Artificial intelligence-based economic risk assessment method and system

By screening and weighting economic data under multiple data sources and establishing an economic representation model, the problem of not being able to screen high-quality data in data processing is solved, the accuracy and reliability of risk assessment are improved, and decision-making in complex environments is provided. support.

CN118941094AInactive Publication Date: 2024-11-12SHENZHEN TIANZHIQU INTELLIGENT TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411176724.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, high-quality data cannot be accurately screened out when data processing is performed, resulting in a decrease in the accuracy of economic risk assessment results.

Method used

By obtaining the target economic data of the target object under multiple data sources, determining the model parameters and establishing an economic representation model, monitoring the membership between the sensor data and the model in real time, calculating the credibility and weighting processing, and then conducting risk assessment.

Benefits of technology

It improves the integration, real-time and accuracy of data, enhances the ability to assess risks, and provides more reliable support for decision-making in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941094A_ABST
    Figure CN118941094A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an economic risk assessment method and system based on artificial intelligence, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining target economic data corresponding to target economic parameters of a target object under various data sources; determining model parameters corresponding to the target object according to the target economic data, and determining an economic representation model according to the model parameters; obtaining sensor data corresponding to the target object under real-time monitoring, and calculating a membership degree between the sensor data and the economic representation model; performing data fusion on the sensor data according to the membership degree to obtain credibility corresponding to the sensor data; and determining weight information corresponding to the sensor data according to the membership degree and the credibility, and performing risk assessment according to the weight information and the sensor data to obtain a target assessment result. The problem that high-quality data cannot be accurately screened out during data processing in the prior art, so that the accuracy of an evaluation result is reduced is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an economic risk assessment method and system based on artificial intelligence. Background Art

[0002] With the development of artificial intelligence, machine learning models can provide more accurate and reliable risk predictions. These models can use complex algorithms and large-scale data sets to identify potential risk factors and patterns. Moreover, with the improvement of real-time data processing and analysis capabilities, machine learning has shown increasing potential in real-time risk assessment and instant decision support. This is particularly important in fields such as finance, insurance, and security. However, the performance of machine learning models in related technologies is highly dependent on the quality of input data. If the data quality is poor or the data is incomplete, the accuracy of the evaluation results may be greatly reduced. However, in related technologies, high-quality data cannot be accurately screened out during data processing, thereby reducing the accuracy of the evaluation results. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide an economic risk assessment method and system based on artificial intelligence, aiming to solve the problem in related technologies that high-quality data cannot be accurately screened out during data processing, thereby reducing the accuracy of the assessment results.

[0004] In a first aspect, an embodiment of the present invention provides an economic risk assessment method based on artificial intelligence, comprising:

[0005] Obtain target economic data corresponding to target economic parameters of target objects under multiple data sources;

[0006] Determining model parameters corresponding to the target object according to the target economic data, and determining an economic representation model according to the model parameters;

[0007] Obtaining sensor data corresponding to the target object under real-time monitoring, and calculating the degree of membership between the sensor data and the economic representation model;

[0008] Performing data fusion on the sensor data according to the degree of membership to obtain the credibility corresponding to the sensor data;

[0009] The weight information corresponding to the sensor data is determined according to the membership degree and the credibility, and a risk assessment is performed according to the weight information and the sensor data to obtain a target assessment result.

[0010] In a second aspect, an embodiment of the present invention provides an economic risk assessment system based on artificial intelligence, comprising:

[0011] A data collection module is used to obtain target economic data corresponding to target economic parameters of target objects under multiple data sources;

[0012] A model determination module, used to determine the model parameters corresponding to the target object according to the target economic data, and determine the economic representation model according to the model parameters;

[0013] A data processing module, used to obtain sensor data corresponding to the target object under real-time monitoring, and calculate the degree of membership between the sensor data and the economic representation model;

[0014] A data fusion module, used for performing data fusion on the sensor data according to the membership degree to obtain the credibility corresponding to the sensor data;

[0015] The data evaluation module is used to determine the weight information corresponding to the sensor data according to the membership degree and the credibility, and perform risk evaluation according to the weight information and the sensor data to obtain a target evaluation result.

