurality of keywords after combination determined by combination is relatively large probability not in line with semantic logic. At this time, the semantic association degree between the keywords can be ignored. The present embodiment is not limited.

[0136] It can be seen that implementing the optional embodiment can determine the target information of each keyword in the keyword set, calculate the keyword score corresponding to each keyword according to the target information corresponding to each keyword, calculate the string distance between each keyword in the keyword set, and determine the keyword information of each keyword according to the keyword score corresponding to each keyword and the string distance between each keyword. The keyword information can be determined through the keyword score and the string distance, the determination accuracy of the keyword information is improved, and the rationality of dividing the keyword set through the keyword information is improved.

[0137] In another optional embodiment, the text detection system divides the keyword set according to the keyword information of each keyword to obtain at least two sub-keyword sets, which can include the following operations:

[0138] The text detection system obtains a preset weight allocation rule, and determines the keyword score weight corresponding to each keyword and the string distance weight between each keyword according to the weight allocation rule;

[0139] The text detection system calculates the association parameter between each keyword according to the keyword score corresponding to each keyword, the keyword score weight, the string distance between each keyword, and the string distance weight.

[0140] The text detection system divides the keyword set according to the preset correlation parameter threshold and the correlation parameter between each keyword, and obtains at least two sub-keyword sets;

[0141] Each sub-keyword set includes at least two associated keywords, and the correlation parameter between each associated keyword in each sub-keyword set is greater than the correlation parameter threshold.

[0142] In the optional embodiment, the keyword score weight corresponding to each keyword and the string distance weight between each keyword can be determined according to the weight distribution rule, and the correlation parameter between each keyword can be calculated according to the keyword score corresponding to each keyword, the keyword score weight, the string distance between each keyword, and the string distance weight.

[0143] In the optional embodiment, when calculating the correlation parameter between each keyword, the matching degree between the keyword scores corresponding to each keyword can be calculated, for example, the higher the matching degree between the keyword scores corresponding to two keywords, the higher the semantic matching degree and the word frequency matching degree between the two keywords; it is determined whether the string distance between each keyword is less than the preset string distance threshold, for example, the string distance between two keywords is less than the preset string distance threshold, the correlation degree of the two keywords is higher, and then the correlation parameter between each keyword is calculated according to the matching degree between the keyword scores corresponding to each keyword and whether the string distance between each keyword is less than the preset string distance threshold. In the text detection system, the string distance weight between each keyword can be much greater than the keyword score weight, that is, the influence degree of the string distance between each keyword on the correlation parameter between each keyword is greater, and this embodiment is not limited.

[0144] In the optional embodiment, the keyword set can be divided according to the preset correlation parameter threshold and the correlation parameter between each keyword to obtain at least two sub-keyword sets, each sub-keyword set includes at least two associated keywords, and the correlation parameter between each associated keyword in each sub-keyword set is greater than the correlation parameter threshold, that is, each associated keyword in the same sub-keyword set can be randomly combined to determine the combined semantic feature, and this embodiment is not limited.

[0145] It can be seen that the optional embodiment can calculate the association parameters between each keyword based on the keyword scores and the string distance, and then divide the keywords with the association parameters greater than the association parameter threshold into the same sub-keyword set, thereby improving the association degree of each associated keyword in the keyword set in terms of semantics and context text information, improving the rationality of combining each associated keyword in the keyword set, and further improving the rationality and accuracy of sensitive semantic recognition through the semantic features corresponding to each sub-keyword set.

[0146] In yet another optional embodiment, the text detection system determining the semantic features corresponding to each sub-keyword set can include the following operations:

[0147] For each sub-keyword set, the text detection system determines the expansion word information of each associated keyword in the sub-keyword set according to the keyword meaning of each associated keyword in the sub-keyword set, and the expansion word information includes the synonym expansion word information and / or the antonym expansion word information.

[0148] For each sub-keyword set, the text detection system determines the context semantic information of each associated keyword in the sub-keyword set.

