Sensitive word identification method, identification system, storage medium and program product

Abstract

The present application relates to the field of data processing technology, and in particular to a sensitive word identification method, identification system, storage medium, and program product. The method comprises obtaining real-time input text information and identifying text features contained in the real-time input text information; determining excluded sensitive words based on the text features and a preset sensitive word list, and updating the preset sensitive word list based on the excluded sensitive words; based on the updated preset sensitive word list and text features, determining whether the real-time input text information contains a target sensitive word, and whether the preset sensitive word list contains both the preset sensitive word and the excluded sensitive word; and if so, generating a sensitivity detection result based on the target sensitive word. The present application facilitates improving the accuracy and efficiency of the sensitive word identification process.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a sensitive word identification method, identification system, storage medium, and program product. Background Art

[0002] With the rapid development of the internet, the speed and scope of online information dissemination are increasing, making online content regulation increasingly important. Sensitive word identification, as a key component of online content regulation, is crucial for maintaining a healthy online environment and preventing the spread of harmful information.

[0003] Traditional sensitive word identification methods mainly rely on pre-defined sensitive word libraries and matching rules to match the input text information word by word. Once the input text information contains the same words as those in the pre-defined sensitive word library, it is determined to be a sensitive word. Although this method is simple and easy to implement, the pre-defined sensitive word library may not be able to adapt to the ever-changing network environment and identification needs, and may thus not be able to effectively identify newly emerging sensitive words. It may also perform unnecessary filtering on outdated sensitive words. In addition, some words that are harmless in a specific context may be mistakenly determined to be sensitive words when using the pre-defined sensitive word library and matching rules for keyword matching. Therefore, relying on the pre-defined sensitive word library and matching rules to match the input text information word by word, the accuracy and efficiency of identifying sensitive words contained in the input text information are relatively low. Summary of the Invention

[0004] In order to improve the accuracy and efficiency of sensitive word recognition, the present application provides a sensitive word recognition method, recognition system, storage medium and program product.

[0005] In the first aspect, the present application provides a sensitive word identification method, which adopts the following technical solutions:

[0006] A sensitive word identification method, comprising:

[0007] Acquiring real-time input text information and identifying text features contained in the real-time input text information;

[0008] Determine exclusion of sensitive words based on the text features, and update a preset sensitive word list based on the exclusion of sensitive words;

[0009] Based on the updated preset sensitive word list and the text features, determining whether the real-time input text information contains target sensitive words, the preset sensitive word list containing preset sensitive words and preset excluded sensitive words;

[0010] If so, a sensitivity detection result is generated based on the target sensitive word.

[0011] By adopting the above technical solution, by performing real-time feature recognition on the input text information, it is convenient to conduct in-depth analysis of the content contained in the real-time input text information, determine the exclusion of sensitive words through the feature recognition results and add the excluded sensitive words to the preset sensitive word list, and realize dynamic updating of the preset sensitive word list, so that the recognition system can continuously learn and adapt to new sensitive words and excluded sensitive words, instead of using a fixed sensitive word library or matching rules for matching. Sensitive word recognition is performed by combining preset sensitive words with excluded sensitive words, which is convenient for meeting the ever-changing network environment and user needs while reducing the probability of false alarms, thereby improving the accuracy and efficiency of the sensitive word recognition process.

[0012] In one possible implementation, after updating the preset sensitive word list based on the excluded sensitive words, the method further includes:

[0013] Performing semantic analysis on the real-time input text information to determine a text summary, and determining a derived sensitive word corresponding to the text summary based on a mapping relationship between the text summary and preset sensitive words;

[0014] Obtain matching records of the preset sensitive word list within a first preset time period, and determine hot sensitive words based on the matching records;

[0015] Obtaining a derived word vector corresponding to the derived sensitive word and a hot word vector corresponding to the hot sensitive word, and determining a sensitive word to be supplemented based on the derived word vector and the hot word vector;

[0016] The preset sensitive word list is updated based on the sensitive words to be supplemented.

[0017] By adopting the above technical solution, through semantic analysis of real-time input text information, the text overview can be determined, and based on the preset sensitive word mapping relationship, the derived sensitive words that may exist in the text can be deduced, so as to facilitate the capture of some disguised sensitive expressions that circumvent direct sensitive word detection through synonym replacement, pinyin abbreviation, etc., by analyzing the word vectors of derived sensitive words and hot sensitive words, and using the similarity of these word vectors to identify potential sensitive words to be supplemented, the preset sensitive word list is updated based on the sensitive words to be supplemented, so as to facilitate timely response to newly emerging sensitive topics or issues, thereby facilitating the reduction of detection vulnerabilities caused by the lag of the preset sensitive word list.

