Target object supervision risk assessment method, device and equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and discloses a monitoring risk assessment method, device and equipment of a target object and a storage medium. The method comprises the steps of preprocessing initial impact factor data of a target object to obtain optimized impact factor data; constructing an initial risk assessment baseline model according to the optimized impact factor data and a machine learning classification algorithm, and performing parameter tuning on the initial risk assessment baseline model to obtain an optimized risk assessment baseline model; inputting the optimized impact factor data into the optimized risk assessment baseline model to obtain initial risk assessment information; and constructing a risk assessment knowledge base, if the initial risk assessment information meets a preset rule of the risk assessment knowledge base, constructing an experience assessment model according to the optimized risk assessment baseline model and the risk assessment knowledge base, and correcting the initial risk assessment information to obtain final risk assessment information. The target object is evaluated by fusing the multi-source information, and the accuracy is high.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for assessing the risk of prison entry of a target object. Background Art

[0002] In today's complex and ever-changing business and social environment, accurate and comprehensive risk assessment of target objects has become an indispensable part of many fields such as project planning and legal compliance.

[0003] Traditional hazard assessment methods often rely on expert experience, historical case comparisons, and simple statistical models. These methods have limitations in data processing, real-time, accuracy, and predictive capabilities, and are difficult to cope with the increasingly complex and rapidly changing hazardous environment. In particular, traditional methods are unable to cope with large-scale data sets, nonlinear relationships, and uncertain factors.

[0004] In recent years, with the advancement of technology, the essence of modern information technology has been gradually integrated into the risk assessment method, through the construction of data analysis models, such as machine learning algorithms, deep learning networks, natural language processing, etc. However, the current use of machine learning algorithms for the risk assessment of target objects for prison entry has a relatively single source of information, starting from only one dimension, and conducting a purely data-driven assessment without integrating multi-source information and comprehensive assessment, so the assessment effect is still not ideal. Summary of the invention

[0005] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method, device, equipment and storage medium for assessing the risk of entry into prison of a target object.

[0006] The present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present disclosure provides a method for assessing the risk of prison admission of a target object, the method comprising:

[0008] Acquire initial impact factor data of the target object, and preprocess the initial impact factor data to obtain optimized impact factor data;

[0009] According to the optimized influencing factor data and using a machine learning classification algorithm, an initial risk assessment baseline model is constructed, and parameters of the initial risk assessment baseline model are tuned to obtain an optimized risk assessment baseline model;

[0010] Inputting the optimized influencing factor data into the optimized risk assessment baseline model, and outputting initial risk assessment information of the target object through the optimized risk assessment baseline model;

[0011] Obtaining comprehensive assessment data of the target object, constructing a risk assessment knowledge base based on the comprehensive assessment data, and determining whether the initial risk assessment information satisfies preset rules of the risk assessment knowledge base;

[0012] If the initial risk assessment information meets the preset rules of the risk assessment knowledge base, an empirical assessment model is constructed according to the optimized risk assessment baseline model and the risk assessment knowledge base, and the initial risk assessment information is corrected by the empirical assessment model to obtain the final risk assessment information of the target object.

[0013] Optionally, preprocessing the initial impact factor data to obtain optimized impact factor data includes:

[0014] Performing data cleaning on the initial impact factor data, removing duplicate data, missing data and abnormal data in the initial impact factor data, and obtaining cleaned impact factor data;

[0015] Integrating the cleaning impact factor data in a unified format to obtain integrated impact factor data;

[0016] The continuous variables in the integrated impact factor data are standardized, and the categorical variables in the integrated impact factor data are discretized to obtain the optimized impact factor data.

[0017] Optionally, constructing an initial risk assessment baseline model based on the optimized impact factor data and using a machine learning classification algorithm includes:

[0018] The optimized influencing factor data is divided into training set data and test set data according to a preset ratio, and the training set data is used to train the machine learning classification algorithm to obtain the initial risk assessment baseline model;

[0019] The step of inputting the optimized influencing factor data into the optimized risk assessment baseline model comprises:

[0020] The test set data is input into the optimized risk assessment baseline model.

