Target object identification method and device, equipment, storage medium and program product

Abstract

The invention relates to a target object recognition method and device, equipment, a storage medium and a program product, and the method comprises the steps: firstly obtaining the historical behavior data of a to-be-recognized object, then constructing a behavior index system of the to-be-recognized object according to the historical behavior data, and finally carrying out the recognition of a target object according to the behavior index system and an evaluation index system. And identifying the to-be-identified object to obtain an identification result. According to the method, the evaluation index system comprises various standard indexes, and the various standard indexes can reflect the information of the illegal behaviors in different aspects, so that the behavior index system and the evaluation index system are combined for analysis, and the incidence relation between the behaviors of the to-be-identified object and the illegal behaviors can be analyzed from multiple aspects; therefore, subsequent recognition of the to-be-recognized object based on the association relationship can realize comprehensive analysis, and the recognition accuracy is further improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment, storage medium and program product for identifying a target object. Background Art

[0002] With the rapid development of the Internet and information technology, many violations have emerged on the Internet, and now many violations have become more and more complex and hidden, which not only brings hidden dangers to network security, but also has a great impact on the stable development of society. In view of these problems, it is very meaningful to use network information technology to efficiently and accurately identify the violations of violators.

[0003] At present, the identification method of illegal behavior mainly relies on analyzing the relevant information of the illegal person logging into the network to determine whether it involves illegal behavior and further identify the illegal person. However, the above identification method has the problem of inaccurate identification. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, equipment, storage medium and program product for identifying a target object that can improve recognition accuracy in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for identifying a target object, the method comprising:

[0006] Obtain historical behavior data of the object to be identified;

[0007] Construct a behavioral indicator system for the object to be identified based on historical behavioral data;

[0008] According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain the identification result.

[0009] The target object identification method provided in the embodiment of the present application first obtains the historical behavior data of the object to be identified, then constructs the behavior index system of the object to be identified based on the historical behavior data, and finally identifies the object to be identified based on the behavior index system and the evaluation index system to obtain the identification result. In the above method, since the evaluation index system includes a variety of standard indicators, and the multiple standard indicators can reflect information on different aspects of illegal behaviors, the behavior index system and the evaluation index system are combined for analysis, and the correlation between the behavior of the object to be identified and the illegal behavior can be analyzed from multiple aspects. Therefore, the subsequent identification of the object to be identified based on the correlation relationship can achieve a comprehensive analysis, thereby improving the accuracy of identification.

[0010] In one embodiment, a behavior indicator system of an object to be identified is constructed based on historical behavior data, including:

[0011] Classify historical behavior data into indicators to obtain multiple behavior indicators;

[0012] Conduct statistical analysis on the historical behavior data under each behavior indicator to obtain the evaluation information corresponding to each behavior indicator;

[0013] A behavior indicator system is constructed based on multiple behavior indicators and evaluation information corresponding to each behavior indicator; the behavior indicator system includes the corresponding relationship between the behavior indicators and the evaluation information.

[0014] In one embodiment, the behavior indicators include primary behavior indicators and secondary behavior indicators. The historical behavior data is classified into indicators to obtain multiple behavior indicators, including:

[0015] Classifying the historical behavior data into first-level behavior indicators to obtain multiple first-level behavior indicators;

[0016] The historical behavior data under each first-level behavior indicator is classified into second-level behavior indicators to obtain multiple second-level behavior indicators.

[0017] The method described in the embodiment of the present application realizes the hierarchical classification of data and the effect of analyzing data from different dimensions by macro-classifying the primary behavior indicators of historical behavior data and refining the classification of secondary behavior indicators. It can accurately analyze the characteristics and trends of historical behavior data, thereby improving the accuracy of data analysis.

[0018] In one embodiment, the object to be identified is identified according to the behavior indicator system and the evaluation indicator system to obtain an identification result, including:

[0019] Determine the similarity between the behavioral indicator system and the evaluation indicator system;

[0020] If the similarity is greater than a preset similarity threshold, then determining that the recognition result indicates that the object to be recognized is the target object;

[0021] If the similarity is not greater than the preset similarity threshold, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0022] In the method described in the embodiment of the present application, since the behavior index system and the evaluation index system represent the characteristics of the object to be identified and the target object respectively, by comparing the similarity of multiple characteristics, it is possible to accurately determine whether the object to be identified meets the characteristics of the target object. Moreover, since the behavior index system contains data of multiple dimensions, by comprehensively considering the data of multiple dimensions, the characteristics of the object to be identified can be more comprehensively and accurately evaluated, thereby improving the accuracy of identification.

[0023] In one embodiment, determining the similarity between the behavior indicator system and the evaluation indicator system includes:

[0024] Obtaining a first indicator vector corresponding to the behavior indicator system and a second indicator vector corresponding to the evaluation indicator system;

[0025] The similarity between the behavior index system and the evaluation index system is determined according to the cosine value between the first index vector and the second index vector.

[0026] The method described in the embodiment of the present application determines the similarity between the behavior index system and the evaluation index system through the cosine degree, which can reduce the huge amount of calculation and excessive resource consumption of the machine learning algorithm, improve the efficiency of information processing, and further improve the recognition efficiency. Cosine degree calculation performs well in processing high-dimensional data, because the distance between vectors in high-dimensional space is difficult to calculate, so using the angle to reflect the similarity can improve the calculation efficiency and accuracy.

