A risk assessment method and device, electronic equipment and storage medium
By adjusting the risk normalization coefficient using artificial intelligence genetic algorithms, a dynamic target risk assessment model is constructed, which solves the problem of low accuracy in risk assessment in existing technologies and achieves more timely and accurate risk warnings.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA TELECOM CORP LTD
- Filing Date
- 2022-12-23
- Publication Date
- 2026-05-19
AI Technical Summary
Existing risk assessment technologies rely on human intervention, which is highly subjective and results in low accuracy, making it difficult to meet business needs.
An artificial intelligence genetic algorithm is used to minimize and iterate the initial risk assessment model, dynamically adjust the risk normalization coefficient, and construct a dynamic, time-varying target risk assessment model.
It improves the accuracy of risk assessment, enabling more timely and accurate risk warnings and reducing reliance on manual intervention.
Smart Images
Figure CN116090817B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of image processing technology, and in particular to a risk assessment method, apparatus, electronic device, and storage medium. Background Technology
[0002] Risk assessment is an important part of business activities. By assessing the risks in business operations, early warnings of potential impacts and losses can be generated in advance, helping companies to develop timely response strategies and avoid risks.
[0003] Current risk assessment solutions mainly adopt a quantitative assessment method based on risk indicator scoring. One or more risk points are set for each assessment object, and corresponding risk indicators are set for each risk point. At the same time, risk supervisors are set up to check the risk points or conduct random checks and score each risk indicator to establish a risk scoring system. When the score of each risk indicator reaches the pre-set risk threshold, a risk warning is issued, and abnormal data is traced and investigated to hold those responsible accountable.
[0004] However, in the above-mentioned risk assessment methods, activities such as setting risk points, formulating risk indicators and values, and risk scoring are mostly completed manually, which is highly subjective. Therefore, the accuracy of risk assessment is low and it is difficult to meet business needs. Summary of the Invention
[0005] This disclosure provides a risk assessment system, method, apparatus, electronic device, and storage medium to at least address the problem in related technologies where risk assessment relies on manual labor, is highly subjective, and therefore has low accuracy, failing to meet business needs. The technical solution of this disclosure is as follows:
[0006] According to a first aspect of the present disclosure, a risk assessment method is provided, comprising:
[0007] Obtain the initial risk normalization coefficient for each business process included in the preset business scenario;
[0008] Based on the initial risk normalization coefficient, an initial risk assessment model for the preset business scenario is constructed.
[0009] Based on an artificial intelligence genetic algorithm, the initial risk assessment model is minimized and iterated, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model.
[0010] Based on the target risk assessment model and the current execution status of the preset business scenario, a risk assessment is performed on the preset business scenario.
[0011] Optionally, obtaining the initial risk normalization coefficient for each business process included in the preset business scenario includes:
[0012] Obtain the importance and priority of each business process included in the preset business scenarios;
[0013] Based on the importance and priority, an initial risk normalization coefficient is determined for each business process.
[0014] Optionally, constructing the initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient includes:
[0015] Obtain the initial responsibility risk coefficient matrix for each business process;
[0016] Based on the initial risk normalization coefficient and the initial liability risk coefficient matrix, an initial risk assessment model for the preset business scenario is constructed.
[0017] Optionally, constructing the initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient and the initial liability risk coefficient matrix includes:
[0018] Obtain the risk baseline parameter for each business process;
[0019] Based on the aforementioned risk base parameters, construct a risk base expression for each business process;
[0020] For each business process, the initial risk normalization coefficient, the initial liability risk coefficient matrix, and the risk base expression are multiplied together to obtain the comprehensive risk expression for that business process.
[0021] The initial risk assessment model for the preset business scenario is obtained by summing the comprehensive risk expressions of each business process.
[0022] Optionally, the step of conducting a risk assessment of the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario includes:
[0023] Based on the target risk assessment model and the current execution status of the preset business scenario, a risk assessment is performed on the preset business scenario to obtain the risk assessment value of the preset business scenario;
[0024] If the risk assessment value exceeds a preset threshold, a preset early warning operation will be executed.