[0016] In a third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any one of the economic risk assessment methods based on artificial intelligence provided in the specification of the present invention are implemented.

[0017] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of the economic risk assessment methods based on artificial intelligence provided in the specification of the present invention.

[0018] The embodiment of the present invention provides an economic risk assessment method and system based on artificial intelligence, which includes obtaining target economic data corresponding to target economic parameters of a target object under multiple data sources, and can obtain more comprehensive and accurate target economic data. This helps to comprehensively consider information from different sources and improve the integrity and credibility of the data. Then, the model parameters are determined based on the target economic data, and an economic characterization model is established, which can more accurately describe the economic characteristics and behavior patterns of the target object, and provide a basis for subsequent data analysis and decision-making. Thus, the sensor data of the target object is obtained under real-time monitoring, and the changes in the state and real-time situation of the target object can be captured in time, providing the latest data support for risk assessment. Then, the membership between the sensor data and the model is calculated using the economic characterization model, which can quantify the matching degree between the data and the model, and improve the understanding and utilization efficiency of the sensor data. Then, the credibility of the sensor data is determined based on the membership, and the weight information is determined based on the membership and credibility, which helps to weight each sensor data according to its contribution, and improve the accuracy and comprehensiveness of the comprehensive assessment results. Finally, risk assessment is performed based on the weight information and sensor data, which can comprehensively consider the information of different data sources, provide decision makers with comprehensive assessment results and accurate risk prediction based on real-time data, and support timely decision-making and action. This method can not only improve the integration, real-time and accuracy of data, thereby enhancing the ability of risk assessment and providing more reliable support for decision-making in complex environments, but also solve the problem in related technologies that high-quality data cannot be accurately screened out during data processing, thereby reducing the accuracy of the assessment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of an economic risk assessment method based on artificial intelligence provided by an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of the module structure of an economic risk assessment system based on artificial intelligence provided by an embodiment of the present invention;

[0022] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0025] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] The embodiment of the present invention provides an economic risk assessment method and system based on artificial intelligence. The economic risk assessment method based on artificial intelligence can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0027] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0028] Please refer to Figure 1 , Figure 1 A flowchart of an economic risk assessment method based on artificial intelligence provided in an embodiment of the present invention.

[0029] like Figure 1 As shown, the economic risk assessment method based on artificial intelligence includes steps S101 to S105.

[0030] Step S101: Obtain target economic data corresponding to target economic parameters of a target object under multiple data sources.

[0031] For example, it is first necessary to determine a variety of data sources that may cover the target economic parameters. These data sources may include different databases, data warehouses, data services or real-time sensor data.

[0032] For example, data sources such as economic and financial market data, macroeconomic data, and corporate financial data from the past five years are collected. These data sources mainly include target economic parameters such as stock prices, GDP growth rate, and corporate net profit. Data collection is mainly obtained through channels such as government statistical agencies, financial institutions, and corporate internal systems. In addition, target economic parameters may also include income, expenditure, profit margin, market share, etc.

[0033] Step S102: determining model parameters corresponding to the target object according to the target economic data, and determining an economic representation model according to the model parameters.

[0034] Exemplarily, a suitable economic characterization model is selected according to the characteristics of the target economic data and business requirements. The parameters of the economic characterization model are determined using statistical analysis or machine learning methods based on the target economic data. This can be achieved through parameter estimation, hypothesis testing, or feature selection algorithms of machine learning.

[0035] In some embodiments, determining the model parameters corresponding to the target object based on the target economic data includes: determining the expected information corresponding to the target economic parameter based on the maximum and minimum values ​​corresponding to each target economic parameter in the target economic data; performing fuzzy processing on the target economic data to obtain entropy information corresponding to the target economic parameter; determining adjustment parameters, and determining the fuzzy information corresponding to the target economic parameter based on the adjustment parameters and the entropy information; and determining the model parameters corresponding to the target economic parameter based on the expected information, the entropy information, and the fuzzy information.