[0027] In one embodiment, the object to be identified is identified according to the behavior indicator system and the evaluation indicator system to obtain an identification result, including:

[0028] Determine whether the evaluation information under the indicators in the behavior indicator system meets the evaluation rules under the corresponding indicators in the evaluation indicator system;

[0029] If satisfied, it is determined that the recognition result indicates that the object to be recognized is the target object;

[0030] If not, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0031] The method described in the embodiment of the present application can reduce uncertainty and duplication of work in the evaluation process and improve evaluation efficiency by standardizing whether the evaluation information meets the evaluation rules.

[0032] In one embodiment, the method further comprises:

[0033] Obtain historical behavior data of multiple offenders;

[0034] An evaluation index system is constructed based on historical behavior data of multiple violators; the evaluation index system includes multiple first-level standard indicators, multiple second-level standard indicators, and evaluation rules corresponding to each second-level standard indicator.

[0035] The method described in the embodiments of the present application can comprehensively evaluate the behavior of the violating object through multi-level indicator classification, rather than relying solely on a single indicator, thereby improving recognition accuracy.

[0036] In a second aspect, the present application further provides a target object recognition device, the device comprising:

[0037] A first acquisition module is used to acquire historical behavior data of the object to be identified;

[0038] The first construction module is used to construct a behavior indicator system of the object to be identified based on historical behavior data;

[0039] The recognition module is used to identify the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain the recognition result.

[0040] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0041] Obtain historical behavior data of the object to be identified;

[0042] Construct a behavioral indicator system for the object to be identified based on historical behavioral data;

[0043] According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain the identification result.

[0044] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0045] Obtain historical behavior data of the object to be identified;

[0046] Construct a behavioral indicator system for the object to be identified based on historical behavioral data;

[0047] According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain the identification result.

[0048] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0049] Obtain historical behavior data of the object to be identified;

[0050] Construct a behavioral indicator system for the object to be identified based on historical behavioral data;

[0051] According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain the identification result.

[0052] The above-mentioned target object identification method, device, equipment, storage medium and program product, the method first obtains the historical behavior data of the object to be identified, then constructs the behavior index system of the object to be identified based on the historical behavior data, and finally identifies the object to be identified based on the behavior index system and the evaluation index system to obtain the identification result. In the above method, since the evaluation index system contains a variety of standard indicators, and the multiple standard indicators can reflect information on different aspects of illegal behaviors, the behavior index system and the evaluation index system are combined for analysis, and the correlation between the behavior of the object to be identified and the illegal behavior can be analyzed from multiple aspects. Therefore, the subsequent identification of the object to be identified based on the correlation relationship can achieve a comprehensive analysis, thereby improving the accuracy of identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is an internal structure diagram of a computer device in one embodiment;

[0054] Figure 2 is a schematic flow chart of a target object identification method in one embodiment;

[0055] Figure 3 is a schematic flow chart of a target object identification method in another embodiment;

[0056] Figure 4 is a schematic flow chart of a target object identification method in another embodiment;

[0057] Figure 5 is a flow chart of a target object identification method in another embodiment;

[0058] Figure 6 is a schematic flow chart of a target object identification method in another embodiment;

[0059] Figure 7 is a schematic flow chart of a target object identification method in another embodiment;

[0060] Figure 8 is a schematic flow chart of a target object identification method in another embodiment;

[0061] Fig. 9 is a schematic flow chart of a target object identification method in another embodiment;

[0062] Fig.10 is a structural block diagram of a target object recognition device in one embodiment;

[0063] Fig.11 FIG. 4 is a structural block diagram of a target object recognition device in another embodiment. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0065] With the rapid development of the Internet and information technology, many illegal behaviors on the Internet have appeared, and now many illegal behaviors have more and more complex and hidden characteristics, which not only bring hidden dangers to network security, but also have a great impact on the stable development of society. In view of these problems, it is very meaningful to use network information technology to efficiently and accurately identify the illegal behaviors of illegal personnel. At present, the identification method of illegal behaviors mainly relies on analyzing the relevant information of illegal personnel logging into the network to determine whether illegal behaviors are involved, and further identify illegal personnel. However, the above-mentioned identification method has the problem of inaccurate identification. The present application provides a method for identifying a target object, aiming to solve the above-mentioned technical problems, and the following embodiments will specifically illustrate the method for identifying the target object described in the present application.

[0066] The target object recognition method provided in the embodiment of the present application can be applied to Figure 1 In the computer device shown in the figure, the computer device can be a terminal or a server, and its internal structure diagram can be as shown in FIG. Figure 1 As shown, the computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for identifying a target object is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0067] Those skilled in the art will understand that Figure 1The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0068] In one embodiment, Figure 2 As shown, a method for identifying a target object is provided, and the method is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0069] S201, obtaining historical behavior data of the object to be identified.

[0070] Among them, the objects to be identified include violators and non-violators. Historical behavior data includes personnel trajectory information and basic personnel information. Among them, personnel trajectory information includes at least one of the locations where suspected violations occurred, browsing records of illegal websites, and records of publishing illegal speeches; basic personnel information includes at least one of special place entry and exit information, address book information, Internet record information, user preference information, transaction information, whether or not the person is unmarried at an advanced age, and community street information.

[0071] In an embodiment of the present application, the computer device can obtain the historical behavior data of the object to be identified from the relevant departments through legal channels. Optionally, the computer can obtain the historical behavior data of the object to be identified from the data collected manually or from the data filled in by the user. Further, after obtaining the historical behavior data, the computer can pre-process the historical behavior data, and the specific pre-processing process can include missing value cleaning, format content cleaning and logical error cleaning. Among them, the process of missing value cleaning can include first determining the missing value range, then removing unnecessary fields, then filling in the missing content, and finally re-taking the data; format content cleaning can include removing data with inconsistent display formats such as time, date, value, full and half-width, removing characters that should not exist in the content, and removing data that does not match the content of the field; logical error cleaning is to remove some data that can directly find problems using simple logical reasoning to prevent the analysis results from going astray, and can include data deduplication, removal of unreasonable values ​​and correction of contradictory content.