[0018] In one possible implementation, the method further includes:

[0019] Obtaining a triggering behavior record of the input user within a second preset time period, and determining whether the input user has regular behavior based on the triggering behavior record and a preset operation map;

[0020] If yes, determining the target behavior path of the recorded user based on the regular behavior of the recorded user within the second preset time period;

[0021] Obtaining node data corresponding to each path node in the target behavior path, and identifying encrypted data features corresponding to each node data;

[0022] The preset sensitive word list is updated based on the encrypted data characteristics.

[0023] By adopting the above technical solution, by analyzing the triggering behavior records of the input user within the second preset time period, it is convenient to identify the input user's regular operating habits, thereby facilitating the prediction of the input user's access or operation behavior path in the future, and determining the nodes that the input user may visit based on the prediction results. By analyzing the node data corresponding to the possible access nodes and setting the relevant encrypted data features in advance according to the analysis results, the preset sensitive word list is updated in a timely manner, thereby facilitating the improvement of the recognition system's response and processing capabilities to newly emerging sensitive data.

[0024] In one possible implementation, the method further includes:

[0025] Identifying a first generation time and a first real-time matching number for each sensitive word in the preset sensitive word list, and identifying a second generation time and a second real-time matching number for each excluded sensitive word in the preset sensitive word list;

[0026] Determine a first cache duration corresponding to each sensitive word based on the first preset cache duration mapping relationship and the first generation time and first real-time matching number of each sensitive word in the preset sensitive word list;

[0027] Determine the second cache duration of each excluded sensitive word based on the second preset cache duration mapping relationship, the second generation time of each excluded sensitive word in the preset sensitive word list, and the second real-time matching number;

[0028] Based on the first cache duration corresponding to each sensitive word and the second cache duration corresponding to each excluded sensitive word, each sensitive word and excluded sensitive word in the preset sensitive word list is cached to a preset storage space.

[0029] By adopting the above technical solution, by identifying the first generation time and the first real-time matching number of each sensitive word in the preset sensitive word list, as well as the second generation time and the second real-time matching number of each excluded sensitive word, it is convenient to analyze the usage of each sensitive word and excluded sensitive word, and by dynamically determining the appropriate cache time length for each sensitive word and excluded sensitive word, it is convenient to better adapt to the actual usage needs of different sensitive words and excluded sensitive words, and by caching sensitive words and excluded sensitive words to a preset storage space and setting a reasonable cache time length, it is convenient to ensure that the preset sensitive word list can be quickly accessed when needed, while reducing unnecessary memory usage.

[0030] In one possible implementation, the method further includes:

[0031] When an exclusion sensitive word appears in the real-time input text information, obtaining a text position of the exclusion sensitive word in the real-time input text information;

[0032] Performing semantic recognition on the real-time input text information based on the text position, and determining a replacement word list based on the semantic recognition result, wherein the replacement word list includes a plurality of replacement words;

[0033] Feedback prompt information is generated based on the replacement word list to remind relevant input personnel to select any replacement word from the replacement word list to replace the excluded sensitive word.

[0034] By adopting the above technical solution, by excluding the text position and semantic recognition results of sensitive words in the real-time input text information, it is convenient to intelligently provide a list of relevant alternative words, which helps to guide the relevant input personnel to select compliant words to replace sensitive words after generating feedback prompt information, thereby ensuring the compliance of the text content. By reducing the frequency of occurrence of excluded sensitive words from the input source, it is convenient to reduce the number of excluded sensitive words that the recognition system needs to identify and process in the subsequent text processing process, that is, it helps to reduce the processing pressure of the system, thereby facilitating the improvement of overall operating efficiency.

[0035] In one possible implementation, after determining the replacement word list based on the semantic recognition result, the method further includes:

[0036] Obtaining a call frequency of each alternative word in the alternative word list by the relevant input user within a third preset time period;

[0037] When the call frequency higher than the preset frequency threshold is not higher than a preset number, adjusting the list position of each substitute word in the substitute word list based on the call frequency of each substitute word to obtain a first updated substitute word list;

[0038] When the call frequency higher than the preset frequency threshold is higher than a preset number, based on the call frequency of each alternative word, the list position of each alternative word in the alternative word list is adjusted, and the alternative words that are not higher than the preset frequency threshold are eliminated to obtain a second updated alternative word list.

[0039] By adopting the above technical solution, by analyzing the frequency of calling each alternative word in the alternative word list by the relevant input user within the third preset time period, it is convenient to understand the preferences and commonly used words of the relevant input user, and adjust the position of the alternative word in the alternative word list based on the usage preferences and commonly used words, so that the alternative words more commonly used by the relevant input user are at the front of the list, thereby improving the experience of the relevant input user when using the alternative word list next time. In addition, infrequently used alternative words can be removed from the alternative word list according to U usage preferences. By streamlining the alternative word list, it can focus more on the alternative words that the relevant input user really needs, thereby improving the effectiveness and practicality of the alternative word list.