[0036] For example, the expected information of each target economic parameter in the target economic data can be calculated based on the maximum and minimum values ​​of the parameter. The expected information can usually be calculated by statistical methods, reflecting the distribution range and central tendency of the data.

[0037] Exemplarily, the target economic data is fuzzified to obtain a fuzzy set of each target economic parameter, and the entropy information of the fuzzy set is calculated. Fuzzy processing can use fuzzy set theory, such as the membership function and membership function of fuzzy sets, to describe the uncertainty and fuzziness of economic parameters.

[0038] Exemplarily, adjustment parameters are determined, which are usually used to adjust the shape and range of the fuzzy set to better adapt to the characteristics of the actual data. According to the adjustment parameters and the calculated entropy information, the fuzzy information of the economic parameters, such as the shape of the membership function and the distribution of the fuzzy set, can be determined.

[0039] For example, the expected information, entropy information and fuzzy information are combined with the reasoning method of fuzzy logic to determine the model parameters corresponding to each economic parameter. These model parameters can be used to construct an economic representation model to reflect the fuzzy characteristics and uncertainty of economic parameters, thereby supporting subsequent risk assessment and decision-making processes.

[0040] Specifically, by determining the model parameters of economic parameters based on expected information, entropy information and fuzzy information, the central trend, uncertainty and fuzzy characteristics of the data can be comprehensively considered in the model, thereby providing good support for the subsequent improvement of the economic characterization model to reflect the actual situation, and also providing more reliable support for subsequent risk assessment and decision-making.

[0041] In some embodiments, determining the economic characterization model based on the model parameters includes: determining the objective function that the target economic parameters obey based on the entropy information and the fuzzy information; and determining the economic characterization model based on the objective function and the expected information.

[0042] For example, the objective function that the target economic parameter should obey is determined based on the entropy information and the fuzzy information. The objective function can be a mathematical form that describes the economic parameter under fuzzy and uncertain conditions, which is usually determined by fuzzy logic or information theory techniques, and then the expected information is combined with the objective function to ensure that the model can accurately describe the characteristics and behavior of the target economic parameter, thereby determining the specific form of the economic representation model.

[0043] Specifically, an economic representation model that can effectively reflect the target economic parameters while taking into account data uncertainty and ambiguity is established based on the model parameters. Such a model can not only provide a more accurate data description, but also support subsequent decision analysis and risk assessment.

[0044] Step S103: obtaining sensor data corresponding to the target object under real-time monitoring, and calculating the degree of membership between the sensor data and the economic representation model.

[0045] Exemplarily, the selection of sensors should take into account the characteristics of the monitored object and the monitoring requirements to ensure that the required data type and accuracy can be obtained, and then a real-time data transmission channel can be established to ensure that the data collected by the sensor can be obtained in a timely manner, so as to obtain the sensor data corresponding to the target object.

[0046] Exemplarily, ensure that the sensor data undergoes necessary preprocessing, including data cleaning, denoising and standardization, to ensure data quality and reliability. Use the economic characterization model determined in the previous step. When the economic characterization model is a fuzzy set model, use the membership function to calculate the membership of the sensor data point in the fuzzy set. When the economic characterization model is a distribution model established by statistical methods (such as Gaussian distribution), use a distance metric (such as Euclidean distance or Mahalanobis distance) to measure the similarity or distance between the sensor data point and the model, and then obtain the membership.

[0047] In some embodiments, calculating the degree of membership between the sensor data and the economic characterization model includes: performing a difference calculation between the sensor data and the expected information to obtain first data, and performing a square calculation on the first data to obtain a first square value; obtaining second data corresponding to the sensor data under the objective function, and performing a square calculation on the second data to obtain a second square value; calculating a data ratio between the first square value and the second square value, and then obtaining the degree of membership based on the data ratio.

