User information risk identification method and device, computer equipment and storage medium
By constructing a fitness function and global-local search through the butterfly optimization algorithm, the problem of inaccurate customer risk assessment in existing technologies is solved, accurate risk identification and reliability assessment of user information are achieved, and the accuracy of insurance business is improved.
Patent Information
- Application Number
- CN202510672888.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-23
- Publication Date
- 2025-10-17
AI Technical Summary
Existing customer risk assessment technologies rely on statistical analysis and machine learning models, resulting in poor adaptability to emerging risk factors, inaccurate assessment results, and affecting the effective development of insurance business.
The butterfly optimization algorithm is used to construct a fitness function by obtaining key risk indicators. The position of user information in the solution space is updated by combining global search and local search to obtain the optimal representation point. The risk level is judged according to the fitness value to issue an alarm or optimize the fitness function until the preset termination condition is met.
It achieves accurate risk classification and early warning of user information, improves the reliability of risk identification, and ensures the accuracy and effectiveness of insurance business.
Smart Images
Figure CN120807171A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of data processing, and can be applied to the fields of finance and medicine, and in particular relates to a user information risk identification method and device, a computer device and a storage medium. BACKGROUND
[0002] With the rapid development of technology, customer risk assessment plays a crucial role in business processes and is a key cornerstone in the insurance underwriting process. It not only directly determines whether a customer can obtain an underwriting qualification, but also is an important basis for formulating a reasonable premium.
[0003] In financial insurance business, customer risk assessment is influenced by various economic factors and indicators (such as financial status, debt level, business history, etc.), resulting in a decrease in the accuracy of customer risk assessment classification. Similarly, in health and medical insurance, a customer's age, medical history, family history of genetic diseases, etc. will determine the risk of illness and the probability of medical expense expenditure. These information is difficult to effectively quantify, resulting in a decrease in the accuracy of customer medical insurance assessment.
[0004] Although existing customer risk assessment techniques have made some progress, current customer risk assessment usually relies on statistical analysis, machine learning models, or even the judgment of insurance company professionals based on experience, making the assessment process and results still have certain limitations. For example, many existing models rely heavily on historical data, limiting their ability to adapt to emerging risk factors, or the model may perform well on a particular data set but have poor generalization ability on new or different data sets. Thus, the final result of customer risk assessment is not accurate enough, affecting the effective development of insurance business. SUMMARY
[0005] The purpose of the embodiments of the present application is to provide a user information risk identification method, device, computer device and storage medium to solve the problem of inaccurate category identification of input images.
[0006] In a first aspect, the embodiments of the present application provide a user information risk identification method, which adopts the technical solution as follows:
[0007] Obtain a risk key indicator, and construct an fitness function according to the risk key indicator;
[0008] Obtain user information, and calculate a fitness value according to the user information and the fitness function;
[0009] Map the user information to a solution space according to the fitness value, and update the position of the user information in the solution space based on global search and local search to obtain an optimal representation point;
[0010] obtaining a current fitness value of the optimal representation point, and determining whether the current fitness value meets a preset termination condition;
[0011] If the current fitness value meets the preset termination condition, the current fitness value is converted into a risk level corresponding to the user, and a risk alarm is performed according to the risk level.
[0012] If the current fitness value does not meet the preset termination condition, the fitness function is optimized until a fitness value corresponding to the user information after optimization meets the preset termination condition.
[0013] In a second aspect, the embodiments of the present application further provide a user information risk identification device, which adopts the technical scheme as follows:
[0014] A function construction module is configured to obtain a risk key indicator, and construct a fitness function according to the risk key indicator.
[0015] A fitness calculation module is configured to obtain user information, and calculate a fitness value according to the user information and the fitness function.
[0016] A space representation module is configured to map the user information to a solution space according to the fitness value, and update a position of the user information in the solution space based on global search and local search, to obtain an optimal representation point.
[0017] A condition determination module is configured to obtain a current fitness value of the optimal representation point, and determine whether the current fitness value meets a preset termination condition.
[0018] A first processing module is configured to, if the current fitness value meets the preset termination condition, convert the current fitness value into a risk level corresponding to the user, and perform a risk alarm according to the risk level.
[0019] A second processing module is configured to, if the current fitness value does not meet the preset termination condition, optimize the fitness function until a fitness value corresponding to the user information after optimization meets the preset termination condition.
[0020] In a third aspect, the embodiments of the present application further provide a computer device, which adopts the technical scheme as follows:
[0021] A computer device includes a memory and a processor, the memory stores computer readable instructions, and the processor executes the computer readable instructions to realize the steps of the user information risk identification method according to any one of the above.
[0022] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which adopts the technical scheme as follows:
[0023] A computer readable storage medium having stored thereon computer readable instructions which, when executed by a processor, implement the steps of the user information risk identification method according to any one of the above.
[0024] Compared with the prior art, the embodiment of the present application has the following beneficial effects: the embodiment obtains a risk key indicator, constructs a fitness function according to the risk key indicator, obtains user information, calculates a fitness value according to the user information and the fitness function, maps the user information to a solution space according to the fitness value, and updates the position of the user information in the solution space based on global search and local search to obtain an optimal representation point; the current fitness value of the optimal representation point is obtained, and it is judged whether the current fitness value satisfies a preset termination condition; if the current fitness value satisfies the preset termination condition, the current fitness value is converted into a risk level corresponding to the user, and risk warning is performed according to the risk level; if the current fitness value does not satisfy the preset termination condition, the fitness function is optimized until the fitness value corresponding to the user information after optimization satisfies the preset termination condition. Thus, accurate risk classification and early warning of user information are effectively realized, so as to improve the risk identification reliability of user information. BRIEF DESCRIPTION OF DRAWINGS
[0025] In order to more clearly illustrate the schemes in the present application, the drawings needed in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained according to these drawings without creative labor.