[0149] For each sub-keyword set, the text detection system determines the first coefficient corresponding to the expansion word information of each associated keyword in the sub-keyword set and the second coefficient corresponding to the context semantic information.

[0150] For each sub-keyword set, the text detection system randomly combines each associated keyword in the sub-keyword set to obtain at least one keyword combination, and each keyword combination includes at least two associated keywords.

[0151] For each sub-keyword set, for each keyword combination, the text detection system determines the combination semantic features corresponding to the keyword combination according to the expansion word information, the first coefficient, the context semantic information, and the second coefficient corresponding to the keyword combination.

[0152] For each sub-keyword set, the text detection system determines the semantic features corresponding to the sub-keyword set according to the combination semantic features corresponding to each keyword combination in the sub-keyword set.

[0153] In the optional embodiment, optionally, the expansion word information of each associated keyword in the sub-keyword set can include synonym expansion word information and / or antonym expansion word information, that is, the synonym semantics and / or the antonym semantics of the associated keyword in the current context are determined, the text detection system determines the first coefficient corresponding to the expansion word information of each associated keyword in the sub-keyword set and the second coefficient corresponding to the context semantic information, and in the text detection system, the second coefficient corresponding to the context semantic information is greater than the first coefficient corresponding to the expansion word information, that is, the influence of the context semantic information of the associated keyword on the combined semantic feature is greater than the influence of the expansion word information, for example, when the game user sends "You are really amazing!" in the game, it may express praise to the teammates or opponents, but when the context semantic information indicates that the teammates or opponents are at a disadvantage or the game is lost in the game, it may express ridicule or blame.

[0154] In the optional embodiment, optionally, the text detection system randomly combines each associated keyword in the sub-keyword set to obtain at least one keyword combination, each keyword combination can include at least two associated keywords, for each keyword combination, the text detection system determines the combined semantic feature corresponding to the keyword combination according to the expansion word information, the first coefficient, the context semantic information and the second coefficient corresponding to the keyword combination, and for each sub-keyword set, the text detection system determines the semantic feature corresponding to the sub-keyword set according to the combined semantic feature corresponding to each keyword combination in the sub-keyword set, that is, the semantic feature corresponding to the sub-keyword set can include a plurality of combined semantic features, and this embodiment is not limited.

[0155] It can be seen that by implementing the optional embodiment, the combined semantic feature corresponding to the keyword combination can be determined by combining the expansion word information and the context semantic information of the associated keyword in the process of determining the semantic feature corresponding to each sub-keyword set by the text detection system, the semantics and the context are comprehensively considered, and the accuracy and rationality of the determined combined semantic feature are improved.

[0156] In yet another optional embodiment, the text recognition method applied to the text detection system can further include the following operations:

[0157] The text detection system obtains an ignored word set for the target game, and updates the sensitive word set according to the ignored word set;

[0158] In addition, the text detection system performs sensitive word recognition on each keyword in the keyword set according to the sensitive word set to obtain a first sub-recognition result corresponding to the keyword set, which can include the following operations:

[0159] The text detection system performs sensitive word identification on the keyword set according to the sensitive word set and the ignored word set, to obtain a first target identification result corresponding to the keyword set;

[0160] The text detection system screens a relevant word set corresponding to the first target identification result from the keyword set, the relevant word set including at least one of a synonym, a synonym, and an antonym corresponding to the first target identification result;

[0161] The text detection system performs sensitive word identification on the relevant word set according to the sensitive word set and the ignored word set, to obtain a second target identification result corresponding to the keyword set;

[0162] The text detection system determines a first sub-identification result corresponding to the keyword set according to the first target identification result and the second target identification result.

[0163] In this optional embodiment, optionally, the ignored word set for the target game can be configured by the game manager according to the requirements of the target game on the operation and management side, and the keyword set can be compared and identified one by one according to the sensitive word set and the ignored word set to obtain a first target identification result corresponding to the keyword set. When the first target identification result indicates that the keyword set includes at least one first sub-target keyword matching the sensitive word set and the ignored word set, a relevant word set corresponding to the first target identification result can be screened from the keyword set. The relevant word set can include at least one of a synonym, a synonym, and an antonym corresponding to the first target identification result, i.e., a synonym, a synonym, and / or an antonym corresponding to each first sub-target keyword in the keyword set is screened to obtain the relevant word set. This embodiment is not limited.