[0025] Optionally, the step of performing minimization optimization iterations on the initial risk assessment model based on artificial intelligence genetic algorithms, and adjusting the initial risk normalization coefficients to obtain the target risk assessment model, includes:
[0026] According to a preset period, based on an artificial intelligence genetic algorithm, the initial risk assessment model is minimized and optimized iteratively, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model corresponding to the preset period.
[0027] According to a second aspect of the present disclosure, a risk assessment apparatus is provided, comprising:
[0028] The acquisition module is used to acquire the initial risk normalization coefficient for each business process included in the preset business scenario;
[0029] A construction module is used to construct an initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient.
[0030] The iterative module is used to perform minimization optimization iteration on the initial risk assessment model based on artificial intelligence genetic algorithm, and to adjust the initial risk normalization coefficient to obtain the target risk assessment model;
[0031] The assessment module is used to assess the risk of the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario.
[0032] According to a third aspect of the present disclosure, a risk assessment electronic device is provided, comprising:
[0033] processor;
[0034] Memory used to store the processor's executable instructions;
[0035] The processor is configured to execute the instructions to implement any of the risk assessment methods described above.
[0036] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when instructions in the computer-readable storage medium are executed by a processor of a risk assessment electronic device, the risk assessment electronic device is enabled to perform the risk assessment method described in any one of the present invention.
[0037] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the risk assessment method described in any one of the present invention.
[0038] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects:
[0039] Obtain the initial risk normalization coefficient for each business process included in the preset business scenario; construct an initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient; perform minimization optimization iteration on the initial risk assessment model based on artificial intelligence genetic algorithm, adjust the initial risk normalization coefficient, and obtain the target risk assessment model; conduct a risk assessment on the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario.
[0040] In this way, the risk normalization coefficient can be dynamically adjusted based on artificial intelligence genetic algorithms, thereby constructing a dynamic, time-varying intelligent target risk assessment model. Compared with the usual method of setting fixed risk nodes and preset risk values for each business process, it can provide more timely and accurate early warning of risks in business scenarios and improve the accuracy of risk assessment.
[0041] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.
[0043] Figure 1 This is a flowchart illustrating a risk assessment method according to an exemplary embodiment.
[0044] Figure 2 This is a flowchart illustrating a prior art risk assessment method according to an exemplary embodiment.
[0045] Figure 3 This is a logical schematic diagram illustrating a risk assessment method according to an exemplary embodiment.
[0046] Figure 4 This is a block diagram illustrating a risk assessment apparatus according to an exemplary embodiment.
[0047] Figure 5 This is a block diagram illustrating an electronic device for risk assessment according to an exemplary embodiment.
[0048] Figure 6 This is a block diagram illustrating an apparatus for risk assessment according to an exemplary embodiment. Detailed Implementation
[0049] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.
[0050] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0051] Figure 1 This is a flowchart illustrating a risk assessment method according to an exemplary embodiment, such as... Figure 1 As shown, the risk assessment method includes:
[0052] In step S11, the initial risk normalization coefficient of each business process included in the preset business scenario is obtained.
[0053] Risk assessment is an important part of business activities. By assessing the risks in business operations, early warnings of potential impacts and losses can be generated in advance, helping companies to develop timely response strategies and avoid risks.
[0054] like Figure 2 The diagram shows a flowchart of the current risk assessment method. Specifically, one or more risk points are first set based on each business processing step, and corresponding risk indicators are set for each risk point. At the same time, risk supervisors are assigned to inspect or randomly check the risk points, score each risk indicator, and determine the risk value of each risk point. When the score of each risk indicator reaches the pre-set risk threshold, a risk warning is issued, and the abnormal data is traced back to its source for investigation and accountability.