[0040] In a second aspect, the present application provides an identification system, which adopts the following technical solutions:

[0041] An identification system, comprising:

[0042] at least one processor;

[0043] Memory;

[0044] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned sensitive word recognition method.

[0045] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0046] A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned sensitive word recognition method.

[0047] In a fourth aspect, the present application provides a computer program product that adopts the following technical solution:

[0048] A computer program product includes a computer program, which implements the above-mentioned sensitive word identification method when executed by a processor.

[0049] In summary, this application includes at least one of the following beneficial technical effects:

[0050] By performing real-time feature recognition on the input text information, it is convenient to conduct in-depth analysis of the content contained in the real-time input text information. The excluded sensitive words are determined through the feature recognition results and added to the preset sensitive word list, so that the preset sensitive word list can be dynamically updated, so that the recognition system can continuously learn and adapt to new sensitive words and excluded sensitive words, instead of using a fixed sensitive word library or matching rules for matching. Sensitive word recognition is performed by combining preset sensitive words with excluded sensitive words, which is convenient for meeting the ever-changing network environment and user needs while reducing the probability of false alarms, thereby improving the accuracy and efficiency of the sensitive word recognition process.

[0051] By identifying the first generation time and the first real-time matching number of each sensitive word in the preset sensitive word list, as well as the second generation time and the second real-time matching number of each excluded sensitive word, it is convenient to analyze the usage of each sensitive word and excluded sensitive word. By dynamically determining the appropriate cache duration for each sensitive word and excluded sensitive word, it is convenient to better adapt to the actual usage needs of different sensitive words and excluded sensitive words. By caching sensitive words and excluded sensitive words to the preset storage space and setting a reasonable cache duration, it is convenient to ensure that the preset sensitive word list can be quickly accessed when needed, while reducing unnecessary memory usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flow chart of a sensitive word identification method in an embodiment of the present application;

[0053] Figure 2 This is a schematic diagram of a cache process of a preset sensitive word list in an embodiment of the present application;

[0054] Figure 3 It is a structural diagram of an identification system in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following is combined with Figures 1 to 3 This application is described in further detail.

[0056] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0057] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0058] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information requires the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0059] Specifically, embodiments of the present application provide a sensitive word identification method, which is performed by an identification system. The identification system can be a server or a terminal device. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet computer, laptop computer, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0060] refer to Figure 1 , Figure 1 : is a flow chart of a sensitive word identification method in an embodiment of the present application, the method includes steps S110 to S140, wherein:

[0061] Step S110: Acquire real-time input text information and identify text features contained in the real-time input text information.

[0062] Specifically, the current national software system is not allowed to enter Secret-Associated information as required. Relevant enterprises or companies have confidentiality offices to regularly check the information entered into the system to prevent relevant users from entering sensitive information into the system and causing unnecessary trouble to the project and the company. Among them, Secret-Associated information usually refers to information that is identified as confidential, secret or sensitive. This information needs to be specially protected and managed to prevent unauthorized access, leakage or abuse.

[0063] Real-time text information is text information that is input or entered in real time by the input user after logging into the internal platform or internal system. The recognition system can capture the real-time input of the input user through a pre-set text input interface. The pre-set text input interface can be a text box, a chat window or other interface elements that allow the user to input text. The specific text input interface is not specifically limited in the embodiment of this application. The recognition system can capture and process these real-time text information in a timely manner. In addition, the input content of the input user can be captured in real time by monitoring text input events, such as keyboard key events, text change events, etc. The text input event is usually triggered by the input behavior of the input user and contains information about the input content. The method for obtaining real-time text information is not specifically limited in the embodiment of this application. The text features contained in the real-time text information can be identified based on a preset feature recognition algorithm, wherein the preset feature recognition algorithm can be a word embedding technology such as Word2Vec, GloVe, or a convolutional neural network or a recurrent neural network and its variants. The specific feature recognition algorithm is not specifically limited in the embodiment of this application, as long as it can identify the text features contained in the real-time text information.

[0064] Step S120: determining excluded sensitive words based on the text features and the preset sensitive word list, and updating the preset sensitive word list based on the excluded sensitive words.

