Method and device for generating risk assessment interval, storage medium, and electronic device

Abstract

The embodiment of the present application provides a method and device for generating a risk assessment interval, a storage medium, and an electronic device, wherein the method includes: obtaining risk assessment parameters of N objects to obtain N risk assessment parameters; respectively determining the proportion parameters of the target product corresponding to each of the N objects to obtain N proportion parameters, wherein the proportion parameters are used to represent the proportion of the object's investment in the target product in the corresponding product combination; using the N risk assessment parameters and the N proportion parameters, calculating the target risk assessment parameters; generating a risk assessment interval based on the target risk assessment parameters. Through this application, the problem of low accuracy of risk assessment of products in the related art is solved, and the effect of improving the accuracy of product risk assessment is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and more specifically, to a method and device for generating a risk assessment interval, a storage medium, and an electronic device. Background Art

[0002] Existing risk assessment methods focus on a single dimension, such as financial risk, but are weak in comprehensive risk assessment of multiple dimensions such as environment, society and governance. In addition, since different assessment agencies use different scoring standards and methods, it is difficult to unify the current risk assessment results and make direct comparisons, which affects the determination of risk assessment parameters and makes the accuracy of product risk assessment low. Summary of the invention

[0003] The embodiments of the present application provide a method and device for generating a risk assessment interval, a storage medium, and an electronic device to at least solve the problem of low accuracy in risk assessment of products in the related art.

[0004] According to an embodiment of the present application, a method for generating a risk assessment interval is provided, comprising: acquiring risk assessment parameters of N objects to obtain N risk assessment parameters, wherein one object corresponds to one risk assessment parameter, and the risk assessment parameter is used to represent the risk-bearing capacity of the object for a target product in multiple risk dimensions, and N is a natural number greater than 1; determining the proportion parameter of the target product corresponding to each of the N objects respectively to obtain N proportion parameters, wherein the proportion parameter is used to represent the investment proportion of the object in the corresponding product portfolio in the target product; calculating a target risk assessment parameter using the N risk assessment parameters and the N proportion parameters; and generating a risk assessment interval based on the target risk assessment parameter, wherein the risk assessment interval is used to represent the risk level value of the target product in multiple risk dimensions.

[0005] In an exemplary embodiment, risk assessment parameters of N objects are obtained to obtain N risk assessment parameters, including: when the risk assessment parameters are first type parameters, obtaining risk assessment parameters of N objects in multiple risk dimensions from a first target application to obtain N risk assessment parameters; when the risk assessment parameters are second type parameters, determining the dimensions that affect transactions of the target product to obtain multiple risk dimensions; for each of the objects, determining the N risk assessment parameters by the following steps: obtaining performance values ​​of the object corresponding to the target product in multiple risk dimensions to obtain multiple performance values, wherein the performance values ​​are used to indicate the performance of the object in the risk dimensions. The risk-bearing capacity of the target product in the risk dimension, the performance value includes a historical performance value and a real-time performance value; a plurality of the performance values ​​are input into a target generator to obtain a comprehensive performance value generated by the target generator, wherein the target generator is a linear model based on a neural network, and the target generator includes: a data processing layer and a nonlinear regression layer, the data processing layer is used to perform nonlinear numerical conversion on the plurality of the performance values, and extract features from the converted numerical values, and the extracted features are input into the nonlinear regression layer, and the nonlinear regression layer is used to perform correlation analysis on the extracted features and output the comprehensive performance value; based on the comprehensive performance value of each of the objects, N risk assessment parameters are determined.

[0006] In an exemplary embodiment, respectively determining the proportion parameter of the target product corresponding to each of the N objects to obtain N proportion parameters includes: for each of the objects, determining the proportion parameter of the object to the target product by the following steps to obtain N proportion parameters: obtaining report data of the object, wherein the report data is data generated based on the numerical value of the target product held by the object within a preset time period; determining the quantity or parameter value of the target product held by the object from the report data to obtain the proportion parameter.

[0007] In an exemplary embodiment, a target risk assessment parameter is calculated using N risk assessment parameters and N ratio parameters, including: performing a weighted average operation on the N risk assessment parameters and the N ratio parameters to obtain the target risk assessment parameter; wherein the weighted average operation includes the following steps: calculating the product between the risk assessment parameter of each object and the corresponding ratio parameter to obtain N first values; calculating the sum of the N first values ​​to obtain a second value; calculating the sum of the N ratio parameters to obtain a third value; and using the second value and the third value to calculate the target risk assessment parameter.

[0008] In an exemplary embodiment, generating a risk assessment interval based on the target risk assessment parameter includes at least one of the following: dividing a first numerical range of the parameter value of the target risk assessment parameter, and generating multiple risk assessment numerical intervals based on the first numerical range to obtain the risk assessment interval, wherein each of the risk assessment numerical intervals corresponds to a risk level; when the parameter value of the risk assessment parameter is not within a second numerical range corresponding to the original risk assessment interval, adjusting the original risk assessment interval according to the risk assessment parameter to obtain the risk assessment interval.

[0009] In an exemplary embodiment, after generating a risk assessment interval based on the target risk assessment parameters, the method further includes: setting a numerical range of the risk assessment interval; dividing the numerical range into multiple sub-ranges according to a preset numerical length, and generating risk indication information corresponding to the multiple sub-ranges; generating a risk indication chart according to the correspondence between the multiple sub-ranges and the multiple risk indication information; and sending the risk indication chart to a second target application based on a preset format, so as to visually display the risk indication chart through the second target application.

[0010] In an exemplary embodiment, after sending the risk indication chart to a second target application based on a preset format so as to visually display the risk indication chart through the second target application, the method further includes: receiving a trigger operation acting on the risk indication chart through the second target application, wherein the trigger operation includes querying the data included in the risk indication chart and adjusting the playback parameters of the risk indication chart; generating trigger data using the trigger operation, and adjusting the risk indication chart based on the trigger data.

[0011] According to another embodiment of the present application, a device for generating a risk assessment interval is also provided, including: a first acquisition module, used to acquire risk assessment parameters of N objects, to obtain N risk assessment parameters, wherein one object corresponds to one risk assessment parameter, and the risk assessment parameter is used to represent the risk-bearing capacity of the object for a target product in multiple risk dimensions, and N is a natural number greater than 1; a first determination module, used to respectively determine the proportion parameter of the target product corresponding to each of the N objects, to obtain N proportion parameters, wherein the proportion parameter is used to represent the investment proportion of the object in the corresponding product portfolio to the target product; a first calculation module, used to calculate a target risk assessment parameter using the N risk assessment parameters and the N proportion parameters; a first generation module, used to generate a risk assessment interval based on the target risk assessment parameter, wherein the risk assessment interval is used to represent the risk level value of the target product in multiple risk dimensions.