[0072] S202, constructing a behavior indicator system for the object to be identified based on historical behavior data.

[0073] The behavior indicator system includes multiple behavior indicators and evaluation information corresponding to each behavior indicator.

[0074] In an embodiment of the present application, after the computer device obtains the historical behavior data of the object to be identified based on the above steps, it can classify the historical behavior data to obtain behavior data of different categories, and then construct a behavior indicator system of the object to be identified based on the behavior data of different categories. Optionally, after obtaining the historical behavior data, the computer device can input the historical behavior data into a preset neural network or a preset algorithm model, perform feature extraction through the preset neural network or the preset algorithm model, and then construct a behavior indicator system of the object to be identified based on the extracted features. Optionally, after the computer device obtains the behavior data of different categories, it can perform hierarchical clustering analysis on the data in each category, calculate the distance between the two data, remove the data whose distance is greater than the preset distance, and then construct a behavior indicator system of the object to be identified based on the remaining data.

[0075] S203, identifying the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain an identification result.

[0076] The evaluation index system is a standard index system pre-built based on the historical behavior data of the violating object, and the evaluation index system includes multiple standard indicators and evaluation rules corresponding to each standard indicator. The identification result includes whether the object to be identified is an illegal object and / or whether the object to be identified is not an illegal object.

[0077] In the embodiment of the present application, the computer device can construct a standard indicator system based on the historical behavior data of the violating object in advance, and then after the computer device obtains the behavior indicator system of the object to be identified based on the above steps, it can use the evaluation indicator system as the identification standard to analyze the behavior indicator system of the object to be identified, and identify the object to be identified based on the analysis result to obtain the identification result. Optionally, after the computer device obtains the behavior indicator system, it can input the behavior indicator system and the evaluation indicator system into the neural network for correlation analysis to obtain the correlation result, and then the computer device identifies the object to be identified based on the correlation result to obtain the identification result.

[0078] The target object identification method provided in the embodiment of the present application first obtains the historical behavior data of the object to be identified, then constructs the behavior index system of the object to be identified based on the historical behavior data, and finally identifies the object to be identified based on the behavior index system and the evaluation index system to obtain the identification result. In the above method, since the evaluation index system includes a variety of standard indicators, and the multiple standard indicators can reflect information on different aspects of illegal behaviors, the behavior index system and the evaluation index system are combined for analysis, and the correlation between the behavior of the object to be identified and the illegal behavior can be analyzed from multiple aspects. Therefore, the subsequent identification of the object to be identified based on the correlation relationship can achieve a comprehensive analysis, thereby improving the accuracy of identification.

[0079] In one embodiment, a specific implementation method for constructing a behavior indicator system of an object to be identified is also provided, such as Figure 3 As shown, the "constructing a behavior indicator system of the object to be identified based on historical behavior data" in the above step S202 includes:

[0080] S301, classifying historical behavior data into indicators to obtain multiple behavior indicators.

[0081] Among them, indicators are classification categories.

[0082] In an embodiment of the present application, the computer device can pre-construct or obtain various standard indicators in the evaluation index system, and then after obtaining the historical behavior data of the object to be identified, the computer device can classify the historical behavior data according to the standard indicators to obtain multiple indicators.

[0083] Furthermore, the above behavioral indicators include primary behavioral indicators and secondary behavioral indicators. On this basis, Figure 4 As shown, the "classifying the historical behavior data into indicators to obtain multiple behavior indicators" in the above step S301 includes:

[0084] S3011, classify the historical behavior data into first-level behavior indicators to obtain multiple first-level behavior indicators.

[0085] Among them, the first-level behavior indicators include the time when the historical behavior occurred, the transaction amount involved in the historical behavior, the transaction object information of the historical behavior, and the personal information of the object to be identified.

[0086] In an embodiment of the present application, a computer device may pre-construct or obtain each first-level standard indicator and each second-level standard indicator in an evaluation index system. Then, after obtaining the historical behavior data of the object to be identified, the computer device may classify the historical behavior data into first-level behavior indicators according to each first-level standard indicator to obtain the first-level behavior indicators and the historical behavior data under each first-level behavior indicator.

[0087] S3012, classifying the historical behavior data under each first-level behavior indicator into second-level behavior indicators to obtain multiple second-level behavior indicators.

[0088] Among them, the secondary behavior indicators are sub-indicators under each primary behavior indicator. Specifically, the time of occurrence of historical behaviors includes at least one of the frequency of special time periods, high-frequency time periods, and abnormal frequency of profits; the transaction amount involved in historical behaviors includes at least one of the frequency of special amounts and abnormal amounts in profitable time periods; the transaction object information of historical behaviors includes the number of high-frequency occurrences of special amounts of many-to-one payees, and the number of complaints or reports from payees; the personal information of the object to be identified includes at least one of the number of abnormal personal behaviors, the number of family adjustment behaviors, the number of browsing bad websites, and the number of publishing bad speech behaviors. The above-mentioned frequency of special time periods indicates the number of times trading behaviors occur in special time periods; high-frequency time periods indicate the high-frequency time periods in which trading behaviors occur; abnormal profit frequency indicates the number of times trading behaviors are only recorded and no refunds occur during special time periods; special amount frequency indicates the number of times special transaction amounts occur; abnormal amount in profitable time periods indicates the number of times special transaction amounts occur in profitable time periods; high-frequency occurrence of special amounts for many-to-one payees indicates the number of times special amounts of many-to-one payees occur; number of complaints and reports from payees indicates the number of times payees are complained and reported; number of abnormal individual behaviors indicates the number of times special cases are involved; number of family mediation behaviors indicates the number of times family mediation incidents occur; number of browsing of bad websites indicates the number of times bad websites are browsed; number of bad speech behaviors indicates the number of times bad speech is posted.