[0048] Exemplarily, the sensor data and expected information are differenced to obtain first data, and the first data is squared to obtain a first square value; second data corresponding to the sensor data under the objective function is obtained, and the second data is squared to obtain a second square value.

[0049] Exemplarily, a data ratio between the first square value and the second square value is calculated, and then the degree of membership of the sensor data in the economic representation model is determined based on the data ratio combined with fuzzy logic or other methods. Generally, a smaller data ratio indicates that the data is closer to the expected information, and a larger data ratio indicates that the data deviates further from the expected information.

[0050] Specifically, the data ratio is calculated and the membership of the sensor data in the economic representation model is further determined. Such analysis can help evaluate the degree of deviation between actual data and expected values, and thus provide support for subsequent risk assessment.

[0051] Step S104: performing data fusion on the sensor data according to the degree of membership to obtain the credibility corresponding to the sensor data.

[0052] Exemplarily, the membership calculated previously is used as a weight to weight the contribution of different sensor data. Generally, sensor data with a higher membership should have a greater impact on the fusion result, and vice versa, and then a weight is applied to each sensor data point to perform data fusion calculations. For example, methods such as weighted averaging, Kalman filtering, Bayesian estimation, or fuzzy logic are used in combination with membership to fuse data from different sensors. The weight is usually proportional to the membership of the respective data, so that more reliable data will receive a greater weight.

[0053] Exemplarily, the fused data is classified according to credibility, thereby obtaining a credibility probability, and then the credibility corresponding to the sensor data is determined according to the credibility probability.

[0054] In some embodiments, the sensor data is fused according to the membership to obtain the credibility corresponding to the sensor data, including: calculating the distance information between the sensor data according to the membership, and performing an average calculation based on the distance information to obtain the average distance; performing an inverse calculation based on the average distance to obtain support information, and performing normalization processing based on the support information to obtain the credibility.

[0055] For example, a distance metric function is defined, and the distance information between two sensor data is calculated using the membership degree. The distance information can be measured in different ways according to the specific situation, such as Euclidean distance, Manhattan distance, etc. Then, the distances calculated for all sensor data pairs are averaged to obtain the average distance.

[0056] For example, the average distance is used to calculate the support information. The support can be simply defined as the inverse of the average distance, because the smaller the distance, the closer the data points are, and the higher the support (or credibility) should be. The support information is then normalized and its range is limited to between 0 and 1 as the credibility of the sensor data point.

[0057] Specifically, the distance information between sensor data is calculated based on the membership, and then the average distance is calculated based on the distance information, followed by the support information, and finally normalization is performed to obtain the credibility of the sensor data point. Such a method can effectively help evaluate and utilize the reliability information of sensor data.

[0058] Step S105: determining weight information corresponding to the sensor data according to the degree of membership and the credibility, and performing risk assessment according to the weight information and the sensor data to obtain a target assessment result.

[0059] Exemplarily, the weight of each sensor data point is determined based on the given membership and credibility information. The weight reflects the importance or contribution of the data in the integration process. Generally speaking, data points with higher membership and credibility will have higher weight information.

[0060] Exemplarily, the determined weight information is used to filter the sensor data, and the filtered sensor data is applied to the risk assessment model to obtain a target assessment result. The target assessment result can be a risk score, decision advice, or other required output form.

[0061] In some embodiments, determining the weight information corresponding to the sensor data based on the membership and the credibility includes: performing information conversion on the membership to obtain the amount of information corresponding to the sensor data; normalizing the amount of information to obtain the information weight corresponding to the sensor data; and performing information fusion on the credibility and the information weight to obtain the weight information corresponding to the sensor data.

[0062] Exemplarily, the amount of information is calculated based on the degree of membership, and the amount of information is usually used to indicate the amount of information provided by the sensor data. A common calculation method is to use the concept of information entropy, thereby calculating the information entropy based on the degree of membership to obtain the amount of information corresponding to the sensor data.