[0012] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0013] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0014] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0015] Through this application, by collecting the risk assessment parameters and proportion parameters of the object, the comprehensive risk assessment parameters of the target product are calculated, and then a risk assessment interval that can reflect the true risk level of the product is generated. This method not only takes into account the multi-dimensional characteristics of risk, but also takes into account the relative importance of each object in the product portfolio, thereby improving the accuracy of product risk assessment. Therefore, the problem of low accuracy of product risk assessment in related technologies can be solved, achieving the effect of improving the accuracy of product risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a hardware structure block diagram of a server device of a method for generating a risk assessment interval according to an embodiment of the present application;

[0017] Figure 2 is a flow chart of a method for generating a risk assessment interval according to an embodiment of the present application;

[0018] Figure 3 It is a flow chart of an improved fund ESG scoring system according to a specific embodiment of the present application;

[0019] Figure 4 It is a structural block diagram of a device for generating risk assessment intervals according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0022] The method embodiments provided in the embodiments of the present application can be executed in a server device or a similar computing device. Taking running on a server device as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a server device for a method for generating a risk assessment interval in an embodiment of the present application. Figure 1 As shown, the server device may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the server device may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above server device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0023] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for generating risk assessment intervals in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the server device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0024] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the server device. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0025] In this embodiment, a method for generating a risk assessment interval is provided. Figure 2 is a flow chart of a method for generating a risk assessment interval according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0026] Step S202, acquiring risk assessment parameters of N objects, obtaining N risk assessment parameters, wherein one object corresponds to one risk assessment parameter, the risk assessment parameter is used to represent the risk bearing capacity of the object for the target product in multiple risk dimensions, and N is a natural number greater than 1;

[0027] Step S204, respectively determining a proportion parameter of the target product corresponding to each of the N objects, to obtain N proportion parameters, wherein the proportion parameter is used to represent the investment proportion of the object in the corresponding product combination to the target product;

[0028] Step S206, using the N risk assessment parameters and the N ratio parameters, calculating a target risk assessment parameter;

[0029] Step S208: generating a risk assessment interval based on the target risk assessment parameter, wherein the risk assessment interval is used to represent the risk level value of the target product in the plurality of risk dimensions.

[0030] In this embodiment, the execution subject of the above steps can be a terminal, a server, a specific processor set in the terminal or server, or a processor or processing device set relatively independently from the terminal or server, but is not limited thereto.

[0031] Optionally, this embodiment involves evaluating the risk-bearing capacity of multiple objects (e.g., individuals, companies, or other entities) for target products in multiple risk dimensions. This method can be applied to a variety of scenarios, including but not limited to at least one of the following scenarios:

[0032] In the scenario of portfolio management, this method can be used to evaluate the impact of different assets on the risk of the entire portfolio. The risk assessment parameters of each asset can be determined based on its historical performance, volatility, credit rating and other factors, while the proportion parameter reflects the weight of the asset in the portfolio. The resulting risk assessment range can help investors understand the risk level of the entire portfolio.

[0033] In the supply chain management scenario, each supplier can be regarded as an object, and its risk assessment parameters may include delivery reliability, financial stability, and quality control capabilities. The proportion parameter represents the share of each supplier in the supply chain. With this method, enterprises can assess the risk of the entire supply chain and optimize supplier selection and management strategies accordingly.

[0034] In the scenario of project risk management, different project participants (such as contractors, suppliers, partners) can be regarded as objects, and their risk assessment parameters may include project delivery capabilities, historical performance, and financial status. The ratio parameter reflects their degree of involvement in the project. Project managers can use this method to assess the overall risk of the project and formulate corresponding risk mitigation measures.

[0035] In the insurance industry, in the design of insurance products, insurance companies can use this method to evaluate the risk-bearing capacity of different insured objects (such as individuals and enterprises). Risk assessment parameters may include factors such as the insured object's historical claims record, industry risk, and geographical location, while the ratio parameter may reflect the scope of insurance coverage. Through this method, insurance companies can set reasonable premiums and insurance terms for different objects.

[0036] In the credit assessment scenario, during the credit approval process, banks or financial institutions can assess the risk-bearing capacity of borrowers. Risk assessment parameters may include the borrower's credit score, income stability, and debt level, while the proportion parameter may represent the borrower's share of the bank's total loans. This approach can help financial institutions assess the overall risk of the loan portfolio and make credit decisions accordingly.

[0037] Environmental risk assessment scenario, in environmental management, different pollution sources can be regarded as objects, and their risk assessment parameters may include emission, pollution type and impact on the environment. The proportional parameter may represent the contribution of each pollution source to the total pollution load. In this way, environmental managers can assess environmental risks and formulate corresponding pollution control strategies.

[0038] In the gaming scenario, applying this risk assessment interval generation method can help game developers, operation teams, or investors evaluate the risk-bearing capacity of game projects in different risk dimensions.

[0039] Optionally, the object in this embodiment refers to a unit or entity involved in risk assessment, which can be a company, asset, project, or any other entity whose risk-bearing capacity can be quantified. For example, in an ESG investment scenario, an object refers to a specific company or asset in a fund portfolio, and each object has its own unique ESG risk characteristics.

[0040] Optionally, risk assessment parameters are quantitative indicators used to assess the risk-bearing capacity of an object in multiple risk dimensions. For example, in ESG evaluation, these parameters may include but are not limited to: environmental risks (such as carbon emissions, water resource use, etc.), social risks (such as labor rights, product safety, etc.), governance risks (such as board structure, financial transparency, etc.). The evaluation parameters of each dimension can be based on authoritative ESG scoring systems, such as Sustainalytics, MSCI, etc., or customized evaluation criteria.

[0041] Optionally, the target product refers to a product or investment portfolio that needs to be risk evaluated. For example, the target product refers to a fund composed of N objects, or it may be a broader financial product, such as a stock portfolio, a bond portfolio, an investment trust, etc. The risk level of the target product is obtained by calculating the risk evaluation parameters and proportion parameters of its constituent objects.

[0042] Optionally, the proportion parameter reflects the weight or investment ratio of a certain object in the target product. In the context of a fund, the proportion parameter can represent the proportion of the fund's holdings in a certain company or asset, which is directly related to the overall risk level of the fund, because the risk assessment parameters of different objects vary significantly in their risk-bearing capacity. The determination of the proportion parameter ensures that the risk assessment can take into account the actual importance of each object.

[0043] Optionally, the target risk assessment parameter is calculated by weighted average, which combines the risk assessment parameters of N objects and their respective proportional parameters to quantify the overall risk-bearing capacity of the target product in multiple risk dimensions. This parameter provides a comprehensive perspective on the risk level of the target product and is the basis for generating the risk assessment interval.

[0044] Optionally, the risk assessment interval is divided based on the target risk assessment parameters to indicate the risk level range of the target product in multiple risk dimensions. This interval can be a numerical range, for example, low risk (1-30), medium risk (31-70), high risk (71-100), or a more refined level division. The risk assessment interval provides investors with intuitive risk assessment results, helping them make choices based on their risk preferences and investment goals.