[0026] Figure 1 is an exemplary system architecture diagram to which the present application can be applied;
[0027] Figure 2 is a flowchart of an embodiment of the user information risk identification method according to the present application;
[0028] Figure 3 is a structural schematic diagram of an embodiment of the user information risk identification device according to the present application;
[0029] Figure 4 is a structural schematic diagram of an embodiment of the computer device according to the present application. DETAILED DESCRIPTION
[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terms used in the specification are intended to describe the particular embodiments and are not intended to limit the application; the terms "include" and "have" and their any variations used in the specification and the claims and the above description of drawings are intended to cover the non-exclusive inclusion; the terms "first", "second" and the like used in the specification and the claims and the above description of drawings are intended to distinguish different objects, not to describe a particular order.
[0031] Reference herein to "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive or alternative embodiments. It is expressly understood that the embodiments described herein are combinable with each other.
[0032] In order to make the person skilled in the art better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings below.
[0033] As shown in Figure 1 The system architecture 100 can include a terminal device 101, a network 102 and a server 103, and the terminal device 101 can be a notebook computer 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103. The network 102 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0034] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.
[0035] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing, in addition to the notebook computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an electronic book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer and a desktop computer, etc.
[0036] The server 103 can be a server providing various services, for example, a background server providing support for the page displayed on the terminal device 101.
[0037] It should be noted that the user information risk identification method provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the user information risk identification apparatus is generally arranged in a server / terminal device.
[0038] It should be understood that, Figure 1 The number of terminal devices, networks and servers in
[0039] With reference to Figure 2 , a flow chart of one embodiment of the method of user information risk identification according to the present application is shown. The user information risk identification method comprises the following steps:
[0040] Step S10, acquiring a risk key indicator, and constructing a fitness function according to the risk key indicator;
[0041] In the present embodiment, in a financial insurance system, the risk key indicator comprises financial status, debt level, business history, market position, industry risk, legal compliance, historical underwriting and claims, etc., and the fitness function refers to a calculation function constructed according to each risk key indicator, which is used to calculate the fitness value corresponding to the risk key indicator of the user.
[0042] Step S20, acquiring user information, and calculating a fitness value according to the user information and the fitness function;
[0043] In the embodiment, in the financial insurance system, the user information refers to data information collected and acquired for the real situation of a user, and the data content of the user information corresponds to a risk key indicator, that is, the user information includes data such as financial status, debt level, operation history, market position, industry risk, legal compliance, and historical underwriting and claim.
[0044] In step S30, the user information is mapped to a solution space according to the fitness value, and the position of the user information in the solution space is updated based on global search and local search to obtain an optimal representation point.
[0045] In the embodiment, the solution space refers to a solution space in the butterfly optimization algorithm, and the solution space refers to a set of all possible solutions of the butterfly optimization algorithm, and each solution corresponds to a potential optimal position. Global search and local search are two key search strategies in the butterfly optimization algorithm. In the butterfly optimization algorithm, global search and local search are alternately performed rather than sequentially executed completely independently. Specifically, the algorithm determines whether to perform global search or local search in the current iteration by a switching probability p, and the switching probability p is usually set to a high value (such as 0.8), indicating the probability of global search. The butterfly optimization algorithm initially tends to perform global search to quickly explore the solution space. In each iteration, the algorithm generates a random number r (in the range of [0, 1]), and if r < p, global search is performed; otherwise, local search is performed. In the financial insurance system, the optimal representation point is point information representing the accurate risk situation of a user, and the current fitness value of the optimal representation point represents the good or bad risk situation of the user.
[0046] In step S40, the current fitness value of the optimal representation point is obtained, and it is determined whether the current fitness value satisfies a preset termination condition.
[0047] In the embodiment, the optimal representation point is an optimal solution obtained after global search and local search in the solution space of the butterfly optimization algorithm, and the optimal solution is the most accurate risk representation of the user information in the solution space. The current fitness value corresponding to the optimal representation point is the risk representation value corresponding to the user information. The preset termination condition refers to a preset fitness value judgment condition, which can be that the fitness value is updated to a preset maximum iteration number or the fitness value is lower than a preset fitness threshold. In the financial insurance system, the preset termination condition adopts a preset insurance fitness threshold, and the current fitness value of the optimal representation point and the preset insurance fitness threshold are compared. When the current fitness value is greater than the preset fitness threshold, it is determined that the current fitness value does not satisfy the preset termination condition, and when the current fitness value is less than or equal to the preset fitness threshold, it is determined that the current fitness value satisfies the preset termination condition.
[0048] In step S50, if the current fitness value meets the preset termination condition, the current fitness value is converted into a risk level corresponding to the user, and risk warning is performed according to the risk level.