[0164] In this optional embodiment, optionally, the keyword set is identified according to the sensitive word set and the ignored word set to obtain a second target identification result corresponding to the keyword set, i.e., a second sub-target keyword in the relevant word set is identified in the sensitive word set and the ignored word set. For example, when the first target identification result indicates that word A in the keyword set is a sensitive word or an ignored word in the sensitive word set and the ignored word set, the synonym, synonym, and / or antonym corresponding to word A in the keyword set is screened to obtain the relevant word set, such as word B, word C, and word D. The sensitive word set and the ignored word set are identified according to the relevant word set to obtain a second target identification result corresponding to the keyword set. When the second target identification result indicates that word B and word D in the relevant word set are sensitive words or ignored words in the sensitive word set and the ignored word set, it is determined that the first sub-identification result corresponding to the keyword set includes word A, word B, and word D. This embodiment is not limited.

[0165] It can be seen that the optional embodiment can obtain the ignored word set for the target game, update the sensitive word set according to the ignored word set, perform sensitive word identification on the keyword set according to the sensitive word set and the ignored word set, and further identify according to the related word set of the sensitive word identification result, thereby improving the accuracy and comprehensiveness of the sensitive word identification, reducing the probability of the sensitive word appearing in the game text during the game development process, improving the health degree and safety of the game, reducing the probability of inappropriate remarks appearing when the players chat in the game, standardizing the chat behavior of the players in the game, and improving the health of the game operation.

[0166] In yet another optional embodiment, when the sensitive word identification result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text recognition method applied to the text detection system can further include the following operations:

[0167] The text detection system determines the feature information of each keyword in the keyword set, and the feature information includes attribute label features and / or fine-grained features.

[0168] For each keyword, the text detection system stores the keyword in the preset feature library according to the feature information of the keyword.

[0169] In addition, the text recognition method applied to the text detection system can further include the following operations:

[0170] When the text detection system receives the sensitive word identification range and the sensitive word configuration requirement sent by the operation and management end, the text detection system configures the sensitive word set based on the feature library according to the sensitive word identification range and the sensitive word configuration requirement.

[0171] In the optional embodiment, the feature information of each keyword in the keyword set can include attribute label features and / or fine-grained features, and the keyword can be stored in the preset feature library according to the feature information of the keyword. The feature library is constantly updated and improved with each new text recognition process, and gradually accumulates more abundant and comprehensive vocabulary and feature information.

[0172] In the optional embodiment, optionally, the game manager can set a sensitive word recognition range and a sensitive word configuration requirement on the operation management end. The sensitive word recognition range can include global recognition and / or local recognition. For example, sensitive word recognition can be performed only on game text during game development or updating, and sensitive word recognition can be performed only on game user chat text after the game is put into operation. The sensitive word configuration requirement can include a sensitive word content requirement and / or a sensitive word action range requirement. The sensitive word action range requirement can represent that the recognition range of certain special sensitive words is limited, for example, global recognition or only in a certain text part. When the text detection system receives the sensitive word recognition range and the sensitive word configuration requirement sent by the operation management end, the text detection system configures a sensitive word set based on the feature word library according to the sensitive word recognition range and the sensitive word configuration requirement. This embodiment is not limited.

[0173] It can be seen that by implementing the optional embodiment, the feature information of each keyword in the keyword set can be determined, and the keyword is classified and stored in the preset feature word library according to the feature information of the keyword. The feature word library is continuously updated and improved with each new text recognition processing, and more abundant and comprehensive vocabulary and feature information are gradually accumulated, forming a self-learning closed loop, improving the sensitive word recognition and classification capability, and continuously improving the sensitive word recognition accuracy and efficiency. When the text detection system receives the sensitive word recognition range and the sensitive word configuration requirement sent by the operation management end, the text detection system configures a sensitive word set based on the feature word library according to the sensitive word recognition range and the sensitive word configuration requirement, which can realize the game manager to customize the sensitive word content and the recognition range, improve the flexibility of sensitive word recognition, and improve the user experience.