[0045] For example, in a financial scenario, the target product could be an ESG fund, and the targets are the companies in the fund’s portfolio. The following is a detailed implementation step:

[0046] In step S202, risk assessment parameters are obtained: Assume that there are N companies in the fund portfolio, corresponding to N risk assessment parameters, where N = 10. Each company has an ESG risk score based on an authoritative ESG rating website (such as Sustainalytics), ranging from 0 (lowest risk) to 100 (highest risk). These scores reflect the comprehensive risk-bearing capacity of each company in the three dimensions of environment, society and governance.

[0047] In step S204, determine the proportion parameter: determine the proportion of the holdings of the 10 companies in the fund as the proportion parameter. For example, the holding proportion of the first company is 20%, the second company is 15%, and so on, until the tenth company. These proportion parameters represent the investment proportion of the fund in each company, reflecting the importance of the company in the fund portfolio.

[0048] In step S206, the target risk assessment parameter is calculated: the comprehensive ESG risk score of the fund is calculated using the weighted average method. For example, if the first company's ESG risk score is 30 and its holding ratio is 20%, its contribution to the fund's risk score is 30×20%=6. After performing the same calculation for all companies, all contribution values ​​are added together and then divided by N to obtain the target risk assessment parameter. Alternatively, the score of each company can be directly multiplied by the corresponding ratio parameter and then summed, that is, the fund ESG score = ∑(company ESG score × holding ratio).

[0049] In step S208, generate risk assessment intervals: formulate the fund's ESG risk intervals based on the calculated target risk assessment parameters. For example, if the fund's comprehensive ESG risk score is 45, it can be classified as a medium risk interval. The risk interval division should take into account industry standards, historical data and market best practices to ensure the rationality and accuracy of the interval division.

[0050] For another example, in a game scenario, the target product can be a teamwork task in a multiplayer online game (such as an MMORPG), and the target is the players who participate in the task. The following is a detailed implementation step:

[0051] In step S202, a risk assessment parameter is obtained: Assume that a game team consists of N players, N = 5. Each player is assigned a risk assessment parameter based on his or her behavior and performance in the game, such as team contribution, role skills, and task completion. This parameter reflects the stability and potential risks of the player when completing team tasks, such as the proficiency of his or her skills, contribution to team goals, etc.

[0052] In step S204, determine the ratio parameter: determine the importance of each player in the team as the ratio parameter. For example, if the first player is responsible for team leadership and strategy formulation, and his importance ratio is higher than other members, then his ratio parameter can be set to a higher value, such as 35%, while the ratio parameters of other members are set accordingly according to their roles and contributions in the task.

[0053] In step S206, the target risk assessment parameter is calculated: the weighted average method is used to calculate the comprehensive risk of the team performing the task. For example, the risk assessment parameter of the first player is 60, and the proportion parameter is 35%, then his contribution to the team risk is 60×35%=21. After performing the same calculation for all players, all contribution values ​​are added together to obtain the team's comprehensive risk assessment parameter, which is used to evaluate the team's stability and risk level in completing a specific task.

[0054] In step S208, a risk assessment interval is generated: based on the calculated comprehensive risk assessment parameters, a risk interval for the team to perform the task is formulated. For example, if the team's comprehensive risk score is 80, it can be classified as a high-risk interval, which means that the team faces a greater potential risk when performing the task. Game developers can use this risk assessment to adjust the difficulty of the task, the reward mechanism, or provide additional training and guidance to improve the team's stability and the success rate of completing the task.

[0055] In gaming scenarios, this risk assessment interval generation method can be used to optimize the design of team tasks, improve players' gaming experience, and provide feedback on players' behavior and skill development. It also provides game developers with a tool to assess and manage in-game risks.

[0056] Although the two scenarios in the above embodiments are in different fields, they both obtain the risk assessment parameters and ratio parameters of the object, calculate the target risk assessment parameters, and finally generate a risk assessment interval to reflect the risk level of the target product in a specific dimension. In the financial field, this helps investors assess and manage non-financial risks; in the game field, it helps game developers and players optimize teamwork and task completion strategies. These embodiments demonstrate the application potential and value of the risk assessment interval generation method in different scenarios.

[0057] Through the above steps, by collecting the risk assessment parameters and proportion parameters of the object, the comprehensive risk assessment parameters of the target product are calculated, and then the risk assessment interval that can reflect the real risk level of the product is generated. This method not only takes into account the multi-dimensional characteristics of risk, but also takes into account the relative importance of each object in the product portfolio, thereby improving the accuracy of product risk assessment. Therefore, it can solve the problem of low accuracy of product risk assessment in related technologies and achieve the effect of improving the accuracy of product risk assessment.

[0058] In an exemplary embodiment, obtaining risk assessment parameters of N objects to obtain N risk assessment parameters includes: when the risk assessment parameters are first type parameters, obtaining risk assessment parameters of the N objects in multiple risk dimensions from a first target application to obtain N risk assessment parameters; when the risk assessment parameters are second type parameters, determining dimensions that affect transactions of the target product to obtain multiple risk dimensions;

[0059] For each of the objects, N risk assessment parameters are determined by the following steps: obtaining the performance value of the object corresponding to the target product in multiple risk dimensions to obtain multiple performance values, wherein the performance value is used to represent the risk-bearing capacity of the object for the target product in the risk dimension, and the performance value includes a historical performance value and a real-time performance value; inputting the multiple performance values ​​into a target generator to obtain a comprehensive performance value generated by the target generator, wherein the target generator is a linear model based on a neural network, and the target generator includes: a data processing layer and a nonlinear regression layer, the data processing layer is used to perform nonlinear numerical conversion on the multiple performance values, and extract features from the converted numerical values, and the extracted features are input into the nonlinear regression layer, and the nonlinear regression layer is used to perform correlation analysis on the extracted features and output the comprehensive performance value; determining N risk assessment parameters based on the comprehensive performance value of each of the objects.

[0060] Optionally, the first type of parameters in this embodiment refer to risk assessment parameters obtained directly from an authoritative risk assessment source, which are usually based on historical data and professional assessments, and can directly reflect the object's ability to bear specific risk dimensions. In a financial scenario, this may refer to scores obtained through ESG rating agencies such as Sustainalytics and MSCI, or risk values ​​calculated based on historical financial and market data. The second type of parameters refers to risk assessment parameters automatically generated based on the transaction impact dimensions of the target product. The acquisition of such parameters involves the identification of specific risk dimensions that may be encountered in the transaction of the target product, and the analysis of real-time or historical performance on these dimensions.