[0065] Specifically, before the update based on the exclusion of sensitive words, the preset sensitive word list only contains preset sensitive words. The preset sensitive words can be determined by relevant staff based on historical experimental data and uploaded to the recognition system. Text features can be lexical features, syntactic features, semantic features, and contextual features. Among them, lexical features facilitate the analysis of the key points of the real-time input text information by the number of times each word appears in the real-time input text information, and the function and role of each word in the real-time input text information can be understood by the word part of speech; syntactic features facilitate the understanding of the dependency relationship between each word in the real-time input text information, thereby facilitating the understanding of the structural relationship between each component in the real-time input text information, and further facilitating the understanding of the overall semantics of the real-time input text information; semantic features facilitate the understanding of the emotion expressed in the real-time input text information, such as positive emotion, negative emotion, or neutral emotion, thereby facilitating the understanding of the real-time input text information; contextual features facilitate the understanding of the position of a word or sentence in the real-time input text information and other surrounding words or sentences, providing additional contextual information to help more accurately understand the meaning of the word or sentence.

[0066] When determining exclusionary sensitive words based on text features and a preset sensitive word list, the identified text features can first be matched against the preset sensitive word list using a preset keyword matching algorithm. The preset keyword matching algorithm can be a simple matching algorithm, a prefix tree matching algorithm, or the like. Based on the matching results and analysis of the text features, the context of the word in the real-time text input is determined to determine whether it constitutes sensitive content. This includes consideration of surrounding words, the overall semantics of the sentence, and the subject of the text. For example, if the preset sensitive word is "confidential," and "diesel engine seal" appears in text describing mechanical or engineering technology and has no direct association or implication with "confidential," then "diesel engine seal" can be determined as an exclusionary sensitive word. Semantic models such as Word2Vec and BERT can also be used to analyze similar words corresponding to the preset sensitive words. The similar words can then be analyzed to determine whether they have similar meanings to the corresponding preset sensitive words in the context of the real-time text input. If not, the similar words corresponding to the preset sensitive words can be determined as exclusionary sensitive words. In addition to determining exclusion of sensitive words through semantic recognition or analysis, relevant staff can also determine exclusion of sensitive words corresponding to preset sensitive words based on historical experience. The specific method is not specifically limited in the embodiments of this application. Based on the exclusion of sensitive words, the preset sensitive word list is updated, that is, the exclusion of sensitive words is added to the preset sensitive word list. The preset sensitive word configuration and the exclusion of sensitive word configuration can be configured on the recognition system properties. For example, the key of the preset sensitive word can be: mgc, and the key of the exclusion of sensitive words can be: exclude.mgc. When there are a large number of preset sensitive words or exclusion of sensitive words, commas can be used to separate them.

[0067] Step S130: Based on the updated preset sensitive word list and text features, determine whether the real-time input text information contains the target sensitive word, and the preset sensitive word list includes preset sensitive words and excluded sensitive words.

[0068] Step S140: If yes, generate a sensitivity detection result based on the target sensitive word.

[0069] Specifically, the sensitive word detection component in the recognition system will intercept all real-time input request text information and perform sensitive word detection on the text in the real-time input request text information. If the real-time input request text information contains preset sensitive words, the sensitive word detection component will intercept the input user's input request and respond with the detected preset sensitive word result. For example, when the preset sensitive word is "confidential", the generated sensitive detection result may be "Operation failed, please replace the sensitive words in the text information, sensitive words are: confidential". Since the exclusion of sensitive words is set, even if the text information contains "diesel engine seal", the recognition system will not determine "diesel engine seal" as a sensitive word.

[0070] For the embodiments of the present application, by performing real-time feature recognition on the input text information, it is convenient to perform in-depth analysis of the content contained in the real-time input text information, determine the exclusion of sensitive words through the feature recognition results and add the excluded sensitive words to the preset sensitive word list, and realize dynamic update of the preset sensitive word list, so that the recognition system can continuously learn and adapt to new sensitive words and excluded sensitive words, instead of using a fixed sensitive word library or matching rules for matching. Sensitive word recognition is performed by combining preset sensitive words and excluded sensitive words, which is convenient for meeting the ever-changing network environment and user needs while reducing the probability of false alarms, thereby improving the accuracy and efficiency of the sensitive word recognition process.

[0071] Furthermore, in order to reduce the detection loopholes caused by the lag of the preset sensitive word list, after updating the preset sensitive word list based on excluding sensitive words, the method provided in the embodiment of the present application further includes:

[0072] Perform semantic analysis on the real-time input text information to determine the text overview, and determine the derived sensitive words corresponding to the text overview based on the mapping relationship between the text overview and the preset sensitive words; obtain matching records of the preset sensitive word list within the first preset time period, and determine the hot sensitive words based on the matching records; obtain the derived word vectors corresponding to the derived sensitive words and the hot word vectors corresponding to the hot sensitive words, and determine the sensitive words to be supplemented based on the derived word vectors and the hot word vectors; update the preset sensitive word list based on the sensitive words to be supplemented.