[0089] In an embodiment of the present application, after the computer device level obtains multiple first-level behavior indicators based on the above steps, it can further classify the historical behavior data under each first-level behavior indicator into second-level behavior indicators according to each second-level standard indicator to obtain multiple second-level behavior indicators and historical behavior data under each second-level behavior indicator.

[0090] S302, statistically analyzing the historical behavior data under each behavior indicator to obtain evaluation information corresponding to each behavior indicator.

[0091] The evaluation information is the historical behavior data under each indicator, which may include the evaluation information under the primary behavior indicator, and may further include the evaluation information under the secondary behavior indicator.

[0092] In the embodiment of the present application, the computer device can pre-construct or obtain the evaluation rules corresponding to each first-level standard indicator and the second-level standard indicator in the evaluation index system, and then after obtaining the historical behavior data under each indicator, the computer device can perform statistical analysis on the historical behavior data under each indicator according to each evaluation rule to obtain the evaluation information corresponding to each indicator. The computer device can first obtain the evaluation information under each first-level behavior indicator, specifically including the evaluation information corresponding to the time of occurrence of the historical behavior, the evaluation information corresponding to the transaction amount involved in the historical behavior, the evaluation information corresponding to the transaction object of the historical behavior, and the evaluation information corresponding to the individual of the object to be identified. Then, the evaluation information under the second-level behavior indicator included in each first-level behavior indicator can be further obtained, specifically including the evaluation information corresponding to the frequency of special time periods, the evaluation information corresponding to the high-frequency time period, the evaluation information corresponding to the abnormal frequency of profits, the evaluation information corresponding to the frequency of occurrence of special amounts, the evaluation information corresponding to the abnormal amount of profit time periods, the evaluation information corresponding to the high-frequency occurrence of special amounts of many-to-one payees, the evaluation information corresponding to the number of complaints and reports of payees, the evaluation information corresponding to the number of family adjustment behaviors, the evaluation information corresponding to the number of browsing bad websites, and the evaluation information corresponding to the number of bad speech behaviors.

[0093] S303: constructing a behavior indicator system according to the multiple behavior indicators and the evaluation information corresponding to each behavior indicator.

[0094] Among them, the behavioral indicator system includes the correspondence between behavioral indicators and evaluation information.

[0095] In the embodiment of the present application, after the computer device obtains multiple behavior indicators and the evaluation information corresponding to each behavior indicator based on the above steps, the multiple behavior indicators and the evaluation information corresponding to each indicator can be used to construct a behavior indicator system according to a preset template. Specifically, multiple behavior indicators and the evaluation information corresponding to each behavior indicator can be filled into a preset table template to form a table, and the formed table can be shown in the following table.

[0096]

[0097] The method described in the embodiment of the present application realizes the hierarchical classification of data and the effect of analyzing data from different dimensions by macro-classifying the primary behavior indicators of historical behavior data and refining the classification of secondary behavior indicators. It can accurately analyze the characteristics and trends of historical behavior data, thereby improving the accuracy of data analysis.

[0098] In one embodiment, a specific implementation method for identifying an object to be identified is also provided, such as Figure 5 As shown, the above step S203 of "identifying the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain the identification result" includes:

[0099] S401, determining the similarity between the behavior index system and the evaluation index system.

[0100] Among them, the evaluation index system includes multiple first-level standard indicators and multiple second-level standard indicators.

[0101] In the embodiment of the present application, after obtaining the behavior indicator system and the evaluation indicator system, the computer device can determine the similarity between each first-level behavior indicator and the first-level standard indicator, and then determine the similarity between the behavior indicator system and the evaluation indicator system according to the similarity between each first-level behavior indicator and the first-level standard indicator; optionally, the similarity between each first-level behavior indicator and the first-level standard indicator can be weighted, and then the similarity between the behavior indicator system and the evaluation indicator system can be determined based on the result after the weighting. Optionally, after obtaining the behavior indicator system and the evaluation indicator system, the computer device can determine the similarity between each second-level behavior indicator and the second-level standard indicator, and then determine the similarity between the behavior indicator system and the evaluation indicator system according to the similarity between each second-level behavior indicator and the second-level standard indicator; optionally, the similarity between each second-level behavior indicator and the second-level standard indicator can be weighted, and then the similarity between the behavior indicator system and the evaluation indicator system can be determined based on the result after the weighting.

[0102] S402, determine whether the similarity is greater than a preset similarity threshold; if so, execute S403; if not, execute S404.

[0103] In the embodiment of the present application, after obtaining the similarity between the behavior index system and the evaluation index system, the computer device may further determine whether the similarity is greater than a preset similarity threshold.

[0104] S403: Determine whether the recognition result indicates that the object to be recognized is a target object.

[0105] The preset similarity threshold is a threshold set in advance according to the requirements. The target object is an illegal object.

[0106] In the embodiment of the present application, if the similarity is greater than a preset similarity threshold, it is determined that the recognition result indicates that the object to be recognized is a target object.

[0107] S404: Determine that the recognition result indicates that the object to be recognized is not a target object.