[0049] In this embodiment, the risk level corresponding to the user refers to level information divided according to the risk situation of the user, and corresponding risk warning and reminding are performed through the level information, so as to effectively realize risk situation assessment of the user. In the financial insurance system, the risk level includes low risk, medium risk and high risk, and the corresponding risk warning information is low risk warning information, medium risk warning information and high risk warning information. For example, when the risk level corresponding to the current fitness value is low risk, low risk warning information is generated and sent to the display interface of the financial insurance system for alarm display.
[0050] In step S60, if the current fitness value does not meet the preset termination condition, the fitness function is optimized until the fitness value corresponding to the user information after optimization meets the preset termination condition.
[0051] In this embodiment, the fitness function is provided with an index weight for each risk key indicator, which can be initially set according to historical experience. When the fitness function needs to be optimized, the index weight can be adjusted in size, so as to realize optimization of the fitness function. In the financial insurance system, optimization of the fitness function is automatically performed through setting of an adaptive mechanism. The adaptive mechanism can dynamically adjust the weight according to the fitness value change in the optimization process. For example, if the fitness value change rate of the financial situation in the current fitness value is low, the weight of the financial situation can be increased to realize optimization of the fitness function.
[0052] In this embodiment, the risk key indicator is obtained, the fitness function is constructed according to the risk key indicator, the user information is obtained, the fitness value is calculated according to the user information and the fitness function, the user information is mapped to the solution space according to the fitness value, and the position of the user information in the solution space is updated based on global search and local search to obtain an optimal representation point. The current fitness value of the optimal representation point is obtained, and it is judged whether the current fitness value meets the preset termination condition. If the current fitness value meets the preset termination condition, the current fitness value is converted into a risk level corresponding to the user, and risk warning is performed according to the risk level. If the current fitness value does not meet the preset termination condition, the fitness function is optimized until the fitness value corresponding to the user information after optimization meets the preset termination condition. Thus, accurate risk classification and early warning of the user information are effectively realized, so as to improve the risk identification reliability of the user information.
[0053] The method of the embodiment can be applied to user information risk identification in a financial insurance system. A user uploads user information including data such as financial status, debt level, business history, market position, industry risk, legal compliance, and historical underwriting and claims to the financial insurance system, calculates the fitness value through the system, maps the fitness value to the solution space of the butterfly optimization algorithm, updates the position of the representative point through global search and local search, and obtains the optimal representative point representing the user's risk situation. The optimal representative point is used to judge the corresponding financial risk level of the user, so as to accurately assess the risk level of the user according to the user information. This facilitates subsequent insurance matching according to the risk level.
[0054] In some optional implementation modes of the embodiment, the acquiring of the risk key indicators and the constructing of the fitness function according to the risk key indicators include the following steps:
[0055] Acquiring an indicator extraction identifier and extracting the risk key indicators from the database according to the indicator extraction identifier;
[0056] In the embodiment, the indicator extraction identifier is unique identifier information corresponding to the risk key indicators in the database. The indicator extraction identifier can be a data ID or a UUID. The corresponding risk key indicators are found by traversing and matching in the database by taking the indicator extraction identifier as a query condition.
[0057] Acquiring an indicator weight corresponding to the risk key indicators and constructing the fitness function according to the risk key indicators and the indicator weight.
[0058] In the embodiment, the indicator weight refers to a preset weight value according to the risk key indicators. Each risk key indicator has a corresponding indicator weight. For example, the financial status weight, the debt level weight, the business history weight, the market position weight, the industry risk weight, the legal compliance weight, and the historical underwriting and claims weight. The formula of the fitness function is:
[0059] Fitness(x) = w1·x1 + w2·x2 + … + wn·xn;
[0060] wherein Fitness(x) is the fitness value, wi is the weight of the i th indicator, and xi is the value corresponding to the risk key indicator.
[0061] The embodiment extracts the risk key indicators from the database according to the indicator extraction identifier, acquires an indicator weight corresponding to the risk key indicators, and constructs the fitness function according to the risk key indicators and the indicator weight. Thus, the corresponding fitness function is effectively constructed according to reliable data indicators to facilitate subsequent calculation of the fitness value according to the fitness function.
[0062] In some optional implementations of the embodiment, the obtaining the user information, and calculating the fitness value according to the user information and the fitness function include the following steps.
[0063] The user information is preprocessed to obtain standard user information.
[0064] In the embodiment, the preprocessing of the user information includes data cleaning: removing noise data, filling in missing values, and correcting error data; data standardization: converting data to a unified format, such as normalizing all numerical values to [0, 1] or standardizing to a distribution with a mean of 0 and a standard deviation of 1; and data conversion: converting non-numerical data (such as classification data) into numerical form, for example, by one-hot encoding or the like.
[0065] The standard user information is analyzed according to the risk key indicators to obtain indicator feature values.
[0066] In the embodiment, the feature analysis is to correspond each feature in the standard user information to a risk key indicator, so as to extract the feature value of each indicator. For example, the feature values of the financial condition include the asset-liability ratio, the current ratio, etc.; the feature values of the debt level include the interest coverage ratio, the debt-to-equity ratio, etc.; the feature values of the operating history include the operating period, the historical profitability, etc.; the feature values of the market position include the market share, the brand influence, etc.; the feature values of the industry risk include the industry volatility, the policy influence, etc.; the feature values of the legal compliance include the number of violation records, the legal litigation situation, etc.; and the feature values of the historical underwriting and claim include the claim ratio, the claim amount, etc.
[0067] The indicator feature values are calculated according to the fitness function to obtain the fitness value.