[0061] Optionally, the first target application in this embodiment refers to an application scenario that directly uses existing risk assessment parameters. For example, when conducting ESG risk assessment on a fund, the company's score data can be directly obtained from the ESG rating website. The second target application refers to an application scenario that requires analysis and determination of risk dimensions and their impact on target product transactions. For example, in a high-frequency trading environment, to assess the market risk of stocks, it may be necessary to analyze the stock's volatility, trading volume, market sentiment and other real-time performance values.

[0062] Optionally, the performance value in this embodiment is a quantitative indicator used to represent the object's ability to bear risk in the risk dimension, and may include historical performance values ​​and real-time performance values. Historical performance values ​​are based on past data, such as the company's financial statements, ESG reports, etc.; real-time performance values ​​reflect current or recent data points, such as real-time stock price fluctuations, corporate environmental emergencies, etc.

[0063] Optionally, the target generator in this embodiment is a linear model based on a neural network, which is used to process and analyze performance values ​​and generate comprehensive performance values. The model includes a data processing layer and a nonlinear regression layer: the data processing layer is used to perform nonlinear numerical conversion on the original performance value, with the purpose of converting the performance values ​​of different dimensions into a unified numerical range, which is convenient for subsequent analysis and processing. In addition, the data processing layer can also extract key features from the converted values, such as the volatility of a company's ESG score or the sensitivity of stock prices. The nonlinear regression layer performs correlation analysis on the extracted features, aiming to identify the intrinsic connection and influence degree between the performance values ​​of different risk dimensions. Through nonlinear regression analysis, the risk level faced by the object in the target product can be predicted and evaluated, and the comprehensive performance value is finally output as a risk assessment parameter. The comprehensive performance value is obtained by the target generator based on the analysis of the performance values ​​of multiple risk dimensions, reflecting the overall risk-bearing capacity of the object in the target product. Compared with the original performance value, the comprehensive performance value more comprehensively considers the interaction between the various risk dimensions, so it can provide a more accurate and comprehensive indicator for risk assessment.

[0064] When implementing the above method, the acquisition of the first type of parameters is usually relatively straightforward, while the generation of the second type of parameters involves complex algorithms and model training processes. The target generator achieves a dynamic assessment of risk-bearing capacity by converting real-time and historical performance values ​​into comprehensive performance values, which is particularly important for scenarios that require real-time monitoring and adjustment of risk strategies. Whether it is financial investment or risk management in other fields, this sophisticated and comprehensive risk assessment parameter generation method can provide strong support.

[0065] For example, in a gaming scenario, this risk assessment parameter generation method can be applied to a multiplayer online game, especially when a team is performing a difficult task or challenge. The following are the detailed implementation steps:

[0066] First type of parameters: Assuming that the risk assessment parameter is the first type of parameter, the scores of each player in multiple risk dimensions are obtained from the game's internal scoring system (first target application), such as teamwork ability, role completion, task success rate, etc. For example, the system can assign a teamwork risk score to each player based on historical task records to reflect his reliability when forming a team.

[0067] Second type of parameters: If the risk assessment parameter is a second type of parameter, it is necessary to determine the dimensions that affect the success rate of the team mission, such as the player's combat skills, equipment level, and tactical understanding ability. These dimensions are derived from the player's real-time performance in the game and historical data analysis, and specific indicators such as damage output in combat, mission completion time, and team contribution may need to be considered.

[0068] Obtain performance values: For each player, obtain their performance values ​​in multiple risk dimensions from game logs and real-time data, including historical performance values ​​(such as the success rate of past tasks) and real-time performance values ​​(such as the survival time of the current battle). These performance values ​​reflect the player's ability level and stability in specific risk dimensions.

[0069] Target Generator Input: Multiple performance values ​​for each player are input into the target generator, which includes a data processing layer and a nonlinear regression layer. The data processing layer performs nonlinear numerical transformations on the performance values, for example, converting the player's damage output into a standardized risk value, while extracting key features such as the player's combat skill proficiency and equipment level.

[0070] Non-linear regression layer analysis: The extracted features are fed into a non-linear regression layer for correlation analysis to determine how the performance values ​​of different dimensions jointly affect the player's overall risk-taking ability. For example, a player with high damage output may be more dangerous in combat, but if their teamwork ability is also strong, the overall risk may be low.

[0071] Comprehensive performance value output: The nonlinear regression layer finally outputs the comprehensive performance value of each player, which takes into account all risk dimensions and reflects the overall risk-taking level of the player in the team.

[0072] Determination of risk assessment parameters: Based on the comprehensive performance value of each player, we have determined N risk assessment parameters. These parameters can be used to evaluate the risks of team tasks, help team leaders choose the most suitable teammates, and improve the success rate of tasks.

[0073] For specific applications in game scenarios, suppose a team of 5 people needs to complete a difficult dungeon task. The teamwork score of each player in the past dungeon is obtained from the game's internal scoring system (first type parameter). At the same time, the real-time game data is analyzed to determine combat skills, equipment level, and tactical understanding ability as risk dimensions that affect dungeon completion (second type parameter). Through the processing and analysis of the above-mentioned goal generator, the comprehensive performance value of each player is generated, and then their risk assessment parameters are determined. Team leaders can optimize the team composition based on these parameters and select players who perform well in both combat skills and teamwork, thereby reducing the risk of mission failure and improving the gaming experience.

[0074] In game scenarios, this risk assessment parameter generation method can be used to evaluate the risk-bearing capacity of players in a team, helping team leaders to screen team members and assign tasks more effectively. At the same time, this neural network-based linear model can process and analyze historical and real-time data to output more accurate comprehensive performance values.

[0075] In an exemplary embodiment, respectively determining the proportion parameter of the target product corresponding to each of the N objects to obtain N proportion parameters includes: for each of the objects, determining the proportion parameter of the object to the target product by the following steps to obtain N proportion parameters: obtaining report data of the object, wherein the report data is data generated based on the numerical value of the target product held by the object within a preset time period; determining the quantity or parameter value of the target product held by the object from the report data to obtain the proportion parameter.

[0076] Optionally, in this embodiment, determining the ratio parameter of each object in the N objects corresponding to the target product refers to measuring the relative weight or contribution of each object in the target product portfolio. This process is crucial for calculating the comprehensive risk of the target product or evaluating its overall performance.

[0077] The following is an explanation of the detailed steps, especially taking funds in a financial scenario as an example:

[0078] Obtaining report data: Report data here refers to the fund's regular financial reports or position reports, which provide details of the fund's holdings within a preset time period (for example, quarterly, semi-annual or annual). The selection of the preset time period should match the risk assessment cycle and the characteristics of the target product to ensure the timeliness and accuracy of the data.

[0079] Determine the number of holdings or parameter values: From the report data, you can determine the number of holdings or parameter values ​​of each object (in this scenario, the company or asset in the fund's portfolio) in the fund. The number of holdings usually refers to the fund's holdings of a company's stock or bonds, while the parameter value may include the investment amount, holding ratio, etc. For example, suppose Fund A shows in its holdings report at the end of a quarter that it holds 1,000 shares of Company B, and the fund's total holdings are 10,000 shares, then the proportion parameter of Company B in Fund A is 10%.