[0063] Exemplarily, the calculated amount of information is normalized to ensure that it is within an appropriate range (usually [0,1]). A common normalization method is linear transformation, and the normalized amount of information is then regarded as an information weight, which represents the relative contribution of the sensor data to the amount of information.

[0064] Exemplarily, the information weight is weighted averaged and fused with the calculated credibility to obtain weight information corresponding to the sensor data.

[0065] Specifically, the membership degree is converted into information quantity, and then the information quantity is normalized to obtain information weight, and finally the information weight is fused with the credibility to obtain the weight information of the sensor data. This method combines the concepts of information theory and the technology of data fusion, which helps to improve the understanding and utilization of the quality and importance of sensor data.

[0066] In some embodiments, performing risk assessment based on the weight information and the sensor data to obtain a target assessment result includes: determining a weight scale based on a ratio of weight information corresponding to adjacent data between the sensor data; normalizing the weight scale to obtain a target weight, and screening the sensor data based on the target weight to obtain target sensor data; and performing risk assessment on the target sensor data using a risk assessment model to obtain the target assessment result.

[0067] Exemplarily, the weight information ratio between adjacent sensor data is calculated. Assume that there are adjacent data data_i and data_{i+1}, and their corresponding weight information is weight_i and weight_{i+1} respectively. The weight ratio can be calculated as ratio_{i}=weight_{i+1} / weight_i. Then, the weight scale is determined according to the weight information ratio. For example, if ratio_{i} is greater than a certain threshold, it may indicate that the data changes greatly and needs to be adjusted accordingly.

[0068] For example, the weight scale is properly normalized to ensure that its range is in a suitable interval (usually 0 to 1). A linear transformation or other normalization method can be used to obtain the target weight. The target weight is then used to filter the sensor data, and the data with higher weights are selected as the target sensor data. The screening can be based on thresholds or other conditions to ensure the selection of high-quality sensor data.

[0069] Exemplarily, the risk assessment model is used to perform risk assessment on the target sensor data. Appropriate risk assessment methods and models are selected, and the target sensor data is evaluated according to its characteristics to obtain corresponding risk assessment results. Thus, the target assessment results finally obtained are obtained by evaluating the target sensor data according to the risk assessment model. This result can provide an important reference for decision-making, help identify risks and formulate effective measures.

[0070] Specifically, by determining the weight scale based on the weight information ratio corresponding to adjacent data between sensor data, the importance and changes of data can be evaluated more accurately. In this way, data with higher weight scales can be given priority, which may reflect key state changes or events in the system, and help optimize the efficiency of data processing and analysis. The target sensor data is then evaluated using the risk assessment model. Since data screening has been performed and more representative and important sensor data has been selected, the accuracy and reliability of the risk assessment results can be improved. This is especially important for application scenarios that require rapid response and decision-making. By selecting sensor data with higher target weights, unnecessary data processing and storage can be reduced, while ensuring that the data processed by the system is more effective and meaningful.

[0071] The embodiment of the present invention provides an economic risk assessment method and system based on artificial intelligence, which includes obtaining target economic data corresponding to target economic parameters of a target object under multiple data sources, and can obtain more comprehensive and accurate target economic data. This helps to comprehensively consider information from different sources and improve the integrity and credibility of the data. Then, the model parameters are determined based on the target economic data, and an economic characterization model is established, which can more accurately describe the economic characteristics and behavior patterns of the target object, and provide a basis for subsequent data analysis and decision-making. Thus, the sensor data of the target object is obtained under real-time monitoring, and the changes in the state and real-time situation of the target object can be captured in time, providing the latest data support for risk assessment. Then, the membership between the sensor data and the model is calculated using the economic characterization model, which can quantify the matching degree between the data and the model, and improve the understanding and utilization efficiency of the sensor data. Then, the credibility of the sensor data is determined based on the membership, and the weight information is determined based on the membership and credibility, which helps to weight each sensor data according to its contribution, and improve the accuracy and comprehensiveness of the comprehensive assessment results. Finally, risk assessment is performed based on the weight information and sensor data, which can comprehensively consider the information of different data sources, provide decision makers with comprehensive assessment results and accurate risk prediction based on real-time data, and support timely decision-making and action. This method can not only improve the integration, real-time and accuracy of data, thereby enhancing the ability of risk assessment and providing more reliable support for decision-making in complex environments, but also solve the problem in related technologies that high-quality data cannot be accurately screened out during data processing, thereby reducing the accuracy of the assessment results.