[0055] However, in this risk assessment method, activities such as risk point setting, risk indicator and value formulation, and risk scoring are mostly completed manually, which is highly subjective and results in low accuracy, making it difficult to meet business needs. The risk assessment method provided in this application can improve the above problems, thereby increasing the accuracy of risk assessment and reducing reliance on manual labor.
[0056] In this application, the initial risk normalization coefficient of each business process included in the preset business scenario can be obtained. The preset business scenario can be any business scenario, such as a business scenario involving handling customer complaints, etc., without any specific limitation. Each business scenario can include multiple business processes, which can be independent of each other or have a sequential order.
[0057] The importance and priority of each business process can be set in advance according to the specific business needs of the preset business scenario, or it can be obtained by machine learning from historical data. Historical data can include historical business process operation data, fault handling data, complaint handling data, etc., without any specific limitations.
[0058] In one implementation, obtaining the initial risk normalization coefficient for each business process included in the preset business scenario includes:
[0059] Obtain the importance and priority of each business process included in the preset business scenario; based on importance and priority, determine the initial risk normalization coefficient for each business process.
[0060] In other words, this application allows for scientific and precise quantitative modeling based on the importance and priority of each business process within a pre-defined business scenario, determining the initial risk normalization coefficient for each process. For instance, in a complaint process, the process can be categorized by complaint type, such as family service complaints, billing and payment complaints, billing and disbursement complaints, electronic channel complaints, and personal service complaints, among other N types. These N complaint process categories are then arranged, and a quantitative model of the complaint handling risk coefficient is performed based on their importance and processing priority, yielding the initial risk normalization coefficient for each process, as shown in the following formula:
[0061]
[0062] in, Let represent the risk normalization coefficient of the i-th type of complaint, and satisfy . The specific value can be set and adjusted according to the actual needs of the preset business scenario, and there is no specific limitation.
[0063] In step S12, an initial risk assessment model for a preset business scenario is constructed based on the initial risk normalization coefficient.
[0064] In other words, based on the initial risk normalization coefficient, an initial risk assessment model for a preset business scenario is constructed. The initial risk assessment model is built on the initial risk normalization coefficient. As the initial risk normalization coefficient changes dynamically, the initial risk assessment model will also change, and the risk assessment results will also change. This enables more timely and accurate early warning of liability risks and minimizes the overall system risk.
[0065] In one implementation, an initial risk assessment model for a preset business scenario is constructed based on the initial risk normalization coefficient, including: obtaining the initial liability risk coefficient matrix for each business process; and constructing the initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient and the initial liability risk coefficient matrix.
[0066] In other words, an initial risk assessment model for a pre-defined business scenario can be constructed simultaneously based on the initial risk normalization coefficient and the initial liability risk coefficient matrix. The initial liability risk coefficient matrix is used to quantitatively model the handling liability risk and related liability risks of each business process. For example, in a complaint business process, for the i-th type of complaint, there are M handling liability actions, such as the liability risk of intelligent complaint classification and review, the liability risk of automatic complaint creation and review, the liability risk of automatic dispatch and review, the liability risk of complaint handling, the liability risk of handling result review, and the liability risk of report review; as well as the related liability risks of intelligent complaint classification and review, the related liability risks of automatic complaint creation and review, the related liability risks of automatic dispatch, the related liability risks of complaint handling, the related liability risks of handling result review, and the related liability risks of report review, etc.
[0067] In this invention, the handling of liability risk refers to the liability risk arising from the dereliction of duty by the person responsible for the execution of the process and the failure to take timely actions in the process; the related liability risk refers to the related liability risk that the subsequent related parties shall bear if the process actions are not completed in a timely manner and the related parties before and after the actions fail to fulfill their supervisory responsibilities.