[0080] Calculate the proportion parameter: After obtaining the number of positions or parameter values ​​of each object, the proportion parameter is usually calculated by comparing the number or parameter value with the total holdings or total investment amount to obtain the relative proportion of the object in the target product. In the fund scenario, this is usually expressed as the fund's holding ratio of a company or asset, that is, its share in the fund's portfolio.

[0081] Applying ratio parameters: Once the ratio parameters of N objects are determined, these parameters will be used in the subsequent risk assessment parameter calculation process. For example, when calculating the ESG risk score of a fund, the risk assessment parameter of each company will be multiplied by its holding ratio in the fund, and then these products will be summed to obtain the comprehensive risk assessment parameter of the fund.

[0082] Specifically for the application of game scenarios, suppose you are evaluating a virtual fund in a game (such as a pool of gold coins and resources jointly managed by players), where the target product can be a specific resource or gold coin. Each object can be a player involved in fund management. In this scenario, the report data may come from the game's internal transaction records or the player's contribution records, and the proportion parameter reflects each player's contribution or control share to the virtual fund. Through this process, the overall risk of the virtual fund can be calculated or its performance in the game can be evaluated, thereby providing players with strategic recommendations for managing resources and gold coins.

[0083] This embodiment can accurately measure the relative importance of each object to the target product by acquiring report data and determining ratio parameters, which provides a basis for subsequent comprehensive risk evaluation and performance assessment.

[0084] In an exemplary embodiment, using the N risk assessment parameters and the N ratio parameters to calculate a target risk assessment parameter includes: performing a weighted average operation on the N risk assessment parameters and the N ratio parameters to obtain the target risk assessment parameter;

[0085] Among them, the weighted average operation includes the following steps: calculating the product between the risk assessment parameter of each object and the corresponding proportion parameter to obtain N first numerical values; calculating the sum of the N first numerical values ​​to obtain a second numerical value; calculating the sum of the N proportion parameters to obtain a third numerical value; using the second numerical value and the third numerical value to calculate the target risk assessment parameter.

[0086] Optionally, in this embodiment, the process of calculating the target risk assessment parameter involves performing a weighted average operation on the risk assessment parameters of N objects and their corresponding ratio parameters. This calculation method can comprehensively consider the individual risk assessments of all objects and their relative importance in the target product, thereby obtaining a more comprehensive target risk assessment parameter.

[0087] Optionally, the product of the risk assessment parameter and the proportion parameter of each object (N first values) is calculated as follows: for each object i (i = 1, 2, ..., N), first calculate the product between its risk assessment parameter Ri and its proportion parameter Pi in the target product, that is, the first value Vi. Mathematically expressed as: Vi = Ri × Pi. For example, in a financial scenario, if there are N = 5 companies in a fund investment portfolio, then for each company, its ESG risk score is multiplied by its holding ratio in the fund to obtain the contribution value of each company to the fund's ESG risk.

[0088] Optionally, the sum of the first values ​​(second value) is calculated as follows: N first values ​​are added together to obtain the total contribution of all objects to the risk assessment of the target product, i.e., the second value S. Mathematically expressed as: S = ∑Vi (i = 1, 2, ..., N); In the above fund investment portfolio example, the contribution values ​​of all companies to ESG risks are added together to obtain the weighted sum of the fund's overall ESG risk score.

[0089] Optionally, the sum of the proportion parameters (third value) is calculated as follows: N proportion parameters are added together to obtain the total weight of all objects in the target product, i.e., the third value T. Mathematically expressed as: T = ∑Pi (i = 1, 2, ..., N); in the fund scenario, this means adding up the holding proportions of all companies in the fund to obtain a sum, which should be equal to 1 (100%), because the holding proportion represents the allocation ratio of the fund investment portfolio.

[0090] Optionally, the target risk assessment parameter is calculated using the second value and the third value as follows: the second value S is divided by the third value T to obtain the target risk assessment parameter M. Mathematically expressed as: M = S / T; in the case of a fund, the fund's comprehensive ESG risk score is obtained by dividing the sum of the weighted contributions of all companies to ESG risks by the total holding ratio of the fund's investment portfolio. This score reflects the overall non-financial risk level of the fund and can be used to compare and evaluate the ESG performance of different funds.

[0091] This embodiment can comprehensively consider the risk assessment parameters of N objects and their relative weights in the target product through weighted average operation, so as to calculate a parameter that can accurately reflect the overall risk level of the target product. This method is particularly useful when dealing with scenarios such as ESG fund risk assessment and risk assessment of teamwork tasks in games, because it can take into account the individual differences of different objects and their different contributions to the overall goal.

[0092] In an exemplary embodiment, generating a risk assessment interval based on the target risk assessment parameter includes at least one of the following:

[0093] Dividing a first numerical range of the parameter value of the target risk assessment parameter, and generating a plurality of risk assessment numerical intervals based on the first numerical range to obtain the risk assessment intervals, wherein each of the risk assessment numerical intervals corresponds to a risk level;

[0094] When the parameter value of the risk assessment parameter is not within the second numerical range corresponding to the original risk assessment interval, the original risk assessment interval is adjusted according to the risk assessment parameter to obtain the risk assessment interval.

[0095] Optionally, in this embodiment, the risk assessment interval is generated to more intuitively understand and express the risk level represented by the target risk assessment parameter. The risk assessment interval can not only help decision makers quickly identify the risk level, but also dynamically adjust the interval when the parameter value changes, ensuring that the assessment result is always close to the actual risk situation.

[0096] There are two ways to generate risk assessment intervals:

[0097] Method 1: Divide the first numerical range to generate a risk assessment numerical interval, including:

[0098] Define the numerical range: First, divide the target risk assessment parameter into several first numerical ranges according to its possible value range. Each range represents a different risk level, such as low risk, medium risk, high risk, etc. This usually requires reference to industry standards, historical data and market best practices to set reasonable boundaries.

[0099] Generate risk assessment numerical intervals: Assign a risk level to each first numerical range to form risk assessment numerical intervals. For example, if the value range of the target risk assessment parameter is 0 to 100, 0 to 30 can be defined as a low risk interval, 31 to 70 as a medium risk interval, and 71 to 100 as a high risk interval.

[0100] Apply risk assessment intervals: Once the value of the target risk assessment parameter falls within a certain risk assessment numerical interval, the risk level of the target product can be directly assessed based on the risk level corresponding to the interval. This method provides a fast and intuitive risk assessment method, especially suitable for scenarios where assessment results need to be updated frequently.