[0073] Specifically, the real-time text information can be pre-processed to remove irrelevant characters, punctuation marks, etc. contained in the real-time text information, and the real-time text information can be segmented to separate it into independent words or phrases. Then, natural language processing technology is used to deeply understand the words or phrases after the segmentation process to extract the core information and theme of the real-time text information. Unlike the text features determined in the above embodiment, the text summary is mainly used to summarize the main content of the real-time text information. The preset sensitive word mapping relationship includes derived sensitive words corresponding to different text summaries. The specific content is not specifically limited in the embodiment of this application and can be determined by relevant staff based on historical experimental data and uploaded to the recognition system. Derived sensitive words are different from the preset sensitive words proposed in the above embodiment. The preset sensitive words are sensitive words determined by relevant staff based on historical experimental data and are applicable to all subject scenarios, while derived sensitive words are only applicable to the current real-time text information. For example, the corresponding derived sensitive words in the real-time text information of the financial theme may be related to economy, finance, etc., and are not applicable to the real-time text information of the breeding theme. Since the real-time text information is changing, the corresponding derived sensitive words are also dynamically changing.

[0074] After determining the derived sensitive words, you can first obtain and analyze the matching records of the preset sensitive word list in the first preset time period. The first preset time period is a period of time after the preset sensitive word list is updated based on the exclusion of sensitive words. The duration corresponding to the first preset time period can be 3 minutes or 5 minutes. The specific duration is not specifically limited in the embodiment of this application. The matching record contains the time and number of times each preset sensitive word is successfully matched in the first preset time period. Based on the matching record, the hot sensitive words corresponding to the first preset time period can be determined. The number of times the hot sensitive words are successfully matched in the first preset time period is higher than the preset number threshold, and the frequency of successful matching is higher than the preset frequency threshold. The number of hot sensitive words, the preset number threshold and the preset frequency threshold are not specifically limited in the embodiment of this application, and can be determined by relevant staff based on historical experimental data and uploaded to the recognition system.

[0075] After determining the hot sensitive words, you can first obtain the derived word vectors corresponding to the derived sensitive words and the hot word vectors corresponding to the hot sensitive words based on the preset pre-training models such as Word2Vec, GloVe, BERT, and then use measurement methods such as cosine similarity to calculate the candidate words that have similarity with the derived word vectors and the hot word vectors, and determine the candidate words and derived sensitive words with similarity higher than the preset similarity threshold as sensitive words to be supplemented. The preset similarity threshold and the number of sensitive words to be supplemented are not specifically limited in the embodiments of this application, and can be determined by relevant staff based on historical experimental data and uploaded to the recognition system. Add the sensitive words to be supplemented to the preset sensitive word list to implement the update operation of the preset sensitive word list. Update the preset sensitive word list based on the sensitive words to be supplemented, so as to facilitate timely response to newly emerging sensitive topics or issues.

[0076] Furthermore, in order to improve the recognition system's ability to respond to and process newly emerging sensitive data, the method provided in the embodiment of the present application further includes:

[0077] Obtain the trigger behavior record of the input user within the second preset time period, and based on the trigger behavior record and the preset operation map, determine whether the input user has regular behavior; if so, determine the target behavior path of the input user based on the regular behavior of the input user within the second preset time period; obtain the node data corresponding to each path node in the target behavior path, and identify the encrypted data features corresponding to each node data; update the preset sensitive word list based on the encrypted data features.

[0078] Specifically, the second preset time period is a period of time after the input user is detected to log in or access the identification system. The duration corresponding to the second preset time period can be 30 seconds or 60 seconds. The specific duration is not specifically limited in the embodiment of this application. The triggering behavior record of the input user in the second preset time period can be monitored by the monitoring tool built into the identification system, and recorded in the memory of the identification system or written into a log file, which can be directly retrieved when needed. The preset operation map includes multiple start nodes, operation nodes, decision nodes and end nodes, as well as connecting lines between each node. The trigger behavior record of the input user within the second preset time period is matched with the preset operation map. When the trigger behavior record follows the operation sequence of a node route in the preset operation map, it can be determined that the input user has regular behavior. At this time, the node route followed by the trigger behavior record can be predicted as the target behavior path that the input user may need to execute in full. There can be one or more target behavior paths. For example, based on the trigger behavior record within the second preset time period, the trigger nodes of the input user are determined to be node a, node b, node c, node c, where path X is composed of node a, node b, node c, node d and node e, and path Y is composed of node a, node b, node c, node f and node g. At this time, both path X and path Y can be predicted as the target behavior path of the input user.