[0174] Embodiment three

[0175] Please refer to Figure 4 , Figure 4 is a structural schematic diagram of a text detection system disclosed by the embodiment of the application. Wherein, Figure 4 The text detection system described can include an intelligent server or an intelligent platform for keyword and / or sensitive word recognition detection of text. The intelligent server includes a local server or a cloud server, and the embodiment of the application does not limit it. As Figure 4 indicated, the text detection system can include:

[0176] The acquisition module 301 is configured to acquire text information of a target game and extract a keyword set from the text information. The text information includes game content text information and / or user chat text information.

[0177] The acquisition module 301 is further configured to acquire a preset sensitive word set and perform sensitive word recognition on the keyword set according to the sensitive word set to obtain a sensitive word recognition result corresponding to the keyword set.

[0178] The analysis module 302 is configured to analyze the sensitive word recognition result, generate prompt information of each target keyword when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set matching the sensitive word set, and send the prompt information of each target keyword to the operation and management end of the target game.

[0179] It can be seen that the implementation Figure 4 The text detection system described can obtain text information of a target game through the text detection system, extract a keyword set from the text information, obtain a preset sensitive word set, perform sensitive word recognition on the keyword set according to the sensitive word set, obtain a sensitive word recognition result corresponding to the keyword set, analyze the sensitive word recognition result, generate prompt information of each target keyword when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set matching the sensitive word set, and send the prompt information of each target keyword to the operation and management end of the target game. Based on the text detection system, sensitive words in the game text can be recognized and reminded, the comprehensiveness and accuracy of recognizing sensitive information are improved, the probability of sensitive words appearing in the game text during game development is reduced, the health and safety of the game are improved, the game development and maintenance costs are reduced, the probability of inappropriate remarks appearing when players chat in the game is reduced, the chatting behavior of players in the game is standardized, and the health of game operation is improved.

[0180] In an optional embodiment, as Figure 5 The sensitive word recognition result includes a first sub-recognition result and a second sub-recognition result.

[0181] The specific manner in which the obtaining module 301 performs sensitive word recognition on the keyword set according to the sensitive word set to obtain a sensitive word recognition result corresponding to the keyword set includes:

[0182] Performing sensitive word recognition on each keyword in the keyword set according to the sensitive word set to obtain a first sub-recognition result corresponding to the keyword set.

[0183] Determining keyword information of each keyword in the keyword set, and dividing the keyword set according to the keyword information of each keyword to obtain at least two sub-keyword sets.

[0184] Determining a semantic feature corresponding to each sub-keyword set, and performing sensitive semantic recognition on the semantic feature corresponding to each sub-keyword set according to the sensitive word set to obtain a second sub-recognition result corresponding to the keyword set.

[0185] It can be seen that the implementation Figure 5The described text detection system can obtain text information of a target game through the text detection system, extract a keyword set from the text information, obtain a preset sensitive word set, perform sensitive word recognition on each keyword in the keyword set according to the sensitive word set, obtain a first sub-recognition result corresponding to the keyword set, determine keyword information of each keyword in the keyword set, divide the keyword set according to the keyword information of each keyword, obtain at least two sub-keyword sets, determine semantic features corresponding to each sub-keyword set, and perform sensitive semantic recognition on the semantic features corresponding to each sub-keyword set according to the sensitive word set, to obtain a second sub-recognition result corresponding to the keyword set. The text detection system can perform sensitive recognition on each keyword in the text one by one and perform semantic sensitive recognition after combination, improve the comprehensiveness and accuracy of sensitive word recognition, analyze the sensitive word recognition result, and when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates prompt information of each target keyword and sends the prompt information of each target keyword to an operation and management end of the target game. The text detection system can identify sensitive words in game text based on the text detection system and provide a sensitive word reminder, improve the comprehensiveness and accuracy of sensitive information identification, reduce the probability of sensitive words appearing in game text during game development, improve the health and safety of the game, reduce the probability of inappropriate remarks appearing when players chat in the game, standardize the chat behavior of players in the game, and improve the health of game operation.