[0101] Method 2: Dynamically adjust the original risk assessment interval, including:

[0102] Original risk assessment range: At the beginning, according to the existing data and assessment criteria, a set of second value ranges is set, each range corresponds to a risk level. This set of second value ranges can be based on the average risk level of historical data, or refer to the general risk status of similar products.

[0103] Evaluate target risk assessment parameters: After calculating the value of the target risk assessment parameter, if it is found that the value is not within any of the set second numerical ranges, or deviates significantly from market trends or industry standards, then the original second numerical range may need to be adjusted.

[0104] Interval adjustment: Based on the value of the target risk assessment parameter, the original risk assessment interval is adjusted by analyzing market conditions, industry dynamics, etc. For example, if the fund's comprehensive ESG score is significantly higher than the industry average, the threshold of the high-risk interval can be adjusted upward to more accurately reflect its performance in ESG.

[0105] Update risk level: After adjustment, the original second value range becomes a new risk assessment interval. Each interval still corresponds to a risk level, but the interval boundaries and level definitions may change according to the latest assessment results. This method is more flexible and can adapt to the ever-changing market environment and assessment standards, ensuring that the risk assessment interval is always consistent with the actual situation.

[0106] This embodiment can determine a clear and intuitive risk level division by dividing the first numerical range or dynamically adjusting the original risk assessment interval. In financial scenarios, this helps investors evaluate and compare the ESG performance of different funds; in gaming scenarios, it can help game developers or team leaders optimize strategies and improve task completion efficiency. By regularly updating the risk assessment interval, the accuracy and timeliness of the assessment results can be ensured, and better responses to market changes and player needs can be achieved.

[0107] In an exemplary embodiment, after generating a risk assessment interval based on the target risk assessment parameters, the method further includes: setting a numerical range of the risk assessment interval; dividing the numerical range into multiple sub-ranges according to a preset numerical length, and generating risk indication information corresponding to the multiple sub-ranges; generating a risk indication chart according to the correspondence between the multiple sub-ranges and the multiple risk indication information; and sending the risk indication chart to a second target application based on a preset format, so as to visually display the risk indication chart through the second target application.

[0108] Optionally, in this embodiment, after the risk assessment interval is generated, the interval is further refined and displayed in a chart form to enhance information visualization and user understanding. The following are the detailed steps:

[0109] S1, set the numerical range of the risk assessment interval: First, determine the numerical range covered by the risk assessment interval. This step is based on the possible value range of the target risk assessment parameter and the risk level boundary set previously. For example, if the value range of the risk assessment parameter is 0 to 100, the entire range can be divided into three risk levels: low, medium, and high.

[0110] S2, dividing sub-ranges and generating risk indication information: the above numerical range is further divided into multiple sub-ranges according to a preset numerical length (for example, the length of each sub-range can be set to 10). Each sub-range corresponds to a more specific risk indication information, such as "very low risk (0-10)", "low risk (11-20)", "medium-low risk (21-30)", etc. In this way, a more fine-grained division can provide a more accurate risk assessment.

[0111] S3, generate risk indicator chart: Based on the sub-ranges and risk indicator information, an intuitive risk indicator chart, such as a bar chart, heat map or distribution chart, can be generated. Each sub-range in the chart is represented by a different color or pattern, and the corresponding risk indicator information is attached to the chart or directly marked on each sub-range. For example, in a bar chart, the range of values ​​0-10 can be marked in green, indicating extremely low risk; while the range of values ​​91-100 can be marked in red, indicating extremely high risk.

[0112] S4, sending to a second target application: sending the generated risk indication chart to a second target application in a preset format (e.g., image formats such as PNG, JPEG, or SVG, or data formats such as JSON, XML, etc.). The second target application may be a risk management platform, a fund analysis software, or a decision support tool within a game, which has the ability to display charts and data for users (e.g., fund managers, investors, or game team leaders) to intuitively understand the risk status.

[0113] S5, Visualization Display: After receiving the risk indication chart, the second target application displays it in a visual way on its interface. The display of the chart can be static or dynamic, for example, dynamically displaying the changes in the fund's ESG risk score through a time series, or displaying the risk level of the team's task execution in real time in the game.

[0114] Through the above steps, this embodiment not only realizes the conversion from quantitative data to qualitative risk levels, but also further presents this information to users in the form of intuitive charts, so that they can quickly grasp the details of risk assessment. In complex scenarios such as finance and games, this visual display helps improve decision-making efficiency and make risk management more accurate and efficient. At the same time, the dynamic update function of the chart ensures the timeliness and flexibility of risk assessment information, and can cope with rapid changes in the market or game environment.

[0115] In an exemplary embodiment, after sending the risk indication chart to a second target application based on a preset format so as to visually display the risk indication chart through the second target application, the method further includes: receiving a trigger operation acting on the risk indication chart through the second target application, wherein the trigger operation includes querying the data included in the risk indication chart and adjusting the playback parameters of the risk indication chart; generating trigger data using the trigger operation, and adjusting the risk indication chart based on the trigger data.

[0116] Optionally, in this embodiment, based on the improved interactivity of the risk indication chart, the user can receive and act on the chart through the second target application to achieve more in-depth analysis and customized information display. The following is a description of the specific steps:

[0117] Trigger operation reception: In the interface of the second target application, users can perform trigger operations on risk indicator charts, including data query and adjustment of chart playback parameters. For example, in the ESG risk assessment chart of a fund, users can query detailed data within a certain risk level by clicking on a sub-range of the risk level, such as which specific funds or companies fall into this level; or users can adjust chart playback parameters, such as the size of the playback window, time window, and data filtering conditions, to dynamically view the risk distribution in different historical periods or under specific conditions.

[0118] Trigger data generation: When a user performs a trigger operation, the system generates corresponding trigger data. The trigger data contains the specific content of the user's query or the information of the playback parameter adjustment. For example, in a data query operation, the trigger data may include the risk level selected by the user and the relevant time period; in a playback parameter adjustment, the trigger data may include the new time window or data filtering conditions set by the user.

[0119] Risk indicator chart adjustment: The system adjusts the risk indicator chart accordingly based on the trigger data received. If the trigger operation is a data query, the system will display the query results, which may be a list of detailed data next to the chart, or highlight a specific sub-range in the chart; if the trigger operation is a chart playback parameter adjustment, the system will regenerate or update the chart according to the new parameters to reflect the content that the user wants to view. For example, the system can dynamically adjust the timeline to display the ESG risk distribution in different historical periods, or filter out certain data points to only display risk assessments under specific conditions.

[0120] This embodiment increases the flexibility and practicality of the risk indicator chart through this interactivity, allowing users to customize the chart according to their needs and concerns. In financial scenarios, investors can obtain more personalized ESG risk assessments through query and adjustment, helping them make more accurate investment decisions; in game scenarios, team leaders can dynamically adjust the chart to monitor the risk level of team members completing tasks in real time, optimize team composition or adjust tactics.