[0068] In the embodiment, the indicator feature values are substituted into the above-mentioned fitness function formula to calculate, so as to effectively calculate the fitness value corresponding to the user information, which represents the risk situation of the user.
[0069] The embodiment preprocesses the user information to obtain standard user information, analyzes the standard user information according to the risk key indicators to obtain indicator feature values, and calculates the indicator feature values according to the fitness function to obtain the fitness value. Thus, the calculation of the fitness value according to the feature values of the user information is effectively realized, so as to facilitate the subsequent mapping of the fitness value in the solution space.
[0070] In some optional implementations of the embodiment, the mapping of the user information to the solution space according to the fitness value and updating the position of the user information in the solution space based on global search and local search to obtain the optimal representation point comprises the following steps:
[0071] Obtaining dimension information corresponding to the user information;
[0072] In the embodiment, each feature (such as financial status, debt level, operation history, etc.) of the user information corresponds to a dimension in the butterfly optimization algorithm, and the dimension information of the user information is the number of the features. For example, if the user information contains 7 features, the dimension of the solution space is 7.
[0073] Defining the dimension of the solution space according to the dimension information, and mapping the user information and the fitness value to the solution space according to the dimension of the solution space to obtain a user representation point;
[0074] In the embodiment, the dimension of the solution space is determined by the number of features of the user information. Each user information is calculated by a fitness function to obtain a fitness value, and the value and the user information form a point in the solution space. The steps of the mapping process are as follows: initializing the feature values of the user information to form an initial population; calculating the fitness value of each user information; mapping the user information and the fitness value to the solution space, each user information corresponding to a point in the solution space, the point in the solution space being the user representation point.
[0075] Taking the user representation point with the lowest fitness value as the global optimal solution, and performing global search on other user representation points according to the global optimal solution to obtain an adjusted representation point;
[0076] In the embodiment, the global optimal solution in the butterfly optimization algorithm refers to the user representation point with the lowest fitness value, and the purpose of the global search is to guide other user representation points to move in a better direction through the global optimal solution. The steps of the global search are as follows: finding the user representation point with the lowest fitness value and taking it as the global optimal solution; performing global search on other user representation points, adjusting the position of the user representation point according to the position of the global optimal solution, and taking the user representation point after the position adjustment as the adjusted representation point.
[0077] Performing local search on the adjusted representation point to obtain the optimal representation point.
[0078] In the embodiment, the purpose of the local search is to further optimize the position of the user representation point on the basis of the global search to find a better solution. The steps of the local search are as follows: performing a local search on the adjusted user representation point, further optimizing the position by random movement or other strategies; repeating the process of global search and local search until a preset ending condition is met, such as reaching a maximum number of iterations or the fitness value no longer changes significantly, and when the preset ending condition is met, the adjusted representation point after the local search is taken as the optimal representation point.
[0079] In the embodiment, the dimension information corresponding to the user information is obtained; the dimension information is used to define the dimension of the solution space, and the user information and the fitness value are mapped to the solution space according to the dimension of the solution space to obtain a user representation point; the user representation point with the lowest fitness value is taken as a global optimal solution, and a global search is performed on other user representation points according to the global optimal solution to obtain an adjusted representation point; a local search is performed on the adjusted representation point to obtain the optimal representation point. Thus, the optimal representation point representing the user risk situation is effectively obtained according to the fitness value corresponding to the user information, so that subsequent corresponding processing can be conveniently performed according to the current fitness value of the optimal representation point.
[0080] In some optional implementation modes of the embodiment, the step of obtaining the current fitness value of the optimal representation point and determining whether the current fitness value meets a preset termination condition includes the following steps:
[0081] obtaining a preset fitness threshold;
[0082] In the embodiment, the preset fitness threshold is a preset judgment threshold, which can be set according to historical data or experience. In the example, the preset fitness threshold is set to 10, which can be set and adjusted according to actual conditions.
[0083] determining whether the current fitness value is less than or equal to the preset fitness threshold;
[0084] In the embodiment, after each iteration, the algorithm compares the calculated current fitness value with the preset fitness threshold to determine whether the current fitness value is less than or equal to the preset fitness threshold.
[0085] If the current fitness value is less than or equal to the preset fitness threshold, it is determined that the current fitness value meets the preset termination condition.
[0086] In the embodiment, if the current fitness value is less than or equal to the preset fitness threshold, the algorithm stops and it is determined that the current fitness value meets the preset termination condition.
[0087] If the current fitness value is greater than the preset fitness threshold, it is determined that the current fitness value does not satisfy the preset termination condition.
[0088] In this embodiment, if the current fitness value is greater than the preset fitness threshold, the algorithm stops, and it is determined that the current fitness value does not satisfy the preset termination condition.
[0089] In this embodiment, the preset fitness threshold is obtained; it is determined whether the current fitness value is less than or equal to the preset fitness threshold; if the current fitness value is less than or equal to the preset fitness threshold, it is determined that the current fitness value satisfies the preset termination condition; and if the current fitness value is greater than the preset fitness threshold, it is determined that the current fitness value does not satisfy the preset termination condition. Thus, the corresponding condition of determining whether the preset termination condition is satisfied according to the current fitness value is effectively realized, so as to facilitate subsequent corresponding processing according to the corresponding condition.
[0090] In some optional implementation modes of this embodiment, the step of converting the current fitness value into a risk level corresponding to the user and performing risk warning according to the risk level includes the following steps:
[0091] A preset risk level mapping table is obtained.