[0079] After predicting the target behavior path that the input user may need to access, feature recognition can be performed on the node data corresponding to each path node in the target behavior path. After determining the encrypted data features corresponding to each node data, based on the method of determining the derived sensitive words in the above embodiment, the encrypted sensitive words corresponding to the encrypted data features are determined. No further details are given here. The encrypted sensitive words are added to the preset sensitive word list to implement the update operation of the preset sensitive word list.

[0080] By analyzing the triggering behavior records of the input user within the second preset time period, it is convenient to identify the input user's regular operating habits, thereby facilitating the prediction of the input user's access or operating behavior path in the future, and determining the nodes that the input user may visit based on the prediction results. By analyzing the node data corresponding to the possible access nodes and setting the relevant encrypted data features in advance according to the analysis results, the preset sensitive word list is updated in a timely manner, thereby facilitating the improvement of the recognition system's response and processing capabilities to newly emerging sensitive data.

[0081] Furthermore, in order to ensure that the preset sensitive word list can be quickly accessed when needed, the method provided in the embodiment of the present application may further include steps S210 to S240, such as Figure 2 As shown, where:

[0082] Step S210: Identify the first generation time and the first real-time matching number of each sensitive word in the preset sensitive word list, and identify the second generation time and the second real-time matching number of each excluded sensitive word in the preset sensitive word list.

[0083] Specifically, since the preset sensitive word list will be updated when the real-time input text information changes, the first generation moments corresponding to different sensitive words in the preset sensitive word list are different. The corresponding first generation moment is determined according to the moment when each sensitive word is written into the preset sensitive word list. Based on the same method, the second generation moment of each excluded sensitive word is determined according to the real-time updated preset sensitive word list. After the first generation moment when the sensitive word is written into the preset sensitive word list, the number of times the sensitive word completes matching is the first real-time matching number corresponding to the sensitive word. The more the first real-time matching number is, the more times the corresponding sensitive word appears in the real-time input text information. Based on the same method as above, the second real-time matching number of each excluded sensitive word can be determined.

[0084] Step S220: Determine the first cache duration corresponding to each sensitive word based on the first preset cache duration mapping relationship, and the first generation time and first real-time matching number of each sensitive word in the preset sensitive word list.

[0085] Specifically, based on the first generation time and the current time, the first generation time of each sensitive word can be determined. Different first generation times and first real-time matching times correspond to different first cache times. The first preset cache time mapping relationship includes first cache times corresponding to different parameter combinations of first generation times and first real-time matching times. The specific content is not specifically limited in the embodiments of this application and can be determined by relevant staff based on historical experimental data and uploaded to the recognition system. Based on the above method, the first cache time corresponding to each sensitive word can be determined.

[0086] Step S230: Determine the second cache duration of each excluded sensitive word based on the second preset cache duration mapping relationship, the second generation time and the second real-time matching number of each excluded sensitive word in the preset sensitive word list.

[0087] Specifically, the method for determining the second cache duration corresponding to each excluded sensitive word can refer to the method for determining the first cache duration corresponding to each sensitive word in the above embodiment, which will not be described in detail here. The second preset cache duration mapping relationship includes the second cache duration corresponding to the parameter combination of different second generation durations and second real-time matching times. The specific content is not specifically limited in the embodiments of this application and can be determined by relevant staff based on historical experimental data and uploaded to the recognition system.

[0088] Step S240: Based on the first cache duration corresponding to each sensitive word and the second cache duration corresponding to each excluded sensitive word, each sensitive word and excluded sensitive word in the preset sensitive word list is cached to a preset storage space.

[0089] Specifically, based on the first cache duration corresponding to each sensitive word, the storage duration of each sensitive word in the preset storage space is limited. At the same time, based on the second cache duration corresponding to each excluded sensitive word, the storage duration of each excluded sensitive word in the preset storage space is limited. The preset storage space can be JVM memory, so that the recognition system can quickly access the preset sensitive word list when performing sensitive word recognition. Compared with reading the preset sensitive word list from a disk file or database, the JVM memory access speed is much faster. Storing the preset sensitive word list in the JVM memory helps to improve the response speed and overall performance of the program.

[0090] Furthermore, in order to reduce the number of excluded sensitive words that the recognition system needs to identify and process in subsequent text processing, the method provided in the embodiment of the present application further includes:

[0091] When an exclusion sensitive word appears in the real-time input text information, the text position of the exclusion sensitive word in the real-time input text information is obtained; semantic recognition is performed on the real-time input text information based on the text position, and a replacement word list is determined based on the semantic recognition result, and the replacement word list contains multiple replacement words; feedback prompt information is generated based on the replacement word list to remind relevant input personnel to select an replacement word from the replacement word list to replace the exclusion sensitive word.