[0186] In another optional embodiment, as shown in Figure 5 The specific manner in which the obtaining module 301 determines the keyword information of each keyword in the keyword set includes:

[0187] Determine target information of each keyword in the keyword set, and the target information includes keyword frequency information and keyword semantic information;

[0188] According to the target information corresponding to each keyword, calculate a keyword score corresponding to each keyword;

[0189] Calculate the string distance between each keyword in the keyword set;

[0190] According to the keyword score corresponding to each keyword and the string distance between each keyword, determine the keyword information of each keyword.

[0191] It can be seen that the implementation Figure 5The text detection system described can determine target information of each keyword in the keyword set, calculate a keyword score corresponding to each keyword according to the target information corresponding to each keyword, calculate a string distance between each keyword in the keyword set, determine keyword information of each keyword according to the keyword score corresponding to each keyword and the string distance between each keyword, determine the keyword information through the keyword score and the string distance, improve the determination accuracy of the keyword information, and improve the rationality of dividing the keyword set through the keyword information.

[0192] In yet another optional embodiment, as shown in Figure 5 The specific manner in which the obtaining module 301 divides the keyword set according to the keyword information of each keyword to obtain at least two sub-keyword sets includes:

[0193] obtaining a preset weight allocation rule, and determining a keyword score weight corresponding to each keyword and a string distance weight between each keyword according to the weight allocation rule;

[0194] calculating an association parameter between each keyword according to the keyword score corresponding to each keyword and the keyword score weight, the string distance between each keyword and the string distance weight;

[0195] dividing the keyword set according to the preset association parameter threshold and the association parameter between each keyword to obtain at least two sub-keyword sets;

[0196] Each sub-keyword set includes at least two associated keywords, and the association parameter between each associated keyword in each sub-keyword set is greater than the association parameter threshold.

[0197] It can be seen that the implementation Figure 5 The text detection system described can calculate an association parameter between each keyword based on a keyword score and a string distance, then divide keywords with an association parameter greater than an association parameter threshold into the same sub-keyword set, improve the association degree of each associated keyword in the keyword set in terms of semantic and contextual text information, improve the rationality of combining each associated keyword in the keyword set, and further improve the rationality and accuracy of sensitive semantic recognition through the semantic features corresponding to each sub-keyword set.

[0198] In yet another optional embodiment, as shown in Figure 5 The specific manner in which the obtaining module 301 determines the semantic features corresponding to each sub-keyword set includes:

[0199] For each sub-keyword set, according to the keyword meaning of each associated keyword in the sub-keyword set, determine the expansion word information of each associated keyword in the sub-keyword set, and the expansion word information includes synonym expansion word information and / or antonym expansion word information;

[0200] For each sub-keyword set, determine the context semantic information of each associated keyword in the sub-keyword set;

[0201] For each sub-keyword set, determine the first coefficient corresponding to the expansion word information of each associated keyword in the sub-keyword set and the second coefficient corresponding to the context semantic information;

[0202] For each sub-keyword set, randomly combine each associated keyword in the sub-keyword set to obtain at least one keyword combination, and each keyword combination includes at least two associated keywords;

[0203] For each sub-keyword set, for each keyword combination, according to the expansion word information, the first coefficient, the context semantic information and the second coefficient corresponding to the keyword combination, determine the combination semantic feature corresponding to the keyword combination;

[0204] For each sub-keyword set, according to the combination semantic feature corresponding to each keyword combination in the sub-keyword set, determine the semantic feature corresponding to the sub-keyword set.

[0205] It can be seen that the implementation Figure 5 The text detection system described can determine the combination semantic feature corresponding to the keyword combination by combining the expansion word information and the context semantic information of the associated keyword in the process of determining the semantic feature corresponding to each sub-keyword set by the text detection system, comprehensively consider the semantics and context, and improve the accuracy and rationality of the determined combination semantic feature.