[0092] In this embodiment, the preset risk level mapping table is a rule table for mapping the fitness value range to the specific risk level, which is used to convert the quantized fitness value into an intuitive risk level. The preset risk level mapping table can be set according to historical data or experience. In this embodiment, the mapping relationship between the fitness value range and the risk level in the preset risk level mapping table is as follows: Fitness≤30 corresponds to low risk, 30<Fitness≤60 corresponds to medium risk, and Fitness>60 corresponds to high risk.
[0093] The preset risk level mapping table is mapped and matched according to the current fitness value, to obtain the risk level.
[0094] In this embodiment, the current fitness value is matched with the preset risk level mapping table, the corresponding fitness value range is found, and the risk level is determined. For example, it is assumed that the current fitness value is Fitness=45, and according to the preset risk level mapping table: 30<45≤60, therefore the current risk level is medium risk.
[0095] Risk warning information is generated according to the risk level, and the risk warning information is sent to a preset display interface to perform risk warning and reminding.
[0096] In the embodiment, the corresponding risk warning information is generated according to the risk level, and is sent to a preset display interface (such as a monitoring system, a user interface, a notification system, etc.) for subsequent processing process to take timely measures. For example, the risk level is a medium risk, and the risk warning information is generated according to the risk level: user ID: 123456, the current risk level is a medium risk, and further evaluation is suggested. The risk warning information is sent to a preset display interface (such as a webpage, a mobile application, an email, etc.).
[0097] In the embodiment, a preset risk level mapping table is obtained; the preset risk level mapping table is mapped and matched according to the current fitness value, to obtain the risk level; and the risk warning information is generated according to the risk level, and is sent to a preset display interface for risk warning reminding. Thus, the corresponding risk level mapping is effectively realized according to the current fitness value corresponding to the user information, to determine the risk level corresponding to the user and perform alarm reminding.
[0098] In some optional implementation manners of the embodiment, the fitness function is optimized until the fitness value corresponding to the user information after optimization meets the preset termination condition, including the following steps:
[0099] The current fitness value and a preset fitness threshold value are obtained, and a fitness difference value between the current fitness value and the preset fitness threshold value is calculated;
[0100] In the embodiment, the fitness difference value between the current fitness value and the preset fitness threshold value is obtained by difference calculation of the current fitness value and the preset fitness threshold value. The calculation formula of the fitness difference value is: fitness difference value = |current fitness value-preset fitness threshold value|.
[0101] The index weight corresponding to the fitness function is adjusted according to the fitness difference value, to obtain an adjusted fitness function;
[0102] In the embodiment, the fitness difference value can be used to evaluate the advantages and disadvantages of the current fitness function. If the difference value is large, it means that the current fitness function may need to be adjusted. According to the size of the fitness difference value, the weight of some index is increased or decreased. In the embodiment, the adjustment of the fitness function can be performed by self-adaptive adjustment. A self-adaptive mechanism is designed to dynamically adjust the weight according to the fitness value change in the optimization process. For example, if the fitness value change rate of an index is low, the weight of the index can be increased. Or the adjustment can be based on performance, and the weight is dynamically adjusted according to the contribution degree of each index to the fitness value. For example, if the contribution degree of an index is low, the weight of the index can be appropriately reduced.
[0103] The fitness function is adjusted according to the current fitness value and the preset fitness threshold, and the fitness difference value is calculated. The index weight corresponding to the fitness function is adjusted according to the fitness difference value, and an adjusted fitness function is obtained. The user information is recalculated according to the adjusted fitness function, and the optimal representation point is recalculated according to the adjusted fitness value obtained after the calculation, to obtain an adjusted optimal representation point. It is judged whether the current fitness value of the adjusted optimal representation point meets the preset termination condition. The adjustment of the fitness function is repeatedly performed until it is judged whether the current fitness value of the adjusted optimal representation point meets the preset termination condition. The optimization process is stopped when the current fitness value of the adjusted optimal representation point meets the preset termination condition.
[0104] In the embodiment, when the current fitness value of the adjusted optimal representation point meets the preset termination condition, the optimization process is stopped. At this time, a corresponding trigger event can be set to monitor the adjusted optimal representation point. When the adjusted optimal representation point meets the preset termination condition, the action of stopping the optimization process is triggered, and the adjusted optimal representation point is output as the optimal representation point for subsequent processing.
[0105] The current fitness value and the preset fitness threshold are obtained, and the fitness difference value of the current fitness value and the preset fitness threshold is calculated. The index weight corresponding to the fitness function is adjusted according to the fitness difference value, and an adjusted fitness function is obtained. The user information is recalculated according to the adjusted fitness function, and the optimal representation point is recalculated according to the adjusted fitness value obtained after the calculation, to obtain an adjusted optimal representation point. It is judged whether the current fitness value of the adjusted optimal representation point meets the preset termination condition. The adjustment of the fitness function is repeatedly performed until it is judged whether the current fitness value of the adjusted optimal representation point meets the preset termination condition. The optimization process is stopped when the current fitness value of the adjusted optimal representation point meets the preset termination condition. Thus, the real-time adjustment of the optimal representation point is effectively realized, so that the adjusted optimal representation point obtained is more accurate and effective.