[0072] See also Figure 2 , Figure 2An economic risk assessment system 200 based on artificial intelligence is provided for an embodiment of the present application. The economic risk assessment system 200 based on artificial intelligence includes a data acquisition module 201, a model determination module 202, a data processing module 203, a data fusion module 204, and a data evaluation module 205, wherein the data acquisition module 201 is used to obtain target economic data corresponding to target economic parameters of a target object under multiple data sources; the model determination module 202 is used to determine the model parameters corresponding to the target object according to the target economic data, and determine the economic characterization model according to the model parameters; the data processing module 203 is used to obtain sensor data corresponding to the target object under real-time monitoring, and calculate the membership between the sensor data and the economic characterization model; the data fusion module 204 is used to perform data fusion on the sensor data according to the membership to obtain the credibility corresponding to the sensor data; the data evaluation module 205 is used to determine the weight information corresponding to the sensor data according to the membership and the credibility, and perform risk assessment according to the weight information and the sensor data to obtain a target assessment result.

[0073] In some implementations, during the process of determining the model parameters corresponding to the target object according to the target economic data, the model determination module 202 executes:

[0074] According to the maximum value and the minimum value corresponding to each of the target economic parameters in the target economic data, the expected information corresponding to the target economic parameter is determined according to the maximum value and the minimum value;

[0075] Performing fuzzy processing on the target economic data to obtain entropy value information corresponding to the target economic parameter;

[0076] Determine an adjustment parameter, and determine the fuzzy information corresponding to the target economic parameter according to the adjustment parameter and the entropy value information;

[0077] The model parameter corresponding to the target economic parameter is determined according to the expected information, the entropy value information and the fuzzy information.

[0078] In some implementations, in the process of determining the economic representation model according to the model parameters, the model determination module 202 executes:

[0079] Determine the target function that the target economic parameter obeys according to the entropy value information and the fuzzy information;

[0080] The economic representation model is determined according to the objective function and the expected information.

[0081] In some implementations, the data processing module 203 performs, during the process of calculating the degree of membership between the sensor data and the economic representation model:

[0082] Performing a difference calculation on the sensor data and the expected information to obtain first data, and performing a square calculation on the first data to obtain a first square value;

[0083] Obtaining second data corresponding to the sensor data under the objective function, and performing square calculation on the second data to obtain a second square value;

[0084] A data ratio between the first square value and the second square value is calculated, and then the degree of membership is obtained according to the data ratio.

[0085] In some implementations, the data fusion module 204 performs, during the process of fusing the sensor data according to the membership degree to obtain the credibility corresponding to the sensor data:

[0086] Calculating distance information between the sensor data according to the membership degree, and performing average calculation according to the distance information to obtain an average distance;

[0087] The support information is obtained by performing a reciprocal calculation based on the average distance, and the credibility is obtained by performing a normalization process based on the support information.

[0088] In some implementations, the data evaluation module 205, in the process of determining the weight information corresponding to the sensor data according to the membership degree and the credibility, performs:

[0089] Performing information conversion on the degree of membership to obtain the amount of information corresponding to the sensor data;

[0090] Normalizing the amount of information to obtain information weights corresponding to the sensor data;

[0091] The credibility and the information weight are fused to obtain the weight information corresponding to the sensor data.