[0068] This invention provides a comprehensive model for handling liability risks and related liability risks, forming a liability risk coefficient matrix, as shown in the following formula:
[0069]
[0070] in, This represents the liability risk coefficient arising from the failure of the person responsible for the j-th processing action in the i-th type of business process to complete the processing action; This represents the associated liability risk coefficient arising from the failure of the person responsible for the j-th processing action in business process i to complete the processing action, and the failure of the (j-1)-th person to perform the supervisory action. This represents the associated liability risk coefficient arising from the failure of the person responsible for the j-th processing action in business process i to complete the processing action, and the failure of the (j+1)-th person to perform the supervision action, and so on.
[0071] Specifically, based on the initial risk normalization coefficient and the initial liability risk coefficient matrix, an initial risk assessment model for a pre-defined business scenario is constructed, including:
[0072] Obtain the risk base parameters for each business process; construct the risk base expression for each business process based on the risk base parameters; for each business process, multiply the initial risk normalization coefficient, the initial liability risk coefficient matrix, and the risk base expression to obtain the comprehensive risk expression for that business process; add the comprehensive risk expressions of each business process to obtain the initial risk assessment model for the preset business scenario.
[0073] Specifically, the risk base expression can be represented as:
[0074]
[0075] Where k0, k1, a, and b are risk base parameters, and <k0,k1,a,b> is called the risk base parameter quadruple. The parameters of the risk base parameter quadruple can be flexibly adjusted according to the specific circumstances of the preset business scenario. It can be understood that when... And if the j-th processing action is not completed, Reaching the maximum liability risk threshold.
[0076] Furthermore, the initial risk assessment model can be expressed as:
[0077]
[0078] In step S13, the initial risk assessment model is minimized and iterated based on the artificial intelligence genetic algorithm, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model.
[0079] Among them, genetic algorithms are a type of search algorithm that simulates biological genetics and natural selection mechanisms through artificial means. To some extent, genetic algorithms are a mathematical simulation of the biological evolution process. They draw on the ideas of biological genetic evolution and simulate the natural selection and natural variation processes of reproduction, hybridization, gene mutation, and natural variation experienced during population evolution. It is an efficient method for global search and optimization, and can adaptively obtain the individual with the highest fitness during the "evolution" process. This individual is the optimal solution to the optimization problem.
[0080] In one implementation, an artificial intelligence genetic algorithm is used to iteratively minimize the initial risk assessment model, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model, including:
[0081] According to the preset cycle, based on the artificial intelligence genetic algorithm, the initial risk assessment model is minimized and optimized iteratively, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model corresponding to the preset cycle.
[0082] In other words, within the observation period of [nT, (n+1)T], the coefficients of the risk assessment model in the business processing system are optimized. More specifically, S... R(t) is defined as the fitness function F in the artificial intelligence optimization algorithm. The coefficients in the complaint handling type risk coefficient vector and the responsibility risk coefficient matrix are used as optimization variables in the genetic mutation population. The algorithm performs intelligent optimization iteration with the goal of globally minimizing the comprehensive fitness value F. When the global minimum value of F is found, the coefficient values in the complaint handling type risk coefficient vector and the responsibility risk coefficient matrix in the genetic mutation population are extracted and updated in the initial risk assessment model to obtain the target risk assessment model corresponding to the preset period.
[0083] In step S14, a risk assessment is performed on the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario.
[0084] In this step, after obtaining the target risk assessment model, risk assessment can be performed on the preset business scenarios based on the target risk assessment model. Since the target risk assessment model is dynamic and time-varying, the accuracy of the risk assessment results is higher.
[0085] In one implementation, a risk assessment is performed on the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario, including:
[0086] Based on the target risk assessment model and the current execution status of the preset business scenario, a risk assessment is performed on the preset business scenario to obtain the risk assessment value of the preset business scenario; if the risk assessment value is greater than the preset threshold, a preset early warning operation is executed.
[0087] Specifically, in actual business processing system applications, when S R (t) is greater than a certain preset threshold In such cases, risk warnings can be issued to relevant management personnel. For example, a processing interface can be provided to relevant management personnel through a smartphone application or a web-based H5 mini-program to enable timely complaint handling actions.