[0108] Among them, non-target objects are non-illegal objects.

[0109] In the embodiment of the present application, if the similarity is not greater than a preset similarity threshold, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0110] In the method described in the embodiment of the present application, since the behavior index system and the evaluation index system represent the characteristics of the object to be identified and the target object respectively, by comparing the similarity of multiple characteristics, it is possible to accurately determine whether the object to be identified meets the characteristics of the target object. Moreover, since the behavior index system contains data of multiple dimensions, by comprehensively considering the data of multiple dimensions, the characteristics of the object to be identified can be more comprehensively and accurately evaluated, thereby improving the accuracy of identification.

[0111] In one embodiment, a specific implementation method for determining the similarity between the behavior index system and the evaluation index system is also provided, such as Figure 6 As shown, the "determining the similarity between the behavior index system and the evaluation index system" in the above step S401 includes:

[0112] S501, obtaining a first indicator vector corresponding to a behavior indicator system and a second indicator vector corresponding to an evaluation indicator system.

[0113] The first indicator vector is a vector composed of multiple behavioral indicators, which can be a vector composed of multiple first-level behavioral indicators or a vector composed of multiple second-level behavioral indicators. The second indicator vector is a vector composed of multiple standard indicators, which can be a vector composed of multiple first-level standard indicators or a vector composed of multiple second-level standard indicators.

[0114] In the embodiment of the present application, after obtaining the behavior indicator system and the evaluation indicator system, the computer device can take each behavior indicator in the behavior indicator system as a vector value, and then obtain a first indicator vector composed of multiple vector values, and can take each standard indicator in the standard indicator system as a vector value, and then obtain a second indicator vector composed of multiple vector values. Preferably, a vector composed of multiple secondary behavior indicators constitutes the first indicator vector, and a second indicator vector is composed of multiple secondary standard indicators.

[0115] S502: Determine the similarity between the behavior index system and the evaluation index system according to the cosine value between the first index vector and the second index vector.

[0116] In the embodiment of the present application, after the computer device obtains the first indicator vector and the second indicator vector based on the above steps, it can calculate the cosine value between the first indicator vector and the second indicator vector, and analyze the similarity between the behavior indicator system and the evaluation indicator system according to the cosine value. The cosine value between the first indicator vector and the second indicator vector can be determined by the following relationship:

[0117] cos_similarity = (A·B) / (||A|| * ||B||)

[0118] Among them, A is the first indicator vector, B is the second indicator vector, A·B represents the dot product of vector A and vector B, and ||A|| and ||B|| represent the norm (or length) of vector A and vector B. The smaller the angle between the two vectors, the closer the cosine value is to 1, indicating that the two vectors are closer, which means that the similarity between the evaluation index system and the behavior index system is higher. The larger the angle between the two vectors, the further the cosine similarity value is from 1, indicating that the two vectors are farther away, which means that the similarity between the evaluation index system and the behavior index system is lower.

[0119] The method described in the embodiment of the present application determines the similarity between the behavior index system and the evaluation index system through the cosine degree, which can reduce the huge amount of calculation and excessive resource consumption of the machine learning algorithm, improve the efficiency of information processing, and further improve the recognition efficiency. Cosine degree calculation performs well in processing high-dimensional data, because the distance between vectors in high-dimensional space is difficult to calculate, so using the angle to reflect the similarity can improve the calculation efficiency and accuracy.

[0120] In one embodiment, a specific implementation method for identifying an object to be identified is also provided, such as Figure 7 As shown, the above step S203 of "identifying the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain the identification result" includes:

[0121] S601, determine whether the evaluation information under the indicator in the behavior indicator system meets the evaluation rules under the corresponding indicator in the evaluation indicator system, if so, execute S602, if not, execute S603.

[0122] In the embodiment of the present application, after obtaining the behavior indicator system and the evaluation indicator system, the computer device can compare the evaluation information under each behavior indicator in the behavior indicator system with the evaluation rules under the corresponding standard indicators in the evaluation indicator system to obtain the comparison result corresponding to each behavior indicator, and then determine whether the evaluation information under the indicator in the behavior indicator system meets the evaluation rules under the corresponding indicator in the evaluation indicator system based on the comparison result corresponding to each behavior indicator. Specifically, when the number of behavior indicators that meet the evaluation rules reaches a preset number, it can be considered whether the evaluation information under the indicator in the behavior indicator system meets the evaluation rules under the corresponding indicator in the evaluation indicator system.

[0123] S602: Determine whether the recognition result indicates that the object to be recognized is a target object.

[0124] In the embodiment of the present application, if the evaluation information under the indicator in the behavior indicator system satisfies the evaluation rules under the corresponding indicator in the evaluation indicator system, then it is determined that the recognition result indicates that the object to be recognized is the target object.

[0125] S603: Determine that the recognition result indicates that the object to be recognized is not a target object.

[0126] In the embodiment of the present application, if the evaluation information under the indicator in the behavior indicator system does not satisfy the evaluation rules under the corresponding indicator in the evaluation indicator system, it is determined that the recognition result indicates that the object to be recognized is the target object.

[0127] The method described in the embodiment of the present application can reduce uncertainty and duplication of work in the evaluation process and improve evaluation efficiency by standardizing whether the evaluation information meets the evaluation rules.

[0128] In one embodiment, Figure 8 As shown, the above target object recognition method also includes:

[0129] S701, obtaining historical behavior data of multiple violating objects.