[0206] In yet another optional embodiment, as Figure 5 The acquisition module 301 is also used to acquire an ignored word set for the target game, and update the sensitive word set according to the ignored word set;

[0207] In addition, the specific manner in which the acquisition module 301 performs sensitive word identification on each keyword in the keyword set according to the sensitive word set to obtain the first sub-identification result corresponding to the keyword set includes:

[0208] According to the sensitive word set and the ignored word set, the sensitive word identification is performed on the keyword set to obtain the first target identification result corresponding to the keyword set;

[0209] screening the relevant word set corresponding to the first target recognition result in the keyword set, the relevant word set including at least one of the near-synonyms, synonyms and antonyms corresponding to the first target recognition result;

[0210] performing sensitive word recognition on the relevant word set according to the sensitive word set and the ignored word set to obtain a second target recognition result corresponding to the keyword set;

[0211] determining a first sub-recognition result corresponding to the keyword set according to the first target recognition result and the second target recognition result.

[0212] It can be seen that, in the implementation Figure 5 The described text detection system can obtain an ignored word set for a target game, update a sensitive word set according to the ignored word set, perform sensitive word recognition on a keyword set according to the sensitive word set and the ignored word set, and further recognize according to a relevant word set of the sensitive word recognition result, thereby improving the accuracy and comprehensiveness of the sensitive word recognition, reducing the probability of the occurrence of sensitive words in the game text during the game development process, improving the health degree and safety of the game, reducing the probability of the occurrence of inappropriate remarks during the chat of players in the game, standardizing the chat behavior of the players in the game, and improving the health of the game operation.

[0213] In yet another optional embodiment, as Figure 5 shown, the text detection system can further include:

[0214] The determination module 303 is configured to determine feature information of each keyword in the keyword set when the sensitive word recognition result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the feature information including attribute label features and / or fine-grained features;

[0215] The storage module 304 is configured to, for each keyword, store the keyword in a pre-set feature word library according to the feature information of the keyword;

[0216] In addition, the text detection system can further include:

[0217] The configuration module 305 is configured to, when receiving the sensitive word recognition range and the sensitive word configuration requirement sent by the operation and management end, configure the sensitive word set based on the feature word library according to the sensitive word recognition range and the sensitive word configuration requirement.

[0218] It can be seen that, in the implementation Figure 6The described text detection system can determine the feature information of each keyword in the keyword set, store the keyword in the preset feature library according to the feature information of the keyword, and continuously update and improve the feature library with each new text recognition processing, gradually accumulate more rich and comprehensive vocabulary and feature information, form a self-learning closed loop, improve the sensitive word recognition and classification ability, and continuously improve the sensitive word recognition accuracy and efficiency; when the text detection system receives the sensitive word recognition range and the sensitive word configuration requirement sent by the operation management end, the text detection system configures the sensitive word set based on the feature library according to the sensitive word recognition range and the sensitive word configuration requirement, can realize that the game manager customizes the sensitive word content and the recognition range, improves the flexibility of sensitive word recognition, and improves the user experience.

[0219] Embodiment four

[0220] Please refer to Figure 6 , Figure 6 is a structural schematic view of a text recognition device applied to a text detection system according to an embodiment of the present application. As shown in ​ , the text recognition device applied to the text detection system can include:

[0221] a memory 401 storing executable program codes;

[0222] a processor 402 coupled with the memory 401;

[0223] The processor 402 invokes the executable program codes stored in the memory 401 to execute the steps of the text recognition method applied to the text detection system described in the embodiment one or the embodiment two of the present application.

[0224] Embodiment five

[0225] The embodiment of the present application discloses a computer storage medium, which stores computer instructions, and the computer instructions are used to execute the steps of the text recognition method applied to the text detection system described in the embodiment one or the embodiment two of the present application when being invoked.