[0021] Optionally, the initial risk assessment information includes a plurality of risk factors and their corresponding initial risk levels, and the determining whether the initial risk assessment information satisfies a preset rule of the risk assessment knowledge base includes:

[0022] Extracting the preset rule from the risk assessment knowledge base, wherein the preset rule defines a correspondence between a plurality of risk indicators and a plurality of risk levels;

[0023] Determining whether the risk factor output by the optimized risk assessment baseline model is included in the risk index defined by the preset rule;

[0024] If the risk factors output by the optimized risk assessment baseline model are included in the risk index defined by the preset rule, then determining whether the initial risk level corresponding to each risk factor matches the corresponding risk level in the preset rule;

[0025] If the initial risk levels corresponding to all the risk factors match the corresponding risk levels in the preset rules, it is determined that the initial risk assessment information meets the preset rules of the risk assessment knowledge base.

[0026] Optionally, after determining whether the risk factor output by the optimized risk assessment baseline model is included in the risk index defined by the preset rule, the method further includes:

[0027] If the risk factor output by the optimized risk assessment baseline model is not included in the risk index defined by the preset rule, it is determined that the initial risk assessment information does not meet the preset rule of the risk assessment knowledge base, and the initial risk level is used as the final risk level.

[0028] Optionally, the final risk assessment information includes a plurality of risk factors and their corresponding final risk levels, and the correction of the initial risk assessment information by the empirical assessment model to obtain the final risk assessment information of the target object includes:

[0029] Determining the occurrence frequency and preset weight coefficient of each of the risk factors in the initial risk assessment information in the risk assessment knowledge base;

[0030] The initial risk level of each risk factor is adjusted according to the occurrence frequency of each risk factor in the risk assessment knowledge base and the preset weight coefficient by using a preset adjustment formula to obtain the final risk level corresponding to each risk factor.

[0031] Optionally, the preset adjustment formula is:

[0032] B i =A i +n i α i

[0033] In the formula, B i is the final risk level of the ith risk factor, A i is the initial risk level of the ith risk factor, n iis the occurrence frequency of the ith risk factor in the risk assessment knowledge base, α i is the preset weight coefficient of the ith risk factor in the risk assessment knowledge base.

[0034] In a second aspect, an embodiment of the present disclosure provides a device for assessing the risk of entering a prison of a target object, the device comprising:

[0035] A preprocessing module, used to obtain initial impact factor data of a target object, and preprocess the initial impact factor data to obtain optimized impact factor data;

[0036] A construction module is used to construct an initial risk assessment baseline model based on the optimized influencing factor data and using a machine learning classification algorithm, and to perform parameter tuning on the initial risk assessment baseline model to obtain an optimized risk assessment baseline model;

[0037] An evaluation module, used for inputting the optimized influencing factor data into the optimized risk assessment baseline model, and outputting initial risk assessment information of the target object through the optimized risk assessment baseline model;

[0038] A judgment module, used to obtain comprehensive assessment data of the target object, build a risk assessment knowledge base according to the comprehensive assessment data, and judge whether the initial risk assessment information meets the preset rules of the risk assessment knowledge base;

[0039] A correction module is used to construct an empirical assessment model based on the optimized risk assessment baseline model and the risk assessment knowledge base if the initial risk assessment information meets the preset rules of the risk assessment knowledge base, and to correct the initial risk assessment information through the empirical assessment model to obtain the final risk assessment information of the target object.

[0040] In a third aspect, a computer device is provided in an embodiment of the present disclosure, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the method for assessing the risk of entry into prison of a target object described in the first aspect when executing the computer program.

[0041] In a fourth aspect, a computer-readable storage medium is provided in an embodiment of the present disclosure, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for assessing the risk of entry into prison of a target object described in the first aspect are implemented.