[0088] As can be seen from the above, the technical solution provided by the embodiments of this disclosure can dynamically adjust the risk normalization coefficient based on artificial intelligence genetic algorithms, thereby constructing a dynamic, time-varying intelligent target risk assessment model. Compared with the usual method of setting fixed risk nodes and preset risk values for each business process, it can provide early warning of risks in business scenarios more timely and accurately, and improve the accuracy of risk assessment.
[0089] like Figure 3As shown below, a specific embodiment of the present invention will be used to illustrate the method in this embodiment. This embodiment mainly uses quantitative modeling based on the priority of each business process, innovatively constructs the responsibility risk of each link in the business process, uses real-time quantitative modeling algorithm theory, combines machine learning results based on historical work order data, and integrates artificial intelligence parameter global optimization technology to achieve periodic and dynamic optimization of risk assessment model parameters. This enables real-time dynamic modeling of risk coefficients, intelligent adjustment of responsibility association, and intelligent real-time early warning of process risks, thereby achieving more accurate and scientific risk assessment.
[0090] This embodiment specifically includes the following steps:
[0091] First, obtain the initial risk coefficient and assessment model. For example, machine learning can be used to obtain the initial risk coefficient and assessment model from historical data such as historical business process operation data, fault handling data, and complaint handling data.
[0092] Then, according to the importance and priority of various business processes, scientific and precise quantitative modeling is carried out. The business processes in the preset business scenarios are systematically classified, and the importance and priority of various business processes are scientifically and precisely quantitatively modeled to determine the initial risk normalization coefficient.
[0093] For example, in the complaint handling process, the process can be categorized by complaint type, such as family service complaints, account management and payment complaints, billing and payment complaints, electronic channel complaints, personal service complaints, etc., totaling N types. These N complaint handling process categories are then ranked, and a quantitative model of the complaint handling risk coefficient is created based on their importance and processing priority, forming an initial risk normalization coefficient for each complaint handling type, as shown in the following formula:
[0094]
[0095] in, Let represent the risk normalization coefficient of the i-th type of complaint, and satisfy . The specific values can be set and adjusted according to the actual needs of the preset business scenarios.
[0096] Meanwhile, this invention quantifies and models the handling responsibility risks and related responsibilities for each type of business process. For example, for the i-th type of complaint, there are M handling responsibility actions, such as the responsibility risks for intelligent complaint classification and review, automatic complaint creation and review, automatic dispatch and review, complaint handling, handling result review, and report review; as well as the related responsibility risks for intelligent complaint classification and review, automatic complaint creation and review, automatic dispatch and review, complaint handling, handling result review, and report review.
[0097] Among them, the risk of handling liability refers to the liability risk arising from the dereliction of duty by the person responsible for the execution of the process and the failure to take timely action in the process; the risk of related liability refers to the related liability risk that the subsequent related parties shall bear if the process action is not completed in a timely manner and the related parties before and after the action fail to fulfill their supervisory responsibilities.
[0098] Simultaneously, a comprehensive model can be constructed to handle liability risks and related liability risks, forming a liability risk coefficient matrix, as shown in the following formula:
[0099]
[0100] in, This represents the liability risk coefficient arising from the failure of the person responsible for the j-th processing action in the i-th type of business process to complete the processing action; This represents the associated liability risk coefficient arising from the failure of the person responsible for the j-th processing action in business process i to complete the processing action, and the failure of the (j-1)-th person to perform the supervisory action. This represents the associated liability risk coefficient arising from the failure of the person responsible for the j-th processing action in business process i to complete the processing action, and the failure of the (j+1)-th person to perform the supervision action, and so on.