[0121] The present application is described in detail below with reference to specific embodiments:

[0122] This specific embodiment relates to an improved fund ESG (environmental, social and governance) scoring system, which collects and processes the ESG risk scores of fund-holding companies, combines the holding proportions of each company in the fund, calculates the fund's comprehensive ESG score, and generates dynamic risk assessment intervals based on this score, providing investors and fund managers with an intuitive tool to evaluate and monitor the fund's non-financial risks.

[0123] like Figure 3 FIG. 1 is a flowchart of this specific embodiment, which includes the following steps:

[0124] S301, Data Collection: Obtain ESG risk score data of fund holding companies from authoritative ESG scoring websites. At the same time, obtain the holding ratio data of each company in the fund from the fund company's public report.

[0125] S302, weighted average calculation: For each fund, use the ESG risk scores (Ri) and holding proportions (Pi) of N holding companies to calculate the fund's comprehensive ESG score (M) by weighted average. The specific steps are as follows:

[0126] The product of each company's risk score and position ratio (Vi=Ri×Pi) is calculated to obtain N first values.

[0127] The sum of the N first values ​​(S=∑Vi) is calculated to obtain the second value.

[0128] Calculate the sum of N holding ratios (T=∑Pi) to obtain a third value.

[0129] The target risk assessment parameter, i.e., the comprehensive ESG score of the fund (M=S / T), is calculated using the second and third values.

[0130] S303, generate risk assessment interval:

[0131] Set the numerical range of the risk assessment interval, for example, set the ESG score range from 0 to 100.

[0132] The numerical range is divided into multiple sub-ranges according to a preset numerical length (for example, one sub-range every 10 minutes), and risk indication information is generated for each sub-range, such as "low risk (0-10)", "medium risk (11-20)", etc.

[0133] The above sub-ranges and risk indication information are used to generate a risk indication chart. Each sub-range in the chart is represented by a different color, which intuitively shows the ESG risk level distribution of the fund.

[0134] Based on a preset format (such as SVG or JSON), the risk indication chart is sent to a second target application, such as fund analysis software or an internal risk management platform of a financial institution, to achieve visual display of the chart.

[0135] S304, Interaction and Dynamic Adjustment:

[0136] In the second target application, users can perform trigger operations on the risk indicator chart. For example, click on a sub-range on the chart to query the list of companies that fall into that risk level, as well as their detailed ESG scores and holding ratios.

[0137] Users can also adjust chart playback parameters, such as setting a time window to dynamically view the ESG risk distribution of funds in different historical periods, or adjust data filtering conditions to only display fund risk scores in specific industries or regions.

[0138] The system adjusts the risk indicator chart based on the trigger data generated by the user trigger operation, such as highlighting the sub-range of the user query, or regenerating the chart to reflect the playback parameters set by the user.

[0139] If the user adjusts the playback parameters of the chart, the system will recalculate the fund ESG score and risk assessment range for the relevant time period to ensure that the chart always reflects the latest data and user needs.

[0140] Through this specific embodiment, not only an accurate fund ESG score calculation method is provided, but also a comprehensive assessment and effective monitoring of the fund's non-financial risks are achieved by generating risk assessment intervals and risk indication charts, as well as supporting user interaction and dynamic data updates.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0142] In this embodiment, a device for generating a risk assessment interval is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0143] Figure 4 is a structural block diagram of a device for generating a risk assessment interval according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0144] A first acquisition module 42 is used to acquire risk assessment parameters of N objects, and obtain N risk assessment parameters, wherein one object corresponds to one risk assessment parameter, and the risk assessment parameter is used to represent the risk bearing capacity of the object for the target product in multiple risk dimensions, and N is a natural number greater than 1;

[0145] A first determination module 44 is used to determine the proportion parameter of the target product corresponding to each of the N objects, to obtain N proportion parameters, wherein the proportion parameter is used to represent the investment proportion of the object in the corresponding product combination to the target product;

[0146] A first calculation module 46, used to calculate a target risk assessment parameter using the N risk assessment parameters and the N ratio parameters;

[0147] The first generating module 48 is used to generate a risk assessment interval based on the target risk assessment parameter, wherein the risk assessment interval is used to represent the risk level value of the target product in the multiple risk dimensions.

[0148] In an exemplary embodiment, the first acquisition module 42 includes: a first acquisition unit, which is used to obtain risk assessment parameters of N objects in multiple risk dimensions from the first target application when the risk assessment parameter is a first type parameter, so as to obtain N risk assessment parameters; a first determination unit, which is used to determine the dimensions that affect the transaction of the target product when the risk assessment parameter is a second type parameter, so as to obtain multiple risk dimensions; a second determination unit, which is used to determine the N risk assessment parameters for each object through the following steps: obtaining the performance value of the object corresponding to the target product in multiple risk dimensions, so as to obtain multiple performance values, wherein the performance value is used to represent the The object's risk-bearing capacity for the target product in the risk dimension, the performance value includes a historical performance value and a real-time performance value; a plurality of the performance values ​​are input into a target generator to obtain a comprehensive performance value generated by the target generator, wherein the target generator is a linear model based on a neural network, and the target generator includes: a data processing layer and a nonlinear regression layer, the data processing layer is used to perform nonlinear numerical conversion on the plurality of the performance values, and extract features from the converted numerical values, and the extracted features are input into the nonlinear regression layer, and the nonlinear regression layer is used to perform correlation analysis on the extracted features and output the comprehensive performance value; N risk assessment parameters are determined based on the comprehensive performance value of each of the objects.

[0149] In an exemplary embodiment, the above-mentioned first determination module 44 includes: a third determination unit, which is used to determine, for each of the objects, the proportion parameter of the object to the target product through the following steps to obtain N of the proportion parameters: obtaining report data of the object, wherein the report data is data generated based on the numerical value of the target product held by the object within a preset time period; determining the quantity or parameter value of the target product held by the object from the report data to obtain the proportion parameter.

[0150] In an exemplary embodiment, the above-mentioned first calculation module 46 includes: a first processing unit, used to perform a weighted average operation on N risk assessment parameters and N proportion parameters to obtain the target risk assessment parameter; wherein the weighted average operation includes the following steps: calculating the product between the risk assessment parameter of each object and the corresponding proportion parameter to obtain N first numerical values; calculating the sum of the N first numerical values ​​to obtain a second numerical value; calculating the sum of the N proportion parameters to obtain a third numerical value; and using the second numerical value and the third numerical value to calculate the target risk assessment parameter.

[0151] In an exemplary embodiment, the above-mentioned first generation module 48 includes at least one of the following: a first division unit, used to divide the first numerical range of the parameter value of the target risk assessment parameter, and generate multiple risk assessment numerical intervals based on the first numerical range to obtain the risk assessment interval, wherein each of the risk assessment numerical intervals corresponds to a risk level; a first adjustment unit, used to adjust the original risk assessment interval according to the risk assessment parameter to obtain the risk assessment interval when the parameter value of the risk assessment parameter is not within the second numerical range corresponding to the original risk assessment interval.