[0106] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by computer readable instructions instructing related hardware. The computer readable instructions can be stored in a computer readable storage medium. When the program is executed, the processes of the above-mentioned embodiments can be included. The storage medium can be a non-volatile storage medium such as a magnetic disc, an optical disc, a read-only memory (ROM), or a random access memory (RAM).
[0107] It should be understood that although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless explicitly stated herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be alternately executed with at least part of other steps or sub-steps or stages of other steps.
[0108] Further referring to Figure 3 , as an implementation of the method shown in the above Figure 1 , the present application provides an embodiment of a user information risk identification device, which corresponds to the method embodiment shown in Figure 1 , and the device can be specifically applied to various electronic devices.
[0109] As shown in Figure 3 , the user information risk identification device 700 described in the embodiment includes a function construction module 701, a fitness calculation module 702, a space representation module 703, a condition judgment module 704, a first processing module 705, and a second processing module 706. Among them:
[0110] The function construction module 701 is configured to obtain a risk key indicator and construct a fitness function according to the risk key indicator.
[0111] The fitness calculation module 702 is configured to obtain user information and calculate a fitness value according to the user information and the fitness function.
[0112] The space representation module 703 is configured to map the user information to a solution space according to the fitness value, and update the position of the user information in the solution space based on global search and local search to obtain an optimal representation point.
[0113] The condition judgment module 704 is configured to obtain a current fitness value of the optimal representation point, and judge whether the current fitness value meets a preset termination condition.
[0114] The first processing module 705 is configured to convert the current fitness value into a risk level corresponding to the user if the current fitness value meets the preset termination condition, and perform risk warning according to the risk level.
[0115] The second processing module 706 is configured to optimize the fitness function if the current fitness value does not satisfy the preset termination condition, until the fitness value corresponding to the user information after optimization satisfies the preset termination condition.
[0116] By using the user information risk identification device, the risk key indicators are obtained, the fitness function is constructed according to the risk key indicators, the user information is obtained, the fitness value is calculated according to the user information and the fitness function, the user information is mapped to the solution space according to the fitness value, and the position of the user information in the solution space is updated based on global search and local search to obtain the optimal representation point. The current fitness value of the optimal representation point is obtained, and it is judged whether the current fitness value satisfies the preset termination condition. If the current fitness value satisfies the preset termination condition, the current fitness value is converted into a risk level corresponding to the user, and risk warning is performed according to the risk level. If the current fitness value does not satisfy the preset termination condition, the fitness function is optimized until the fitness value corresponding to the user information after optimization satisfies the preset termination condition. Thus, the risk classification and early warning of the user information are accurately realized, and the risk identification reliability of the user information is improved.
[0117] In some optional implementation forms of the embodiment, the function construction module 701 comprises an identification extraction unit and a function construction unit. In this case:
[0118] The identification extraction unit is configured to obtain an index extraction identification, and extract the risk key indicators from a database according to the index extraction identification.
[0119] The function construction unit is configured to obtain index weights corresponding to the risk key indicators, and construct the fitness function according to the risk key indicators and the index weights.
[0120] By setting the function construction module 701 comprising the identification extraction unit and the function construction unit, the corresponding fitness function is constructed according to reliable data indicators, so that the fitness value is calculated according to the fitness function in the subsequent process.
[0121] In some optional implementation forms of the embodiment, the fitness calculation module 702 comprises an information preprocessing unit, a feature analysis unit and a fitness value calculation unit. In this case:
[0122] The information preprocessing unit is configured to preprocess the user information to obtain standard user information.
[0123] The feature analysis unit is configured to perform feature analysis on the standard user information according to the risk key indicators to obtain index feature values.
[0124] The fitness value calculation unit is configured to calculate the fitness value according to the index characteristic value and the fitness function.
[0125] The embodiment sets the fitness calculation module 702 including the information preprocessing unit, the characteristic analysis unit, and the fitness value calculation unit, so that the fitness value is calculated according to the characteristic value of the user information, and the subsequent mapping of the fitness value in the solution space is facilitated.
[0126] In some optional implementation manners of the embodiment, the space representation module 703 includes a dimension obtaining unit, a solution space mapping unit, a global search unit, and a local search unit.
[0127] In some optional implementation manners of the embodiment, the condition judgment module 704 includes a preset threshold obtaining unit, a fitness value judgment unit, a first judgment unit, and a second judgment unit.
[0128] The dimension obtaining unit is configured to obtain dimension information corresponding to the user information.
[0129] The solution space mapping unit is configured to define a solution space dimension according to the dimension information, and map the user information and the fitness value to the solution space according to the solution space dimension, to obtain a user representation point.
[0130] The global search unit is configured to take the user representation point with the lowest fitness value as a global optimal solution, and perform global search on other user representation points according to the global optimal solution, to obtain an adjusted representation point.
[0131] The local search unit is configured to perform local search on the adjusted representation point, to obtain the optimal representation point.
[0132] The embodiment sets the space representation module 703 including the dimension obtaining unit, the solution space mapping unit, the global search unit, and the local search unit, so that the optimal representation point representing the risk situation of the user is obtained according to the fitness value corresponding to the user information, and subsequent corresponding processing is facilitated according to the current fitness value of the optimal representation point.
[0133] In some optional implementation manners of the embodiment, the condition judgment module 704 includes a preset threshold obtaining unit, a fitness value judgment unit, a first judgment unit, and a second judgment unit.
[0134] The preset threshold obtaining unit is configured to obtain a preset fitness threshold.