[0092] In some implementations, the data evaluation module 205, in the process of performing risk evaluation according to the weight information and the sensor data to obtain a target evaluation result, executes:

[0093] Determining a weight scale according to a ratio of weight information corresponding to adjacent data between the sensor data;

[0094] Normalizing the weight scale to obtain a target weight, and filtering the sensor data according to the target weight to obtain target sensor data;

[0095] The risk assessment model is used to perform risk assessment on the target sensor data to obtain the target assessment result.

[0096] In some embodiments, the artificial intelligence-based economic risk assessment system 200 can be applied to a terminal device.

[0097] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the economic risk assessment system 200 based on artificial intelligence described above can refer to the corresponding process in the aforementioned embodiment of the economic risk assessment method based on artificial intelligence, and will not be repeated here.

[0098] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0099] like Figure 3 As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0100] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0101] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0102] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0103] The processor is used to run a computer program stored in a memory, and implement any one of the economic risk assessment methods based on artificial intelligence provided by an embodiment of the present invention when executing the computer program.

[0104] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0105] Obtain target economic data corresponding to target economic parameters of target objects under multiple data sources;

[0106] Determining model parameters corresponding to the target object according to the target economic data, and determining an economic representation model according to the model parameters;

[0107] Obtaining sensor data corresponding to the target object under real-time monitoring, and calculating the degree of membership between the sensor data and the economic representation model;

[0108] Performing data fusion on the sensor data according to the degree of membership to obtain the credibility corresponding to the sensor data;

[0109] The weight information corresponding to the sensor data is determined according to the membership degree and the credibility, and a risk assessment is performed according to the weight information and the sensor data to obtain a target assessment result.

[0110] In some implementations, during the process of determining the model parameters corresponding to the target object according to the target economic data, the processor 301 executes:

[0111] According to the maximum value and the minimum value corresponding to each of the target economic parameters in the target economic data, the expected information corresponding to the target economic parameter is determined according to the maximum value and the minimum value;

[0112] Performing fuzzy processing on the target economic data to obtain entropy value information corresponding to the target economic parameter;

[0113] Determine an adjustment parameter, and determine the fuzzy information corresponding to the target economic parameter according to the adjustment parameter and the entropy value information;

[0114] The model parameter corresponding to the target economic parameter is determined according to the expected information, the entropy value information and the fuzzy information.

[0115] In some implementations, the processor 301, during the process of determining the economic representation model according to the model parameters, executes:

[0116] Determine the target function that the target economic parameter obeys according to the entropy value information and the fuzzy information;

[0117] The economic representation model is determined according to the objective function and the expected information.

[0118] In some implementations, during the process of calculating the degree of membership between the sensor data and the economic representation model, the processor 301 executes:

[0119] Performing a difference calculation on the sensor data and the expected information to obtain first data, and performing a square calculation on the first data to obtain a first square value;

[0120] Obtaining second data corresponding to the sensor data under the objective function, and performing square calculation on the second data to obtain a second square value;

[0121] A data ratio between the first square value and the second square value is calculated, and then the degree of membership is obtained according to the data ratio.

[0122] In some implementations, the processor 301, in the process of performing data fusion on the sensor data according to the degree of membership to obtain the credibility corresponding to the sensor data, executes:

[0123] Calculating distance information between the sensor data according to the membership degree, and performing average calculation according to the distance information to obtain an average distance;

[0124] The support information is obtained by performing a reciprocal calculation based on the average distance, and the credibility is obtained by performing a normalization process based on the support information.

[0125] In some implementations, during the process of determining the weight information corresponding to the sensor data according to the degree of membership and the credibility, the processor 301 executes:

[0126] Performing information conversion on the degree of membership to obtain the amount of information corresponding to the sensor data;

[0127] Normalizing the amount of information to obtain information weights corresponding to the sensor data;

[0128] The credibility and the information weight are fused to obtain the weight information corresponding to the sensor data.