[0101] Then, based on the artificial intelligence genetic algorithm, within the observation period of [nT, (n+1)T], the coefficients of the initial risk assessment model in the preset business scenario are optimized. Specifically, assuming that after the occurrence of the i-th type of complaint, M processing actions need to be performed, and the processing time limit vector... middle This indicates that the j-th processing action out of M processing actions needs to be performed. Completed before time t. If the j-th action is not completed at time t, the base risk of liability for the person responsible for the j-th action is defined as follows: The algorithm is expressed as follows:
[0102]
[0103] Among them, when When, and the j-th processing action is not completed, To reach the maximum liability risk base, k0, k1, a, b are risk base parameters, and <k0,k1,a,b> is called the risk base parameter quadruple. The parameters of the risk base parameter quadruple can be flexibly adapted and adjusted according to specific circumstances.
[0104] when When the j-th processing action is not completed, the risk value for the person responsible for the j-th processing action. The definition is as follows:
[0105]
[0106] Similarly, if the j-th processing action is not completed at time t, the liability risk value for the person responsible for the (j-1)-th processing action is defined as follows: The algorithm is expressed as follows:
[0107]
[0108] At time t, if the j-th processing action is not completed, the comprehensive liability risk value for all M responsible parties for the actions is defined as follows: The algorithm is expressed as follows:
[0109]
[0110] When at time t, and The j-th processing action is completed. That is, once j processing actions are completed ahead of schedule, the sum of all risks and related risks arising from j processing actions will be zero.
[0111] The comprehensive risk liability value generated at time t during the handling of a specific type i complaint. The algorithm is expressed as follows:
[0112]
[0113] when Greater than a certain preset threshold In such cases, risk warnings can be issued to the relevant responsible persons. For example, a processing interface can be provided to the relevant responsible persons through a smartphone terminal application or a web-based H5 mini-program to enable them to perform timely complaint handling actions.
[0114] In this invention, the target risk assessment model can be used to determine the overall system risk for all complaints received in the entire complaint handling system. The target risk assessment model S... R (t) can be defined as follows:
[0115]
[0116] Within the observation period of [nT, (n+1)T], the coefficients of the risk assessment model in the business processing system are optimized, and S... R (t) is defined as the fitness function F in the artificial intelligence optimization algorithm, and the coefficients in the complaint handling type risk coefficient vector and the responsibility risk coefficient matrix are used as genetic variation population optimization variables. The intelligent optimization iteration with the goal of globally minimizing the comprehensive fitness F is performed, as shown in the following set of equations:
[0117] min.{F=SR (t), 0 ≤ t ≤ T}
[0118]
[0119]
[0120] Furthermore, when the global minimum value of F is found, the coefficient values of the complaint handling type risk coefficient vector and the responsibility risk coefficient matrix in the genetically mutated population are extracted and updated in the actual real-time business processing risk assessment system. When S R (t) is greater than a certain preset threshold In this case, the present invention can issue risk warnings to relevant management personnel, for example, by providing a processing interface for relevant management personnel to perform timely complaint handling actions through smartphone terminal applications or web-based H5 mini-programs.
[0121] As can be seen from the above, the technical solution provided by the embodiments of this disclosure can dynamically adjust the risk normalization coefficient based on artificial intelligence genetic algorithms, thereby constructing a dynamic, time-varying intelligent target risk assessment model. Compared with the usual method of setting fixed risk nodes and preset risk values for each business process, it can provide early warning of risks in business scenarios more timely and accurately, and improve the accuracy of risk assessment.
[0122] Figure 4 This is a block diagram of a risk assessment apparatus according to an exemplary embodiment, comprising:
[0123] The acquisition module 201 is used to acquire the initial risk normalization coefficient of each business process included in the preset business scenario;
[0124] The construction module 202 is used to construct an initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient.
[0125] The iteration module 203 is used to perform minimization optimization iteration on the initial risk assessment model based on artificial intelligence genetic algorithm, and adjust the initial risk normalization coefficient to obtain the target risk assessment model;
[0126] The assessment module 204 is used to assess the risk of the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario.
[0127] In one implementation, the acquisition module 201 is used to:
[0128] Obtain the importance and priority of each business process included in the preset business scenarios;
[0129] Based on the importance and priority, an initial risk normalization coefficient is determined for each business process.