[0152] In an exemplary embodiment, the above-mentioned device also includes: a first setting module, which is used to set the numerical range of the risk assessment interval after generating the risk assessment interval based on the target risk assessment parameter; a first processing module, which is used to divide the numerical range into multiple sub-ranges according to a preset numerical length, and generate risk indication information corresponding to the multiple sub-ranges; a second generation module, which is used to generate a risk indication chart according to the correspondence between the multiple sub-ranges and the multiple risk indication information; a first sending module, which is used to send the risk indication chart to the second target application based on a preset format, so as to visually display the risk indication chart through the second target application.

[0153] In an exemplary embodiment, the above-mentioned device also includes: a first receiving module, used to send the risk indication chart to a second target application based on a preset format, so as to visually display the risk indication chart through the second target application, and then receive a trigger operation acting on the risk indication chart through the second target application, wherein the trigger operation includes querying the data included in the risk indication chart and adjusting the playback parameters of the risk indication chart; a third generating module, used to generate trigger data using the trigger operation, and adjust the risk indication chart based on the trigger data.

[0154] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0155] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0156] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0157] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0158] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0159] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0160] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0161] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any one of the above method embodiments.

[0162] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0163] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0164] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for generating a risk assessment interval, characterized in that: The method comprises: Obtaining risk assessment parameters of N objects to obtain N risk assessment parameters, wherein one object corresponds to one risk assessment parameter, the risk assessment parameter is used to represent the risk bearing capacity of the object for the target product in multiple risk dimensions, and N is a natural number greater than 1; Determine the proportion parameter of the target product corresponding to each of the N objects respectively, and obtain N proportion parameters, wherein the proportion parameter is used to represent the investment proportion of the object in the corresponding product combination to the target product; Calculating a target risk assessment parameter using the N risk assessment parameters and the N ratio parameters; A risk assessment interval is generated based on the target risk assessment parameter, wherein the risk assessment interval is used to represent the risk level value of the target product in the plurality of risk dimensions.

2. The method according to claim 1, characterized in that Obtain risk assessment parameters of N objects, and obtain N risk assessment parameters, including: In the case where the risk assessment parameter is a first type parameter, obtaining risk assessment parameters of N objects in the plurality of risk dimensions from a first target application to obtain N risk assessment parameters; In the case where the risk assessment parameter is a second type parameter, determining the dimension that affects the transaction of the target product to obtain a plurality of risk dimensions; For each of the objects, N risk assessment parameters are determined by the following steps: Acquire the performance values ​​of the object corresponding to the target product in the multiple risk dimensions to obtain multiple performance values, wherein the performance values ​​are used to represent the risk-bearing capacity of the object for the target product in the risk dimensions, and the performance values ​​include historical performance values ​​and real-time performance values; Inputting a plurality of the performance values ​​into a target generator to obtain a comprehensive performance value generated by the target generator, wherein the target generator is a linear model based on a neural network, and the target generator includes: a data processing layer and a nonlinear regression layer, the data processing layer is used to perform nonlinear numerical conversion on the plurality of the performance values, and extract features from the converted numerical values, and input the extracted features into the nonlinear regression layer, and the nonlinear regression layer is used to perform correlation analysis on the extracted features and output the comprehensive performance value; N risk assessment parameters are determined based on the comprehensive performance value of each of the objects.

3. The method according to claim 1, characterized in that Determine the proportion parameter of the target product corresponding to each of the N objects respectively, and obtain N proportion parameters, including: For each of the objects, the ratio parameter of the object to the target product is determined by the following steps to obtain N ratio parameters: Acquiring report data of the subject, wherein the report data is data generated based on the value of the subject holding the target product within a preset time period; The quantity or parameter value of the target product held by the object is determined from the report data to obtain the proportion parameter.

4. The method according to claim 1, characterized in that: Calculating a target risk assessment parameter using the N risk assessment parameters and the N ratio parameters includes: Performing a weighted average operation on the N risk assessment parameters and the N ratio parameters to obtain the target risk assessment parameter; The weighted average operation includes the following steps: Calculate the product of the risk assessment parameter of each object and the corresponding ratio parameter to obtain N first values; Calculate the sum of N first values ​​to obtain a second value; Calculating the sum of the N proportion parameters to obtain a third value; The target risk assessment parameter is calculated using the second value and the third value.

5. The method according to claim 1, characterized in that Generating a risk assessment interval based on the target risk assessment parameter includes at least one of the following: Dividing a first numerical range of the parameter value of the target risk assessment parameter, and generating a plurality of risk assessment numerical intervals based on the first numerical range to obtain the risk assessment intervals, wherein each of the risk assessment numerical intervals corresponds to a risk level; When the parameter value of the risk assessment parameter is not within the second numerical range corresponding to the original risk assessment interval, the original risk assessment interval is adjusted according to the risk assessment parameter to obtain the risk assessment interval.

6. The method according to claim 1, characterized in that After generating the risk assessment interval based on the target risk assessment parameter, the method further includes: Setting a numerical range of the risk assessment interval; Dividing the numerical range into a plurality of sub-ranges according to a preset numerical length, and generating risk indication information corresponding to the plurality of sub-ranges; generating a risk indication chart according to the correspondence between the plurality of sub-ranges and the plurality of risk indication information; The risk indication chart is sent to a second target application based on a preset format, so that the risk indication chart is visually displayed through the second target application.

7. The method according to claim 6, characterized in that After sending the risk indication chart to the second target application based on a preset format so as to visually display the risk indication chart through the second target application, the method further includes: receiving, through the second target application, a trigger operation acting on the risk indication chart, wherein the trigger operation includes querying data included in the risk indication chart and adjusting playback parameters of the risk indication chart; The trigger operation is used to generate trigger data, and the risk indication graph is adjusted based on the trigger data.

8. A device for generating a risk assessment interval, characterized in that: include: A first acquisition module is used to acquire risk assessment parameters of N objects, and obtain N risk assessment parameters, wherein one object corresponds to one risk assessment parameter, and the risk assessment parameter is used to represent the risk bearing capacity of the object for the target product in multiple risk dimensions, and N is a natural number greater than 1; A first determination module is used to determine the proportion parameter of the target product corresponding to each of the N objects, to obtain N proportion parameters, wherein the proportion parameter is used to represent the investment proportion of the object in the corresponding product combination to the target product; A first calculation module, used to calculate a target risk assessment parameter using the N risk assessment parameters and the N ratio parameters; The first generating module is used to generate a risk assessment interval based on the target risk assessment parameter, wherein the risk assessment interval is used to represent the risk level value of the target product in the multiple risk dimensions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 7 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.

Images