[0042] Beneficial effects of this application:

[0043] The method for assessing the risk of entry of a target object provided by an embodiment of the present application is to obtain the initial influencing factor data of the target object, and pre-process the initial influencing factor data to obtain the optimized influencing factor data; construct an initial risk assessment baseline model based on the optimized influencing factor data and using a machine learning classification algorithm, and perform parameter tuning on the initial risk assessment baseline model to obtain an optimized risk assessment baseline model; input the optimized influencing factor data into the optimized risk assessment baseline model, and output the initial risk assessment information of the target object through the optimized risk assessment baseline model; obtain the comprehensive assessment data of the target object, construct a risk assessment knowledge base based on the comprehensive assessment data, and determine whether the initial risk assessment information meets the preset rules of the risk assessment knowledge base; if the initial risk assessment information meets the preset rules of the risk assessment knowledge base, then construct an empirical assessment model based on the optimized risk assessment baseline model and the risk assessment knowledge base, and correct the initial risk assessment information through the empirical assessment model to obtain the final risk assessment information of the target object. The present application conducts a comprehensive assessment of the target object by fusing multi-source information, so that the assessment result is more comprehensive, efficient and accurate.

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work. In each of the drawings, similar components are numbered similarly.

[0046] Figure 1 A flowchart of a method for assessing the risk of prison admission of a target object provided in an embodiment of the present application is shown;

[0047] Figure 2 A flowchart showing another method for assessing the risk of prison admission of a target object provided in an embodiment of the present application is shown;

[0048] Figure 3 A schematic diagram of the structure of a device for assessing the risk of entering a prison of a target object provided in an embodiment of the present application is shown;

[0049] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0050] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0051] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. In contrast, when an element is referred to as being "directly on" another element, there is no intermediate element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0052] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0053] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of the template are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0055] Example 1

[0056] like Figure 1 FIG. 1 is a flowchart of a method for assessing the risk of imprisonment of a target object in an embodiment of the present application. The method for assessing the risk of imprisonment of a target object provided in an embodiment of the present application includes the following steps:

[0057] Step S110, obtaining initial impact factor data of the target object, and preprocessing the initial impact factor data to obtain optimized impact factor data.

[0058] In this embodiment, initial impact factor data of a target object is first obtained. The target object is an object for risk assessment. The initial impact factor data is key impact data of multiple dimensions related to the risk assessment of the target object.

[0059] After obtaining the initial impact factor data, a series of data preprocessing operations are performed on the initial impact factor data, including: first, the initial impact factor data is cleaned, the duplicate data in the initial impact factor data is removed, and the rows or columns containing missing data (if the proportion of missing data is very high and has little impact on the model) are filled with the mean, median, mode or predicted value, and then the abnormal data are identified and deleted using methods such as box plots and IQR, and the data are corrected using quantile replacement and capping methods. After the cleaning is completed, the cleaned impact factor data is obtained; then the cleaned impact factor data is integrated in a unified format to ensure that the format of all data is unified for subsequent processing, and the integrated impact factor data is obtained; finally, the continuous variables in the integrated impact factor data are standardized (such as Z-score standardization or Min-Max normalization), and the categorical variables in the integrated impact factor data are discretized (for unordered categorical variables, One-Hot Encoding or Label Encoding is used, and for ordered categorical variables, they can be directly mapped to integers), which helps to improve the performance and stability of subsequent machine learning classification algorithms, and finally obtain the preprocessed optimized impact factor data.

[0060] The above method can significantly improve the accuracy and consistency of data by collecting multi-source data and performing a series of preprocessing on the multi-source data, providing a more reliable basis for subsequent model predictions.

[0061] Step S120, constructing an initial risk assessment baseline model based on the optimized influencing factor data and using a machine learning classification algorithm, and performing parameter tuning on the initial risk assessment baseline model to obtain an optimized risk assessment baseline model.

[0062] Specifically, the optimized impact factor data is randomly divided into training set data and test set data according to a preset ratio, for example, training set data: test set data = 4:1, and random seeds are used to ensure the repeatability of the results. Then, a suitable machine learning classification algorithm (such as logistic regression, decision tree, random forest, gradient boosting machine, etc.) is determined, and the training set data is used to train the machine learning classification algorithm to obtain the initial risk assessment baseline model.