[0092] Specifically, if it is detected that a word or phrase in the real-time text information successfully matches any of the excluded sensitive words, it can be determined that the excluded sensitive words appear in the real-time text information. At this time, the text position of the corresponding excluded sensitive words in the real-time text information can be located. After determining the text position, the real-time text information can be subjected to in-depth semantic analysis based on the preset natural language processing technology and text position to understand the relationship between the meaning of the real-time text information and the context of the text position, and to determine a list of replacement words corresponding to the excluded sensitive words. The replacement word list contains multiple replacement words. When determining the replacement word, the replacement candidate word that has a similar relationship with the exclusion word vector can be determined based on the exclusion word vector corresponding to the exclusion sensitive word and the semantic recognition result. Then, based on the sensitive words contained in the exclusion sensitive word, the replacement candidate word is screened to obtain a replacement word that does not contain sensitive words. For example, when the sensitive word is "confidential", the corresponding exclusion sensitive word can be "diesel engine seal", where "diesel" "Diesel engine seal" contains the sensitive word "confidential". After word matching based on the preset sensitive word list, "diesel engine seal" will not be processed as a sensitive word. After detecting the exclusion sensitive word "diesel engine seal", the replacement candidate words with a similar relationship to the exclusion word vector can be determined based on the exclusion word vector corresponding to "diesel engine seal" and the semantic recognition result. The replacement candidate words can be "diesel engine seal storage", "diesel engine leakproof", "diesel engine closure", "diesel engine airtight", and "diesel engine liquid tight". After removing the replacement candidate word "diesel engine seal storage" including the sensitive word "confidential", "diesel engine leakproof", "diesel engine closure", "diesel engine airtight" and "diesel engine liquid tight" can be used as replacement words.

[0093] If it is detected again that the relevant input person needs to enter "diesel engine seal", the list of alternative words can be directly fed back to remind the relevant input person to select any alternative word from the list of alternative words to replace the excluded sensitive words. By reducing the frequency of occurrence of excluded sensitive words from the input source, it is convenient to reduce the number of excluded sensitive words that the recognition system needs to identify and process in the subsequent text processing process, that is, it helps to reduce the processing pressure of the system, thereby facilitating the improvement of overall operating efficiency.

[0094] Furthermore, after determining the list of replacement words based on the semantic recognition results, the method provided in the embodiment of the present application further includes:

[0095] Obtain the call frequency of each alternative word in the alternative word list by the relevant input user within a third preset time period; when the call frequency higher than the preset frequency threshold is not higher than a preset number, adjust the list position of each alternative word in the alternative word list based on the call frequency of each alternative word to obtain a first updated alternative word list; when the call frequency higher than the preset frequency threshold is higher than a preset number, adjust the list position of each alternative word in the alternative word list based on the call frequency of each alternative word, and eliminate the alternative words that are not higher than the preset frequency threshold to obtain a second updated alternative word list.

[0096] Specifically, based on the triggering records of the replacement word list by the relevant input user, the frequency of the relevant input user's call for each replacement word in the replacement word list within a third preset time period can be determined. The third preset time period is a period of time after the replacement word list is generated. The third preset time period can be 3 minutes or 5 minutes. The specific time period is not specifically limited in the embodiments of the present application. Replacement words with a call frequency higher than the preset frequency threshold are determined as replacement words of interest.

[0097] When the number of concerned substitute words is not higher than the preset number, each substitute word can be sorted based on the call frequency of each substitute word in the substitute word list to obtain a substitute word queue sorted from high to low in call frequency. Based on the substitute word queue, the list position of each substitute word in the substitute word list is determined to obtain a first updated substitute word list. When the number of concerned substitute words is higher than the preset number, the position of each substitute word in the substitute word list is first adjusted based on the content disclosed in the above embodiment, and then the substitute words that are not higher than the preset frequency threshold are eliminated to obtain a second updated substitute word list, that is, the second updated substitute word list only contains concerned substitute words. Among them, the specific preset frequency threshold and preset number are not specifically limited in the embodiment of this application, and can be determined by relevant staff based on historical experimental data.

[0098] For the embodiment of the present application, by analyzing the frequency of calling each alternative word in the alternative word list by the relevant input user within the third preset time period, it is convenient to understand the preferences and commonly used words of the relevant input user, and adjust the position of the alternative word in the alternative word list based on the usage preferences and commonly used words, so that the alternative words more commonly used by the relevant input user are located at the front of the list, thereby facilitating the improvement of the experience of the relevant input user when using the alternative word list next time. In addition, infrequently used alternative words can be removed from the alternative word list according to U usage preferences. By streamlining the alternative word list, it can focus more on the alternative words that the relevant input user really needs, thereby facilitating the improvement of the effectiveness and practicality of the alternative word list.