[0130] In one implementation, the construction module 202 is used for:
[0131] Obtain the initial responsibility risk coefficient matrix for each business process;
[0132] Based on the initial risk normalization coefficient and the initial liability risk coefficient matrix, an initial risk assessment model for the preset business scenario is constructed.
[0133] In one implementation, the construction module 202 is used for:
[0134] Obtain the risk baseline parameter for each business process;
[0135] Based on the aforementioned risk base parameters, construct a risk base expression for each business process;
[0136] For each business process, the initial risk normalization coefficient, the initial liability risk coefficient matrix, and the risk base expression are multiplied together to obtain the comprehensive risk expression for that business process.
[0137] The initial risk assessment model for the preset business scenario is obtained by summing the comprehensive risk expressions of each business process.
[0138] In one implementation, the evaluation module 204 is used to:
[0139] Based on the target risk assessment model and the current execution status of the preset business scenario, a risk assessment is performed on the preset business scenario to obtain the risk assessment value of the preset business scenario;
[0140] If the risk assessment value exceeds a preset threshold, a preset early warning operation will be executed.
[0141] In one implementation, the iteration module 203 is used to:
[0142] According to a preset period, based on an artificial intelligence genetic algorithm, the initial risk assessment model is minimized and optimized iteratively, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model corresponding to the preset period.
[0143] As can be seen from the above, the technical solution provided by the embodiments of this disclosure can dynamically adjust the risk normalization coefficient based on artificial intelligence genetic algorithms, thereby constructing a dynamic, time-varying intelligent target risk assessment model. Compared with the usual method of setting fixed risk nodes and preset risk values for each business process, it can provide early warning of risks in business scenarios more timely and accurately, and improve the accuracy of risk assessment.
[0144] Figure 5 This is a block diagram illustrating an electronic device for risk assessment according to an exemplary embodiment.
[0145] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory including instructions that can be executed by a processor of an electronic device to perform the method. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.
[0146] In an exemplary embodiment, a computer program product is also provided that, when run on a computer, enables the computer to implement the method of risk assessment.
[0147] As can be seen from the above, the technical solution provided by the embodiments of this disclosure can dynamically adjust the risk normalization coefficient based on artificial intelligence genetic algorithms, thereby constructing a dynamic, time-varying intelligent target risk assessment model. Compared with the usual method of setting fixed risk nodes and preset risk values for each business process, it can provide early warning of risks in business scenarios more timely and accurately, and improve the accuracy of risk assessment.
[0148] Figure 6 This is a block diagram illustrating an apparatus 800 for risk assessment according to an exemplary embodiment.
[0149] For example, device 800 can be a mobile phone, computer, digital broadcasting electronic device, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.
[0150] Reference Figure 6 The device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.
[0151] Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps described. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.
[0152] Memory 804 is configured to store various types of data to support the operation of device 800. Examples of this data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.
[0153] Power supply component 807 provides power to various components of device 800. Power supply component 807 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 800.
[0154] Multimedia component 808 includes a screen that provides an output interface between the device 800 and the account. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the account. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
[0155] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.
[0156] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to, a home button, volume buttons, a power button, and a lock button.
[0157] Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of device 800. For example, sensor assembly 814 may detect the on / off state of device 800, the relative positioning of components such as the display and keypad of device 800, changes in position of device 800 or a component of device 800, the presence or absence of contact between an account and device 800, orientation or acceleration / deceleration of device 800, and temperature changes of device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.
[0158] Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices. Device 800 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
[0159] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described in the first and second aspects.
[0160] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of the device 800 to perform the method. Optionally, for example, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.
[0161] In an exemplary embodiment, a computer program product including instructions is also provided, which, when run on a computer, causes the computer to perform any of the risk assessment methods described in the embodiments.