[0130] In the embodiment of the present application, the computer device can obtain the historical behavior data of the violating object from the relevant departments through legal means. Optionally, the computer can obtain the historical behavior data of the violating object from the data collected manually or from the data filled in by the violating object. Further, after obtaining the historical behavior data of multiple violating objects, the computer can pre-process the historical behavior data, and the specific pre-processing process may include missing value cleaning, format content cleaning and logical error cleaning. Among them, the process of missing value cleaning may include first determining the missing value range, then removing unnecessary fields, then filling in the missing content, and finally re-taking the data; format content cleaning may include removing data with inconsistent display formats such as time, date, value, full and half-width, removing characters that should not exist in the content, and removing data that does not match the content of the field; logical error cleaning is to remove some data that can directly find problems using simple logical reasoning, to prevent the analysis results from going astray, and may include data deduplication, removal of unreasonable values ​​and correction of contradictory content.

[0131] S702, constructing an evaluation index system based on historical behavior data of multiple violators.

[0132] Among them, the evaluation index system includes multiple first-level standard indicators, multiple second-level standard indicators, and evaluation rules corresponding to each second-level standard indicator. The first-level standard indicators include the time when the violation occurred, the transaction amount involved in the violation, the transaction object information of the violation, and the personal information of the violation object. The second-level standard indicators are sub-indicators under each first-level standard indicator. Specifically, the time when the violation occurred includes at least one of the frequency of special time periods, high-frequency time periods, and abnormal profit frequency; the transaction amount involved in the violation includes at least one of the frequency of special amounts and abnormal amounts in profitable time periods; the transaction object information of the violation includes the high-frequency occurrence of special amounts of many-to-one payees, and the number of complaints or reports from payees; the personal information of the violator includes at least one of the number of abnormal personal behaviors, the number of family adjustment behaviors, the number of browsing bad websites, and the number of publishing bad remarks.

[0133] In the embodiment of the present application, after obtaining the historical behavior data of multiple illegal objects, the computer device can classify the historical behavior data of the multiple illegal objects to obtain multiple first-level standard indicators, and then classify the historical behavior data under each first-level standard indicator by a second-level standard indicator to obtain multiple second-level standard indicators, and then perform statistical analysis on the historical behavior data under each standard indicator to obtain evaluation information corresponding to each indicator. Then, after obtaining the historical behavior data under each standard indicator, the computer device can perform statistical analysis on the historical behavior data of the illegal objects under each indicator to obtain evaluation rules corresponding to each indicator, and then construct an evaluation index system according to the first-level standard indicator, multiple second-level standard indicators, and the evaluation rules corresponding to each second-level standard indicator. Specifically, the evaluation index system can be shown in the following table.

[0134]

[0135] The method described in the embodiments of the present application can comprehensively evaluate the behavior of the violating object through multi-level indicator classification, rather than relying solely on a single indicator, thereby improving recognition accuracy.

[0136] Based on all the above embodiments, a method for identifying a target object is also provided. Fig. 9 As shown, the method includes:

[0137] S801, obtaining historical behavior data of the object to be identified.

[0138] S802, classifying the historical behavior data into primary behavior indicators to obtain a plurality of primary behavior indicators.

[0139] S803, classifying the historical behavior data under each first-level behavior indicator into second-level behavior indicators to obtain a plurality of second-level behavior indicators.

[0140] S804, statistically analyzing the historical behavior data under each secondary behavior indicator to obtain evaluation information corresponding to each secondary behavior indicator.

[0141] S805: construct a behavior indicator system based on the multiple secondary behavior indicators and the evaluation information corresponding to each secondary behavior indicator, wherein the behavior indicator system includes the corresponding relationship between the behavior indicators and the evaluation information.

[0142] S806, obtaining a first indicator vector corresponding to the behavior indicator system and a second indicator vector corresponding to the evaluation indicator system.

[0143] S807: Determine the similarity between the behavior index system and the evaluation index system according to the cosine value between the first index vector and the second index vector.

[0144] S808, determining whether the similarity is greater than a preset similarity threshold, if so, executing S809, if not, executing S810.

[0145] S809: Determine that the recognition result indicates that the object to be recognized is a target object.

[0146] S810, determining that the recognition result indicates that the object to be recognized is not a target object.

[0147] S811, determine whether the evaluation information under the indicator in the behavior indicator system meets the evaluation rules under the corresponding indicator in the evaluation indicator system, if so, execute S812, if not, execute S813.

[0148] S812: Determine whether the recognition result indicates that the object to be recognized is a target object.

[0149] S813, determining that the recognition result indicates that the object to be recognized is not a target object.

[0150] The methods described in the above steps are all described in the above embodiments. Please refer to the above description for details and will not be repeated here.

[0151] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0152] Based on the same inventive concept, the embodiment of the present application also provides a target object recognition device for implementing the target object recognition method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the device for recognizing one or more target objects provided below can refer to the limitations of the target object recognition method above, and will not be repeated here.

[0153] In one embodiment, Fig.10 As shown, a target object recognition device is provided, comprising:

[0154] The first acquisition module 11 is used to acquire historical behavior data of the object to be identified.

[0155] The first construction module 12 is used to construct a behavior indicator system of the object to be identified based on historical behavior data.

[0156] The identification module 13 is used to identify the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain the identification result.

[0157] In one embodiment, the building block 12 includes:

[0158] The classification unit is used to classify the historical behavior data into indicators to obtain multiple behavior indicators.

[0159] The analysis unit is used to perform statistical analysis on the historical behavior data under each behavior indicator to obtain evaluation information corresponding to each behavior indicator.

[0160] The construction unit is used to construct a behavior indicator system according to multiple behavior indicators and evaluation information corresponding to each behavior indicator; the behavior indicator system includes the corresponding relationship between the behavior indicators and the evaluation information.