[0063] Preferably, after obtaining the initial hazard assessment baseline model, the grid parameter adjustment method is used to tune the parameters of the initial hazard assessment baseline model, that is, the optimal parameter setting is found by traversing multiple parameter combinations, which can be achieved through Scikit-learn's GridSearchCV or RandomizedSearchCV. In addition, during the grid parameter adjustment process, cross-validation (such as K-fold cross-validation) is used to evaluate the model performance under different parameter combinations to improve the reliability of the results, and a variety of model performance indicators (such as accuracy, precision, recall, etc.) are combined to select the model with the best performance, and finally obtain the optimized hazard assessment baseline model.

[0064] The above method provides a basis for subsequent model correction by constructing an initial risk assessment baseline model, thereby improving the efficiency and accuracy of risk assessment.

[0065] Step S130: input the optimized influencing factor data into the optimized risk assessment baseline model, and output the initial risk assessment information of the target object through the optimized risk assessment baseline model.

[0066] It can be understood that the test set data segmented in step S120 is input into the optimized risk assessment baseline model, and the initial risk assessment information of the target object is output by the optimized risk assessment baseline model. The initial risk assessment information includes multiple risk factors and their corresponding initial risk levels.

[0067] The above method can provide accurate preliminary hazard prediction results by optimizing the hazard assessment baseline model, which can serve as the basis for constructing subsequent empirical assessment models, thereby improving the accuracy and rationality of hazard assessment.

[0069] Step S140, obtaining comprehensive assessment data of the target object, constructing a risk assessment knowledge base according to the comprehensive assessment data, and determining whether the initial risk assessment information satisfies preset rules of the risk assessment knowledge base.

[0070] Preferably, comprehensive assessment data of the target object is obtained, and a risk assessment knowledge base is constructed based on the comprehensive assessment data. Understandably, based on optimizing the risk assessment baseline model, this embodiment integrates the risk assessment knowledge base into the assessment, adjusts the risk factor weights, and improves the model accuracy.

[0071] In an optional embodiment, if Figure 2 As shown, step S140 also includes:

[0072] Step S141, extracting the preset rule from the risk assessment knowledge base, wherein the preset rule defines a correspondence between a plurality of risk indicators and a plurality of risk levels;

[0073] Step S142, determining whether the risk factor output by the optimized risk assessment baseline model is included in the risk index defined by the preset rule;

[0074] Step S143, if the risk factors output by the optimized risk assessment baseline model are included in the risk index defined by the preset rule, then determining whether the initial risk level corresponding to each risk factor matches the corresponding risk level in the preset rule;

[0075] Step S144: If the initial risk levels corresponding to all the risk factors match the corresponding risk levels in the preset rules, it is determined that the initial risk assessment information satisfies the preset rules of the risk assessment knowledge base.

[0076] Understandably, the specific judgment method is as follows:

[0077] (1) First, preset rules are extracted from the risk assessment knowledge base, wherein the preset rules define the correspondence between multiple risk indicators and multiple risk levels. These rules are pre-defined based on historical data, expert experience or industry standards, and are used to guide how to determine the risk level based on specific risk indicators;

[0078] (2) Next, the risk factors output by the optimized risk assessment baseline model are compared with the risk indicators defined by the preset rules to determine whether the risk factors output by the optimized risk assessment baseline model are included in the risk indicators defined by the preset rules. The purpose of this step is to confirm whether the risk factors output by the optimized risk assessment baseline model are all important factors that need to be considered in the assessment process, that is, to confirm the validity of the model output;

[0079] (3) If the risk factors output by the optimized risk assessment baseline model are included in the risk indicators defined by the preset rules, it is necessary to further determine whether the initial risk level assigned to each risk factor matches the corresponding risk level in the preset rules. This step is the core risk assessment process, which quantitatively evaluates the risk factors based on the preset rules to ensure that the assessment results are consistent with the expected risk level;