[0099] The present application provides an identification system, such as Figure 3 As shown, Figure 3The identification system 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the identification system 300 may further include a transceiver 304. It should be noted that in practical applications, the number of transceivers 304 is not limited to one, and the structure of the identification system 300 does not constitute a limitation on the embodiments of the present application.

[0100] Processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0101] Bus 302 may include a path for transmitting information between the above components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 3 The fact that only one line is used does not mean that there is only one bus or one type of bus.

[0102] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0103] The memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.

[0104] The identification system includes, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers are also possible. Figure 3 The identification system shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0105] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0106] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in any of the above embodiments is implemented.

[0107] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0108] The above description is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A sensitive word identification method, characterized in that: include: Acquiring real-time input text information and identifying text features contained in the real-time input text information; Determining excluded sensitive words based on the text features and a preset sensitive word list, and updating the preset sensitive word list based on the excluded sensitive words, wherein the excluded sensitive words are determined based on the context of the real-time input text information; Based on the updated preset sensitive word list and the text features, determining whether the real-time input text information contains target sensitive words, the updated preset sensitive word list containing preset sensitive words and excluded sensitive words; If yes, generating a sensitivity detection result based on the target sensitive word; After updating the preset sensitive word list based on the excluded sensitive words, the method further includes: Performing semantic analysis on the real-time input text information to determine a text summary, and determining, based on the text summary and a preset sensitive word mapping relationship, derived sensitive words corresponding to the text summary, wherein the derived sensitive words are related to the field to which the real-time input text information belongs; Obtain matching records of the preset sensitive word list within a first preset time period, and determine hot sensitive words based on the matching records, where the number of successful matches of the hot sensitive words within the first preset time period exceeds a preset number threshold, and the frequency of successful matches exceeds a preset frequency threshold; Obtaining a derived word vector corresponding to the derived sensitive word and a hot word vector corresponding to the hot sensitive word, and determining a sensitive word to be supplemented based on the derived word vector and the hot word vector; Updating the updated preset sensitive word list based on the sensitive words to be supplemented; Among them, also include: Identify the first generation time and the first real-time matching number of each sensitive word in the updated preset sensitive word list, and identify the second generation time and the second real-time matching number of each excluded sensitive word in the updated preset sensitive word list; Determine a first cache duration corresponding to each sensitive word based on the first preset cache duration mapping relationship and the first generation time and first real-time matching number of each sensitive word in the updated preset sensitive word list; Determine the second cache duration of each excluded sensitive word based on the second preset cache duration mapping relationship, the second generation time and the second real-time matching number of each excluded sensitive word in the updated preset sensitive word list; Based on the first cache duration corresponding to each sensitive word and the second cache duration corresponding to each excluded sensitive word, each sensitive word and excluded sensitive word in the updated preset sensitive word list is cached to the preset storage space.

2. A sensitive word identification method according to claim 1, characterized in that: Also includes: Obtaining a triggering behavior record of the input user within a second preset time period, and determining whether the input user has regular behavior based on the triggering behavior record and a preset operation map; If yes, determining the target behavior path of the recorded user based on the regular behavior of the recorded user within the second preset time period; Obtaining node data corresponding to each path node in the target behavior path, and identifying encrypted data features corresponding to each node data; The preset sensitive word list is updated based on the encrypted data characteristics.

3. A sensitive word identification method according to claim 1, characterized in that: Also includes: When an exclusion sensitive word appears in the real-time input text information, obtaining a text position of the exclusion sensitive word in the real-time input text information; Performing semantic recognition on the real-time input text information based on the text position, and determining a replacement word list based on the semantic recognition result, wherein the replacement word list includes a plurality of replacement words; Feedback prompt information is generated based on the replacement word list to remind relevant input personnel to select any replacement word from the replacement word list to replace the excluded sensitive word.

4. A sensitive word identification method according to claim 3, characterized in that: After determining the list of alternative words based on the semantic recognition result, the method further includes: Obtaining a call frequency of each alternative word in the alternative word list by the relevant input personnel within a third preset time period; When the call frequency higher than the preset frequency threshold is not higher than a preset number, adjusting the list position of each substitute word in the substitute word list based on the call frequency of each substitute word to obtain a first updated substitute word list; When the call frequency higher than the preset frequency threshold is higher than a preset number, based on the call frequency of each alternative word, the list position of each alternative word in the alternative word list is adjusted, and the alternative words that are not higher than the preset frequency threshold are eliminated to obtain a second updated alternative word list.

5. A recognition system, characterized in that: The identification system includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a sensitive word identification method according to any one of claims 1-4.

6. A computer-readable storage medium, characterized in that include: A computer program is stored which can be loaded by a processor and executes a sensitive word identification method as described in any one of claims 1 to 4.

7. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the steps of a sensitive word identification method according to any one of claims 1 to 4.

Images