[0226] Embodiment six

[0227] The embodiment of the present application discloses a computer program product, which includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to make a computer execute the steps of the text recognition method applied to the text detection system described in the embodiment one or the embodiment two.

[0228] The apparatus embodiments described above are only illustrative, wherein the modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, i.e., can be located in one place or distributed to multiple network modules. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0229] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage, a magnetic tape storage, or any other computer readable medium that can be used to carry or store data.

[0230] Finally, it should be noted that: the text recognition method applied to the text detection system and the text detection system disclosed by the embodiments of the present application are only the preferred embodiments of the present application, and are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that; it can still modify the technical solutions recorded in the foregoing embodiments, or replace some technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A text recognition method applied to a text detection system, characterized in that, The method comprises: The text detection system obtains text information of a target game, and extracts a keyword set from the text information, wherein the text information comprises game content text information and / or user chat text information; The text detection system obtains a preset sensitive word set, and performs sensitive word identification on the keyword set according to the sensitive word set to obtain a sensitive word identification result corresponding to the keyword set; The text detection system analyzes the sensitive word identification result, and when the sensitive word identification result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the text detection system generates prompt information of each target keyword and sends the prompt information of each target keyword to an operation and management end of the target game; In addition, the sensitive word identification result comprises a first sub-identification result and a second sub-identification result; The text detection system performs sensitive word identification on the keyword set according to the sensitive word set to obtain a sensitive word identification result corresponding to the keyword set, which comprises: The text detection system performs sensitive word identification on each keyword in the keyword set according to the sensitive word set to obtain the first sub-identification result corresponding to the keyword set; The text detection system determines keyword information of each keyword in the keyword set, and divides the keyword set according to the keyword information of each keyword to obtain at least two sub-keyword sets; The text detection system determines semantic features corresponding to each sub-keyword set, and performs sensitive semantic identification on the semantic features corresponding to each sub-keyword set according to the sensitive word set to obtain the second sub-identification result corresponding to the keyword set; In addition, the text detection system determines keyword information of each keyword in the keyword set, which comprises: The text detection system determines target information of each keyword in the keyword set, wherein the target information comprises keyword frequency information and keyword meaning information; The text detection system calculates keyword scores corresponding to each keyword according to the target information corresponding to each keyword; The text detection system calculates string distances between each keyword in the keyword set; The text detection system determines keyword information of each keyword according to the keyword scores corresponding to each keyword and the string distances between each keyword.

2. The text recognition method for a text detection system according to claim 1, wherein, The text detection system divides the keyword set according to the keyword information of each keyword to obtain at least two sub-keyword sets, which comprises: The text detection system obtains a preset weight allocation rule, and determines keyword score weights corresponding to each keyword and string distance weights between each keyword according to the weight allocation rule; The text detection system calculates an association parameter between each of the keywords according to the keyword score corresponding to each of the keywords, the keyword score weight, a string distance between each of the keywords, and the string distance weight; The text detection system divides the keyword set according to a preset association parameter threshold and the association parameter between each of the keywords, to obtain at least two sub-keyword sets; Each of the sub-keyword sets includes at least two associated keywords, and the association parameter between each of the associated keywords in each of the sub-keyword sets is greater than the association parameter threshold.

3. The text recognition method for a text detection system according to claim 1 or 2, wherein, The text detection system determines a semantic feature corresponding to each of the sub-keyword sets, including: For each of the sub-keyword sets, the text detection system determines expansion word information of each of the associated keywords in the sub-keyword set according to the keyword meaning of each of the associated keywords in the sub-keyword set, the expansion word information including synonym expansion word information and / or antonym expansion word information; For each of the sub-keyword sets, the text detection system determines context semantic information of each of the associated keywords in the sub-keyword set; For each of the sub-keyword sets, the text detection system determines a first coefficient corresponding to the expansion word information of each of the associated keywords in the sub-keyword set and a second coefficient corresponding to the context semantic information; For each of the sub-keyword sets, the text detection system randomly combines each of the associated keywords in the sub-keyword set to obtain at least one keyword combination, each of the keyword combinations including at least two of the associated keywords; For each of the sub-keyword sets, for each of the keyword combinations, the text detection system determines a combination semantic feature corresponding to the keyword combination according to the expansion word information, the first coefficient, the context semantic information, and the second coefficient corresponding to the keyword combination; For each of the sub-keyword sets, the text detection system determines a semantic feature corresponding to the sub-keyword set according to the combination semantic feature corresponding to each of the keyword combinations in the sub-keyword set.