[0080] (4) Finally, if the initial hazard levels corresponding to all hazard factors match the corresponding hazard levels in the preset rules, it can be determined that the initial hazard assessment information meets the preset rules of the risk assessment knowledge base, which means that the results of the initial hazard assessment are valid and meet the industry or organizational standards, and can be used as the basis for subsequent decision-making or hazard management;

[0081] (5) If the risk factor output by the optimized risk assessment baseline model is not included in the risk index defined by the preset rules, it is determined that the initial risk assessment information does not meet the preset rules of the risk assessment knowledge base, which means that the assessment of the optimized risk assessment baseline model exceeds the coverage of the risk assessment knowledge base, or the risk assessment knowledge base itself is insufficient. In this case, in order to maintain the continuity of the risk assessment, the initial risk level can be directly used as the final risk level.

[0082] The above method not only relies on the initial risk assessment information output by optimizing the risk assessment baseline model, but also combines the risk assessment knowledge base and its preset rules, integrates the expert assessment experience, and realizes the comprehensive control of risk assessment. At the same time, for situations that do not meet the rules, reasonable processing solutions are also given to ensure the smooth progress of risk assessment work.

[0084] Step S150, if the initial risk assessment information meets the preset rules of the risk assessment knowledge base, an empirical assessment model is constructed according to the optimized risk assessment baseline model and the risk assessment knowledge base, and the initial risk assessment information is corrected by the empirical assessment model to obtain the final risk assessment information of the target object.

[0085] It should be noted that when the initial hazard assessment information meets the preset rules of the risk assessment knowledge base, it is first necessary to determine the frequency of occurrence and the preset weight coefficient of each hazard factor in the initial hazard assessment information in the risk assessment knowledge base, and then use the preset adjustment formula to automatically adjust and correct the initial hazard level of each hazard factor based on the frequency of occurrence and the preset weight coefficient of each hazard factor in the risk assessment knowledge base to obtain the final hazard level of each hazard factor. Each hazard factor and its corresponding final hazard level form the final hazard assessment information.

[0086] Among them, the preset adjustment formula is:

[0087] B i =A i +n i α i

[0088] In the formula, B iis the final risk level of the ith risk factor, A i is the initial risk level of the ith risk factor, n i is the frequency of occurrence of the ith risk factor in the risk assessment knowledge base, α i is the preset weight coefficient of the ith risk factor in the risk assessment knowledge base.

[0089] The above method realizes knowledge fusion and complementarity by combining the optimized hazard assessment baseline model with the risk assessment knowledge base. The optimized hazard assessment baseline model provides a data-driven hazard assessment framework, while the risk assessment knowledge base provides experience- and rule-based hazard assessment knowledge. The combination of the two can more comprehensively assess the hazard status of the target object, thereby improving the accuracy and reliability of hazard assessment.

[0090] The method for assessing the risk of entry of a target object provided by an embodiment of the present application is to obtain the initial influencing factor data of the target object, and pre-process the initial influencing factor data to obtain the optimized influencing factor data; construct an initial risk assessment baseline model based on the optimized influencing factor data and using a machine learning classification algorithm, and perform parameter tuning on the initial risk assessment baseline model to obtain an optimized risk assessment baseline model; input the optimized influencing factor data into the optimized risk assessment baseline model, and output the initial risk assessment information of the target object through the optimized risk assessment baseline model; obtain the comprehensive assessment data of the target object, construct a risk assessment knowledge base based on the comprehensive assessment data, and determine whether the initial risk assessment information meets the preset rules of the risk assessment knowledge base; if the initial risk assessment information meets the preset rules of the risk assessment knowledge base, then construct an empirical assessment model based on the optimized risk assessment baseline model and the risk assessment knowledge base, and correct the initial risk assessment information through the empirical assessment model to obtain the final risk assessment information of the target object. The present application conducts a comprehensive assessment of the target object by fusing multi-source information, so that the assessment result is more comprehensive, efficient and accurate.