[0161] In one embodiment, the above classification unit includes:

[0162] The first classification subunit is used to classify the historical behavior data into first-level behavior indicators to obtain multiple first-level behavior indicators.

[0163] The second classification subunit is used to classify the historical behavior data under each first-level behavior indicator into second-level behavior indicators to obtain multiple second-level behavior indicators.

[0164] In one embodiment, the identification module 13 includes:

[0165] The first determining unit is used to determine the similarity between the behavior index system and the evaluation index system.

[0166] The second determining unit is used to determine that the recognition result indicates that the object to be recognized is a target object when is greater than .

[0167] The third determining unit is configured to determine, when the value is not greater than , that the recognition result indicates that the object to be recognized is not the target object.

[0168] In one embodiment, the first determining unit includes:

[0169] The acquisition subunit is used to acquire a first indicator vector corresponding to the behavior indicator system and a second indicator vector corresponding to the evaluation indicator system.

[0170] The determination subunit is used to determine the similarity between the behavior index system and the evaluation index system according to the cosine value between the first index vector and the second index vector.

[0171] In one embodiment, the identification module 13 further includes:

[0172] The fourth determining unit is used to determine whether the evaluation information under the indicator in the behavior indicator system satisfies the evaluation rules under the corresponding indicator in the evaluation indicator system.

[0173] The fifth determining unit is used to determine that the recognition result indicates that the object to be recognized is a target object if the conditions are met.

[0174] The sixth determining unit is used to determine that the recognition result indicates that the object to be recognized is not the target object when the condition is not satisfied.

[0175] In one embodiment, Fig.11 As shown, the above-mentioned target object recognition device also includes:

[0176] The second acquisition module 14 is used to acquire historical behavior data of multiple violating objects.

[0177] The second construction module 15 is used to construct an evaluation index system based on the historical behavior data of multiple violators; the evaluation index system includes multiple first-level standard indicators, multiple second-level standard indicators, and evaluation rules corresponding to each second-level standard indicator.

[0178] Each module in the above-mentioned target object recognition device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0179] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0180] Obtain historical behavior data of the object to be identified;

[0181] Construct a behavioral indicator system for the object to be identified based on historical behavioral data;

[0182] According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain the identification result.

[0183] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0184] Classify historical behavior data into indicators to obtain multiple behavior indicators;

[0185] Conduct statistical analysis on the historical behavior data under each behavior indicator to obtain the evaluation information corresponding to each behavior indicator;

[0186] A behavior indicator system is constructed based on multiple behavior indicators and evaluation information corresponding to each behavior indicator; the behavior indicator system includes the corresponding relationship between the behavior indicators and the evaluation information.

[0187] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0188] Classifying the historical behavior data into first-level behavior indicators to obtain multiple first-level behavior indicators;

[0189] The historical behavior data under each first-level behavior indicator is classified into second-level behavior indicators to obtain multiple second-level behavior indicators.

[0190] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0191] Determine the similarity between the behavioral indicator system and the evaluation indicator system;

[0192] If the similarity is greater than a preset similarity threshold, then determining that the recognition result indicates that the object to be recognized is the target object;

[0193] If the similarity is not greater than the preset similarity threshold, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0194] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0195] Obtaining a first indicator vector corresponding to the behavior indicator system and a second indicator vector corresponding to the evaluation indicator system;

[0196] The similarity between the behavior index system and the evaluation index system is determined according to the cosine value between the first index vector and the second index vector.

[0197] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0198] Determine whether the evaluation information under the indicators in the behavior indicator system meets the evaluation rules under the corresponding indicators in the evaluation indicator system;

[0199] If satisfied, it is determined that the recognition result indicates that the object to be recognized is the target object;

[0200] If not, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0201] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0202] Obtain historical behavior data of multiple offenders;

[0203] An evaluation index system is constructed based on historical behavior data of multiple violators; the evaluation index system includes multiple first-level standard indicators, multiple second-level standard indicators, and evaluation rules corresponding to each second-level standard indicator.

[0204] The above embodiment provides a computer device, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0205] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0206] Obtain historical behavior data of the object to be identified;

[0207] Construct a behavioral indicator system for the object to be identified based on historical behavioral data;

[0208] According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain the identification result.

[0209] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0210] Classify historical behavior data into indicators to obtain multiple behavior indicators;

[0211] Conduct statistical analysis on the historical behavior data under each behavior indicator to obtain the evaluation information corresponding to each behavior indicator;

[0212] A behavior indicator system is constructed based on multiple behavior indicators and evaluation information corresponding to each behavior indicator; the behavior indicator system includes the corresponding relationship between the behavior indicators and the evaluation information.

[0213] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0214] Classifying the historical behavior data into first-level behavior indicators to obtain multiple first-level behavior indicators;

[0215] The historical behavior data under each first-level behavior indicator is classified into second-level behavior indicators to obtain multiple second-level behavior indicators.

[0216] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0217] Determine the similarity between the behavioral indicator system and the evaluation indicator system;

[0218] If the similarity is greater than a preset similarity threshold, then determining that the recognition result indicates that the object to be recognized is the target object;

[0219] If the similarity is not greater than the preset similarity threshold, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0220] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0221] Obtaining a first indicator vector corresponding to the behavior indicator system and a second indicator vector corresponding to the evaluation indicator system;

[0222] The similarity between the behavior index system and the evaluation index system is determined according to the cosine value between the first index vector and the second index vector.