[0135] The fitness value judgment unit is configured to judge whether the current fitness value is less than or equal to the preset fitness threshold.
[0136] The first judging unit is configured to determine that the current fitness value meets the preset termination condition if the current fitness value is less than or equal to the preset fitness threshold value.
[0137] The second judging unit is configured to determine that the current fitness value does not meet the preset termination condition if the current fitness value is greater than the preset fitness threshold value.
[0138] The condition judging module 704 including the preset threshold value obtaining unit, the fitness value judging unit, the first judging unit and the second judging unit is configured to effectively determine whether the preset termination condition is met according to the current fitness value, so as to facilitate subsequent corresponding processing according to the corresponding condition.
[0139] In some optional implementation manners of the embodiment, the first processing module 705 includes a mapping table obtaining unit, a mapping matching unit and a risk warning unit. In this case:
[0140] The mapping table obtaining unit is configured to obtain a preset risk level mapping table.
[0141] The mapping matching unit is configured to perform mapping matching on the preset risk level mapping table according to the current fitness value, to obtain the risk level.
[0142] The risk warning unit is configured to generate risk warning information according to the risk level, and send the risk warning information to a preset display interface for risk warning reminding.
[0143] The first processing module 705 including the mapping table obtaining unit, the mapping matching unit and the risk warning unit is configured to effectively perform corresponding risk level mapping according to the current fitness value corresponding to the user information, to determine the risk level corresponding to the user and perform warning reminding.
[0144] In some optional implementation manners of the embodiment, the second processing module 706 includes a difference value calculating unit, a function adjusting unit and an adjustment cycle unit. In this case:
[0145] The difference value calculating unit is configured to obtain the current fitness value and a preset fitness threshold value, and calculate a fitness difference value of the current fitness value and the preset fitness threshold value.
[0146] The function adjusting unit is configured to adjust an index weight corresponding to the fitness function according to the fitness difference value, to obtain an adjusted fitness function.
[0147] The adjustment cycle unit is configured to perform fitness calculation on the user information according to the adjusted fitness function, perform calculation of the optimal representation point again according to the adjusted fitness value obtained after the calculation, obtain an adjusted optimal representation point, and determine whether the current fitness value of the adjusted optimal representation point meets the preset termination condition, and repeatedly adjust the fitness function until it is determined whether the current fitness value of the adjusted optimal representation point meets the preset termination condition.
[0148] The second processing module 706 including the difference calculation unit, the function adjustment unit, and the adjustment cycle unit is configured to effectively realize real-time adjustment of the optimal representation point, so that the obtained adjusted optimal representation point is more accurate and effective.
[0149] To solve the above technical problems, the embodiment of the present application further provides a computer device. For details, please refer to Figure 4 , Figure 4 The computer device is a basic structure block diagram of the embodiment.
[0150] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 which are connected to each other through a system bus. It should be noted that only the computer device 8 with components 81-83 is shown in the figure, but it should be understood that all the shown components are not required to be implemented, and more or fewer components can be alternatively implemented. Among them, those skilled in the art can understand that the computer device herein is a device capable of automatically performing numerical calculation 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 (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.
[0151] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and other computing devices. The computer device can interact with the user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device, and the like.
[0152] The memory 81 includes at least one type of readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or a memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 8. Of course, the memory 81 can also include both an internal storage unit and an external storage device of the computer device 8. In this embodiment, the memory 81 is generally used to store an operating system and various application software installed on the computer device 8, such as computer readable instructions of the user information risk identification method, etc. In addition, the memory 81 can also be used to temporarily store various data that have been output or will be output.
[0153] The processor 82 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run computer readable instructions or process data stored in the memory 81, such as computer readable instructions of the user information risk identification method.
[0154] The network interface 83 can include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 8 and other electronic devices.
[0155] The embodiment can obtain a risk key indicator, construct a fitness function according to the risk key indicator, obtain user information, calculate a fitness value according to the user information and the fitness function, map the user information to a solution space according to the fitness value, update a position of the user information in the solution space based on global search and local search, obtain a current fitness value of an optimal representation point, judge whether the current fitness value meets a preset termination condition, convert the current fitness value into a risk level corresponding to the user if the current fitness value meets the preset termination condition, and perform risk warning according to the risk level, and optimize the fitness function if the current fitness value does not meet the preset termination condition, until the fitness value corresponding to the user information after optimization meets the preset termination condition. Therefore, accurate risk classification and early warning of user information are effectively realized, and the risk identification reliability of user information is improved.
[0156] The application further provides another implementation, that is, a computer readable storage medium storing computer readable instructions, which can be executed by at least one processor to enable the at least one processor to perform the steps of the user information risk identification method as described above.
[0157] The embodiment can obtain a risk key indicator, construct a fitness function according to the risk key indicator, obtain user information, calculate a fitness value according to the user information and the fitness function, map the user information to a solution space according to the fitness value, update a position of the user information in the solution space based on global search and local search, obtain a current fitness value of an optimal representation point, judge whether the current fitness value meets a preset termination condition, convert the current fitness value into a risk level corresponding to the user if the current fitness value meets the preset termination condition, and perform risk warning according to the risk level, and optimize the fitness function if the current fitness value does not meet the preset termination condition, until the fitness value corresponding to the user information after optimization meets the preset termination condition. Therefore, accurate risk classification and early warning of user information are effectively realized, and the risk identification reliability of user information is improved.