[0091] Example 2

[0092] like Figure 3 FIG. 1 is a schematic diagram of a device 300 for assessing the risk of entering a prison of a target object in an embodiment of the present application, and the device includes:

[0093] A preprocessing module 310 is used to obtain initial impact factor data of a target object and preprocess the initial impact factor data to obtain optimized impact factor data;

[0094] A construction module 320 is used to construct an initial risk assessment baseline model based on the optimized influencing factor data and using a machine learning classification algorithm, and to perform parameter tuning on the initial risk assessment baseline model to obtain an optimized risk assessment baseline model;

[0095] An evaluation module 330, configured to input the optimized influencing factor data into the optimized risk assessment baseline model, and output initial risk assessment information of the target object through the optimized risk assessment baseline model;

[0096] A judgment module 340 is used to obtain comprehensive assessment data of the target object, construct a risk assessment knowledge base according to the comprehensive assessment data, and judge whether the initial risk assessment information meets the preset rules of the risk assessment knowledge base;

[0097] The correction module 350 is used to construct an empirical assessment model based on the optimized risk assessment baseline model and the risk assessment knowledge base if the initial risk assessment information meets the preset rules of the risk assessment knowledge base, and to correct the initial risk assessment information through the empirical assessment model to obtain the final risk assessment information of the target object.

[0098] The device for assessing the risk of prison entry of a target object provided in the embodiment of the present application performs a comprehensive assessment of the target object by fusing multi-source information, so that the assessment result is more comprehensive, efficient and accurate.

[0099] Example 3

[0100] The present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0101] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0102] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0103] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D slot compatibility test memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the slot compatibility test method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0104] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other target object entry risk assessment chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the computer-readable instructions or process data stored in the memory 41, such as running the computer-readable instructions of the slot compatibility test method.

[0105] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0106] The computer device provided in this embodiment can execute the above-mentioned method for assessing the risk of prison entry of a target object. The method for assessing the risk of prison entry of a target object here can be the method for assessing the risk of prison entry of a target object in each of the above-mentioned embodiments.

[0107] Example 4

[0108] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for assessing the risk of entry into prison of a target object in the embodiment are implemented.

[0109] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, referred to as SMC), a secure digital (Secure Digital, referred to as SD) card, a flash card, etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on the computer device. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0110] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow chart, and the combination of boxes in the structure diagram and / or the flow chart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] In addition, the functional modules or units in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0112] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or partly contributed to the prior art or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium can be a non-volatile storage medium or a volatile storage medium. For example, the storage medium can be: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes.

[0113] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for assessing the risk of imprisonment of a target subject, characterized in that: The method comprises: Acquire initial impact factor data of the target object, and preprocess the initial impact factor data to obtain optimized impact factor data; According to the optimized influencing factor data and using a machine learning classification algorithm, an initial risk assessment baseline model is constructed, and parameters of the initial risk assessment baseline model are tuned to obtain an optimized risk assessment baseline model; Inputting the optimized influencing factor data into the optimized risk assessment baseline model, and outputting initial risk assessment information of the target object through the optimized risk assessment baseline model; Obtaining comprehensive assessment data of the target object, constructing a risk assessment knowledge base based on the comprehensive assessment data, and determining whether the initial risk assessment information satisfies preset rules of the risk assessment knowledge base; If the initial risk assessment information meets the preset rules of the risk assessment knowledge base, an empirical assessment model is constructed according to the optimized risk assessment baseline model and the risk assessment knowledge base, and the initial risk assessment information is corrected by the empirical assessment model to obtain the final risk assessment information of the target object.

2. The method for assessing the risk of imprisonment of a target subject according to claim 1, characterized in that: The preprocessing of the initial impact factor data to obtain optimized impact factor data includes: Performing data cleaning on the initial impact factor data, removing duplicate data, missing data and abnormal data in the initial impact factor data, and obtaining cleaned impact factor data; Integrating the cleaning impact factor data in a unified format to obtain integrated impact factor data; The continuous variables in the integrated impact factor data are standardized, and the categorical variables in the integrated impact factor data are discretized to obtain the optimized impact factor data.