[0162] As can be seen from the above, the technical solution provided by the embodiments of this disclosure can dynamically adjust the risk normalization coefficient based on artificial intelligence genetic algorithms, thereby constructing a dynamic, time-varying intelligent target risk assessment model. Compared with the usual method of setting fixed risk nodes and preset risk values for each business process, it can provide early warning of risks in business scenarios more timely and accurately, and improve the accuracy of risk assessment.
[0163] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0164] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A risk assessment method, characterized in that, include: Obtain the initial risk normalization coefficient for each business process included in the preset business scenario; Based on the initial risk normalization coefficient, an initial risk assessment model for the preset business scenario is constructed. Based on an artificial intelligence genetic algorithm, the initial risk assessment model is minimized and iterated, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model. Based on the target risk assessment model and the current execution status of the preset business scenario, a risk assessment is performed on the preset business scenario; The acquisition of the initial risk normalization coefficient for each business process within the preset business scenario includes: Obtain the importance and priority of each business process included in the preset business scenarios; Based on the importance and priority, an initial risk normalization coefficient is determined for each business process; The step of constructing an initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient includes: Obtain the initial responsibility risk coefficient matrix for each business process; Based on the initial risk normalization coefficient and the initial liability risk coefficient matrix, an initial risk assessment model for the preset business scenario is constructed. The step of constructing an initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient and the initial liability risk coefficient matrix includes: Obtain the risk baseline parameter for each business process; Based on the aforementioned risk base parameters, construct a risk base expression for each business process; For each business process, the initial risk normalization coefficient, the initial liability risk coefficient matrix, and the risk base expression are multiplied together to obtain the comprehensive risk expression for that business process. The initial risk assessment model for the preset business scenario is obtained by summing the comprehensive risk expressions of each business process.
2. The risk assessment method according to claim 1, characterized in that, The step of assessing the risk of the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario includes: Based on the target risk assessment model and the current execution status of the preset business scenario, a risk assessment is performed on the preset business scenario to obtain the risk assessment value of the preset business scenario; If the risk assessment value exceeds a preset threshold, a preset early warning operation will be executed.
3. The risk assessment method according to claim 1, characterized in that, The method, based on an artificial intelligence genetic algorithm, performs minimization and optimization iterations on the initial risk assessment model, adjusts the initial risk normalization coefficient, and obtains the target risk assessment model, including: According to a preset period, based on an artificial intelligence genetic algorithm, the initial risk assessment model is minimized and optimized iteratively, and the initial risk normalization coefficient is adjusted to obtain the target risk assessment model corresponding to the preset period.
4. A risk assessment device, characterized in that, include: The acquisition module is used to acquire the initial risk normalization coefficient for each business process included in the preset business scenario; A construction module is used to construct an initial risk assessment model for the preset business scenario based on the initial risk normalization coefficient. The iterative module is used to perform minimization optimization iteration on the initial risk assessment model based on artificial intelligence genetic algorithm, and to adjust the initial risk normalization coefficient to obtain the target risk assessment model; The assessment module is used to assess the risk of the preset business scenario based on the target risk assessment model and the current execution status of the preset business scenario; The acquisition module is used for: Obtain the importance and priority of each business process included in the preset business scenarios; Based on the importance and priority, an initial risk normalization coefficient is determined for each business process; The building module is used for: Obtain the initial responsibility risk coefficient matrix for each business process; Based on the initial risk normalization coefficient and the initial liability risk coefficient matrix, an initial risk assessment model for the preset business scenario is constructed. The building module is used for: Obtain the risk baseline parameter for each business process; Based on the aforementioned risk base parameters, construct a risk base expression for each business process; For each business process, the initial risk normalization coefficient, the initial liability risk coefficient matrix, and the risk base expression are multiplied together to obtain the comprehensive risk expression for that business process. The initial risk assessment model for the preset business scenario is obtained by summing the comprehensive risk expressions of each business process.
5. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the risk assessment method as described in any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the risk assessment electronic device, the risk assessment electronic device is able to perform the risk assessment method as described in any one of claims 1 to 3.
7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the risk assessment method according to any one of claims 1 to 3.