[0158] Those skilled in the art can clearly understand the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, also can be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of software product, and the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a plurality of instructions to make a terminal device (may be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the method described in each embodiment of the present application.
[0159] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments, and the preferred embodiments of the present application are given in the drawings, but do not limit the patent scope of the present application. The present application can be realized in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing specific embodiments, or make equivalent replacements to some technical features. Any equivalent structure made by using the contents of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the scope of the patent protection of the present application.
[0160] The non-company software tools or components appearing in the embodiments of the present application are only examples for introduction, not representing actual use.
Claims
1. A method for identifying user information risks, characterized in that: The steps include: Obtaining key risk indicators, and constructing a fitness function based on the key risk indicators; Obtaining user information, and calculating a fitness value based on the user information and the fitness function; Mapping the user information to a solution space according to the fitness value, and updating the position of the user information in the solution space based on global search and local search to obtain an optimal representation point; Obtaining a current fitness value of the optimal representation point, and determining whether the current fitness value meets a preset termination condition; If the current fitness value meets the preset termination condition, the current fitness value is converted into a risk level corresponding to the user, and a risk alarm is issued according to the risk level; If the current fitness value does not satisfy the preset termination condition, the fitness function is optimized until the fitness value corresponding to the optimized user information satisfies the preset termination condition.
2. The user information risk identification method according to claim 1, characterized in that: The step of obtaining key risk indicators and constructing a fitness function according to the key risk indicators specifically includes: Obtaining an indicator extraction identifier, and extracting the risk key indicator from a database according to the indicator extraction identifier; Obtain indicator weights corresponding to the key risk indicators, and construct the fitness function according to the key risk indicators and the indicator weights.
3. The user information risk identification method according to claim 1, characterized in that: The step of obtaining user information and calculating a fitness value according to the user information and the fitness function specifically includes: Preprocessing the user information to obtain standard user information; Performing feature analysis on the standard user information according to the key risk indicators to obtain indicator feature values; The fitness value is obtained by performing calculation based on the indicator characteristic value and the fitness function.
4. The user information risk identification method according to claim 1, characterized in that: The step of mapping the user information to a solution space according to the fitness value, and updating the position of the user information in the solution space based on a global search and a local search to obtain an optimal representation point specifically includes: Obtaining dimension information corresponding to the user information; Defining a solution space dimension according to the dimensional information, and mapping the user information and the fitness value to the solution space according to the solution space dimension to obtain a user representation point; Taking the user representation point with the lowest fitness value as the global optimal solution, and performing a global search on other user representation points based on the global optimal solution to obtain an adjusted representation point; Perform a local search on the adjusted representation point to obtain the optimal representation point.
5. The user information risk identification method according to claim 1, characterized in that: The step of obtaining the current fitness value of the optimal representation point and determining whether the current fitness value meets a preset termination condition specifically includes: Get the preset fitness threshold; Determine whether the current fitness value is less than or equal to the preset fitness threshold; If the current fitness value is less than or equal to the preset fitness threshold, determining that the current fitness value meets the preset termination condition; If the current fitness value is greater than the preset fitness threshold, it is determined that the current fitness value does not meet the preset termination condition.
6. The user information risk identification method according to claim 1, characterized in that: The step of converting the current fitness value into a risk level corresponding to the user and issuing a risk alarm according to the risk level specifically includes: Obtain the preset risk level mapping table; Performing mapping matching on the preset risk level mapping table according to the current fitness value to obtain the risk level; Generate risk alarm information based on the risk level, and send the risk alarm information to a preset display interface for risk alarm reminder.
7. The user information risk identification method according to claim 1, characterized in that: The step of optimizing the fitness function until the fitness value corresponding to the optimized user information meets the preset termination condition specifically includes: Obtaining the current fitness value and a preset fitness threshold, and calculating a fitness difference between the current fitness value and the preset fitness threshold; Adjusting the indicator weight corresponding to the fitness function according to the fitness difference to obtain an adjusted fitness function; The fitness of the user information is recalculated according to the adjusted fitness function, and the optimal representation point is recalculated according to the adjusted fitness value obtained after the calculation to obtain the adjusted optimal representation point, and it is judged whether the current fitness value of the adjusted optimal representation point meets the preset termination condition. The fitness function is adjusted to judge whether the current fitness value of the adjusted optimal representation point meets the preset termination condition, and the step of continuously repeating until the current fitness value of the adjusted optimal representation point meets the preset termination condition.
8. A user information risk identification device, characterized in that: include: A function construction module is used to obtain key risk indicators and construct a fitness function based on the key risk indicators; A fitness calculation module, configured to obtain user information and calculate a fitness value based on the user information and the fitness function; a spatial representation module, configured to map the user information to a solution space according to the fitness value, and update the position of the user information in the solution space based on global search and local search to obtain an optimal representation point; A condition judgment module is used to obtain the current fitness value of the optimal representation point and judge whether the current fitness value meets a preset termination condition; a first processing module, configured to convert the current fitness value into a risk level corresponding to the user if the current fitness value satisfies the preset termination condition, and issue a risk alarm according to the risk level; The second processing module is configured to optimize the fitness function if the current fitness value does not satisfy the preset termination condition, until the fitness value corresponding to the optimized user information satisfies the preset termination condition.
9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the user information risk identification method as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the user information risk identification method according to any one of claims 1 to 7.