3. The method for assessing the risk of prison admission of a target subject according to claim 1, characterized in that: The method of constructing an initial risk assessment baseline model based on the optimized impact factor data and using a machine learning classification algorithm includes: The optimized influencing factor data is divided into training set data and test set data according to a preset ratio, and the training set data is used to train the machine learning classification algorithm to obtain the initial risk assessment baseline model; The step of inputting the optimized influencing factor data into the optimized risk assessment baseline model comprises: The test set data is input into the optimized risk assessment baseline model.

4. The method for assessing the risk of prison admission of a target subject according to claim 1, characterized in that: The initial risk assessment information includes a plurality of risk factors and their corresponding initial risk levels, the final risk assessment information includes a plurality of risk factors and their corresponding final risk levels, and the determining whether the initial risk assessment information satisfies the preset rules of the risk assessment knowledge base includes: Extracting the preset rule from the risk assessment knowledge base, wherein the preset rule defines a correspondence between a plurality of risk indicators and a plurality of risk levels; Determining whether the risk factor output by the optimized risk assessment baseline model is included in the risk index defined by the preset rule; If the risk factors output by the optimized risk assessment baseline model are included in the risk index defined by the preset rule, then determining whether the initial risk level corresponding to each risk factor matches the corresponding risk level in the preset rule; If the initial risk levels corresponding to all the risk factors match the corresponding risk levels in the preset rules, it is determined that the initial risk assessment information meets the preset rules of the risk assessment knowledge base.

5. The method for assessing the risk of prison admission of a target subject according to claim 4, characterized in that: After determining whether the risk factor output by the optimized risk assessment baseline model is included in the risk index defined by the preset rule, the method further includes: If the risk factor output by the optimized risk assessment baseline model is not included in the risk index defined by the preset rule, it is determined that the initial risk assessment information does not meet the preset rule of the risk assessment knowledge base, and the initial risk level is used as the final risk level.

6. The method for assessing the risk of prison admission of a target subject according to claim 4, characterized in that: The step of correcting the initial risk assessment information by using the empirical assessment model to obtain final risk assessment information of the target object includes: Determining the occurrence frequency and preset weight coefficient of each of the risk factors in the initial risk assessment information in the risk assessment knowledge base; The initial risk level of each risk factor is adjusted according to the occurrence frequency of each risk factor in the risk assessment knowledge base and the preset weight coefficient by using a preset adjustment formula to obtain the final risk level corresponding to each risk factor.

7. The method for assessing the risk of imprisonment of a target subject according to claim 6, characterized in that: The preset adjustment formula is: B i =A i +n i a i In the formula, B i is the final risk level of the ith risk factor, A i is the initial risk level of the ith risk factor, n i is the occurrence frequency of the ith risk factor in the risk assessment knowledge base, α i is the preset weight coefficient of the ith risk factor in the risk assessment knowledge base.

8. A device for assessing the risk of prison admission of a target object, characterized in that: The device comprises: A preprocessing module, used to obtain initial impact factor data of a target object, and preprocess the initial impact factor data to obtain optimized impact factor data; A construction module is used to construct an initial risk assessment baseline model based on the optimized influencing factor data and using a machine learning classification algorithm, and to perform parameter tuning on the initial risk assessment baseline model to obtain an optimized risk assessment baseline model; An evaluation module, used for inputting the optimized influencing factor data into the optimized risk assessment baseline model, and outputting initial risk assessment information of the target object through the optimized risk assessment baseline model; A judgment module, used to obtain comprehensive assessment data of the target object, build a risk assessment knowledge base according to the comprehensive assessment data, and judge whether the initial risk assessment information meets the preset rules of the risk assessment knowledge base; A correction module is used to construct an empirical assessment model based on the optimized risk assessment baseline model and the risk assessment knowledge base if the initial risk assessment information meets the preset rules of the risk assessment knowledge base, and to correct the initial risk assessment information through the empirical assessment model to obtain the final risk assessment information of the target object.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method for assessing the risk of entry into prison of a target object as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for assessing the risk of entry into prison of a target object according to any one of claims 1 to 7 are implemented.

Images