[0223] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0224] Determine whether the evaluation information under the indicators in the behavior indicator system meets the evaluation rules under the corresponding indicators in the evaluation indicator system;

[0225] If satisfied, it is determined that the recognition result indicates that the object to be recognized is the target object;

[0226] If not, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0227] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0228] Obtain historical behavior data of multiple offenders;

[0229] An evaluation index system is constructed based on historical behavior data of multiple violators; the evaluation index system includes multiple first-level standard indicators, multiple second-level standard indicators, and evaluation rules corresponding to each second-level standard indicator.

[0230] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0231] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0232] Obtain historical behavior data of the object to be identified;

[0233] Construct a behavioral indicator system for the object to be identified based on historical behavioral data;

[0234] According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain the identification result.

[0235] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0236] Classify historical behavior data into indicators to obtain multiple behavior indicators;

[0237] Conduct statistical analysis on the historical behavior data under each behavior indicator to obtain the evaluation information corresponding to each behavior indicator;

[0238] A behavior indicator system is constructed based on multiple behavior indicators and evaluation information corresponding to each behavior indicator; the behavior indicator system includes the corresponding relationship between the behavior indicators and the evaluation information.

[0239] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0240] Classifying the historical behavior data into first-level behavior indicators to obtain multiple first-level behavior indicators;

[0241] The historical behavior data under each first-level behavior indicator is classified into second-level behavior indicators to obtain multiple second-level behavior indicators.

[0242] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0243] Determine the similarity between the behavioral indicator system and the evaluation indicator system;

[0244] If the similarity is greater than a preset similarity threshold, then determining that the recognition result indicates that the object to be recognized is the target object;

[0245] If the similarity is not greater than the preset similarity threshold, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0246] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0247] Obtaining a first indicator vector corresponding to the behavior indicator system and a second indicator vector corresponding to the evaluation indicator system;

[0248] The similarity between the behavior index system and the evaluation index system is determined according to the cosine value between the first index vector and the second index vector.

[0249] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0250] Determine whether the evaluation information under the indicators in the behavior indicator system meets the evaluation rules under the corresponding indicators in the evaluation indicator system;

[0251] If satisfied, it is determined that the recognition result indicates that the object to be recognized is the target object;

[0252] If not, it is determined that the recognition result indicates that the object to be recognized is not the target object.

[0253] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0254] Obtain historical behavior data of multiple offenders;

[0255] An evaluation index system is constructed based on historical behavior data of multiple violators; the evaluation index system includes multiple first-level standard indicators, multiple second-level standard indicators, and evaluation rules corresponding to each second-level standard indicator.

[0256] The above embodiment provides a computer program product, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0257] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0258] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0259] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for identifying a target object, characterized in that: The method comprises: Obtain historical behavior data of the object to be identified; Constructing a behavior indicator system of the object to be identified according to the historical behavior data; According to the behavior index system and the evaluation index system, the object to be identified is identified to obtain an identification result.

2. The method according to claim 1, characterized in that: The step of constructing the behavior indicator system of the object to be identified based on the historical behavior data includes: Classifying the historical behavior data into indicators to obtain multiple behavior indicators; Performing statistical analysis on the historical behavior data under each of the behavior indicators to obtain evaluation information corresponding to each of the behavior indicators; The behavior indicator system is constructed based on the multiple behavior indicators and the evaluation information corresponding to each behavior indicator; the behavior indicator system includes the corresponding relationship between the behavior indicators and the evaluation information.

3. The method according to claim 2, characterized in that The behavior indicators include primary behavior indicators and secondary behavior indicators. The historical behavior data is classified into indicators to obtain multiple behavior indicators, including: Classifying the historical behavior data into primary behavior indicators to obtain a plurality of primary behavior indicators; The historical behavior data under each of the first-level behavior indicators is classified into second-level behavior indicators to obtain a plurality of the second-level behavior indicators.

4. The method according to any one of claims 1 to 3, characterized in that: The step of identifying the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain an identification result includes: Determining the similarity between the behavioral indicator system and the evaluation indicator system; If the similarity is greater than a preset similarity threshold, determining that the recognition result indicates that the object to be recognized is a target object; If the similarity is not greater than a preset similarity threshold, it is determined that the recognition result indicates that the object to be recognized is not a target object.

5. The method according to claim 4, characterized in that Determining the similarity between the behavior index system and the evaluation index system includes: Obtaining a first indicator vector corresponding to the behavior indicator system and a second indicator vector corresponding to the evaluation indicator system; The similarity between the behavior index system and the evaluation index system is determined according to the cosine value between the first index vector and the second index vector.

6. The method according to any one of claims 1 to 3, characterized in that: The step of identifying the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain an identification result includes: Determining whether the evaluation information under the indicator in the behavior indicator system satisfies the evaluation rules under the corresponding indicator in the evaluation indicator system; If satisfied, determining that the recognition result indicates that the object to be recognized is a target object; If not, it is determined that the recognition result indicates that the object to be recognized is not a target object.

7. The method according to claim 1, characterized in that The method further comprises: Obtain historical behavior data of multiple offenders; The evaluation index system is constructed according to the historical behavior data of the multiple violators; the evaluation index system includes multiple first-level standard indicators, multiple second-level standard indicators, and evaluation rules corresponding to each of the second-level standard indicators.

8. A target object recognition device, characterized in that: The device comprises: A first acquisition module is used to acquire historical behavior data of the object to be identified; A first construction module is used to construct a behavior indicator system of the object to be identified based on the historical behavior data; The identification module is used to identify the object to be identified according to the behavior indicator system and the evaluation indicator system to obtain an identification result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images