4. The text recognition method for a text detection system according to claim 1 or 2, wherein, The method further includes: The text detection system acquires a set of ignored words for the target game, and updates the set of sensitive words according to the set of ignored words; And the text detection system performs sensitive word identification on each keyword in the keyword set according to the set of sensitive words, to obtain the first sub-identification result corresponding to the keyword set, including: The text detection system performs sensitive word identification on the keyword set according to the set of sensitive words and the set of ignored words, to obtain a first target identification result corresponding to the keyword set; The text detection system screens a set of related words corresponding to the first target identification result from the keyword set, the set of related words including at least one of synonym words, synonymous words, and antonym words corresponding to the first target identification result; The text detection system performs sensitive word identification on the relevant word set according to the sensitive word set and the ignored word set, to obtain a second target identification result corresponding to the keyword set; The text detection system determines the first sub-identification result corresponding to the keyword set according to the first target identification result and the second target identification result.

5. The text recognition method for a text detection system according to claim 4, wherein, When the sensitive word identification result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, the method further comprises: The text detection system determines feature information of each keyword in the keyword set, and the feature information includes attribute label features and / or fine-grained features; For each keyword, the text detection system stores the keyword in a preset feature word library according to the feature information of the keyword; Furthermore, the method further comprises: When the text detection system receives a sensitive word identification range and a sensitive word configuration requirement sent by the operation and management end, the text detection system configures a sensitive word set based on the feature word library according to the sensitive word identification range and the sensitive word configuration requirement.

6. A text detection system characterized by, The text detection system comprises: An acquisition module configured to acquire text information of a target game, and extract a keyword set from the text information, wherein the text information includes game content text information and / or user chat text information; The acquisition module is further configured to acquire a preset sensitive word set, and perform sensitive word identification on the keyword set according to the sensitive word set, to obtain a sensitive word identification result corresponding to the keyword set; An analysis module configured to analyze the sensitive word identification result, and when the sensitive word identification result indicates that there is at least one target keyword in the keyword set that matches the sensitive word set, generate prompt information of each target keyword, and send the prompt information of each target keyword to an operation and management end of the target game; Furthermore, the sensitive word identification result includes a first sub-identification result and a second sub-identification result; The acquisition module performs sensitive word identification on the keyword set according to the sensitive word set, to obtain the sensitive word identification result corresponding to the keyword set, in the following manner: The acquisition module performs sensitive word identification on each keyword in the keyword set according to the sensitive word set, to obtain the first sub-identification result corresponding to the keyword set; The acquisition module determines keyword information of each keyword in the keyword set, and divides the keyword set according to the keyword information of each keyword, to obtain at least two sub-keyword sets; The acquisition module determines semantic features corresponding to each sub-keyword set, and performs sensitive semantic identification on the semantic features corresponding to each sub-keyword set according to the sensitive word set, to obtain the second sub-identification result corresponding to the keyword set; Furthermore, the acquisition module determines the keyword information of each keyword in the keyword set in the following manner: determine target information of each keyword in the keyword set, the target information comprising keyword frequency information and keyword semantic information; calculate keyword scores corresponding to each keyword according to the target information corresponding to each keyword; calculate string distances between each keyword in the keyword set; determine keyword information of each keyword according to the keyword scores corresponding to each keyword and the string distances between each keyword.

7. A text recognition apparatus for use in a text detection system, characterized by The device comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the text recognition method applied to the text detection system according to any one of claims 1-5.

8. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which are invoked to execute the text recognition method applied to the text detection system according to any one of claims 1-5.

Images