[0129] In some implementations, the processor 301, during the process of performing risk assessment according to the weight information and the sensor data to obtain a target assessment result, executes:

[0130] Determining a weight scale according to a ratio of weight information corresponding to adjacent data between the sensor data;

[0131] Normalizing the weight scale to obtain a target weight, and filtering the sensor data according to the target weight to obtain target sensor data;

[0132] The risk assessment model is used to perform risk assessment on the target sensor data to obtain the target assessment result.

[0133] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned embodiment of the economic risk assessment method based on artificial intelligence, and will not be repeated here.

[0134] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of the economic risk assessment methods based on artificial intelligence provided in the description of the embodiment of the present invention.

[0135] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0136] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0137] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0138] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An economic risk assessment method based on artificial intelligence, characterized in that: The method comprises: Obtain target economic data corresponding to target economic parameters of target objects under multiple data sources; Determining model parameters corresponding to the target object according to the target economic data, and determining an economic representation model according to the model parameters; Obtaining sensor data corresponding to the target object under real-time monitoring, and calculating the degree of membership between the sensor data and the economic representation model; Performing data fusion on the sensor data according to the membership degree to obtain the credibility corresponding to the sensor data; The weight information corresponding to the sensor data is determined according to the membership degree and the credibility, and a risk assessment is performed according to the weight information and the sensor data to obtain a target assessment result.

2. The method according to claim 1, characterized in that The determining the model parameters corresponding to the target object according to the target economic data includes: According to the maximum value and the minimum value corresponding to each of the target economic parameters in the target economic data, the expected information corresponding to the target economic parameter is determined according to the maximum value and the minimum value; Performing fuzzy processing on the target economic data to obtain entropy value information corresponding to the target economic parameter; Determine an adjustment parameter, and determine the fuzzy information corresponding to the target economic parameter according to the adjustment parameter and the entropy value information; The model parameter corresponding to the target economic parameter is determined according to the expected information, the entropy value information and the fuzzy information.

3. The method according to claim 2, characterized in that Determining the economic representation model according to the model parameters includes: Determine the target function that the target economic parameter obeys according to the entropy value information and the fuzzy information; The economic representation model is determined according to the objective function and the expected information.

4. The method according to claim 3, characterized in that The calculating the degree of membership between the sensor data and the economic representation model comprises: Performing a difference calculation on the sensor data and the expected information to obtain first data, and performing a square calculation on the first data to obtain a first square value; Obtaining second data corresponding to the sensor data under the objective function, and performing square calculation on the second data to obtain a second square value; A data ratio between the first square value and the second square value is calculated, and then the degree of membership is obtained according to the data ratio.

5. The method according to claim 1, characterized in that The performing data fusion on the sensor data according to the membership degree to obtain the credibility corresponding to the sensor data includes: Calculating distance information between the sensor data according to the membership degree, and performing average calculation according to the distance information to obtain an average distance; The support information is obtained by performing a reciprocal calculation based on the average distance, and the credibility is obtained by performing a normalization process based on the support information.

6. The method according to claim 1, characterized in that The determining weight information corresponding to the sensor data according to the membership degree and the credibility includes: Performing information conversion on the degree of membership to obtain the amount of information corresponding to the sensor data; Normalizing the amount of information to obtain information weights corresponding to the sensor data; The credibility and the information weight are fused to obtain the weight information corresponding to the sensor data.

7. The method according to claim 1, characterized in that The step of performing risk assessment according to the weight information and the sensor data to obtain a target assessment result includes: Determining a weight scale according to a ratio of weight information corresponding to adjacent data between the sensor data; Normalizing the weight scale to obtain a target weight, and filtering the sensor data according to the target weight to obtain target sensor data; The risk assessment model is used to perform risk assessment on the target sensor data to obtain the target assessment result.

8. An economic risk assessment system based on artificial intelligence, characterized in that: include: A data collection module is used to obtain target economic data corresponding to target economic parameters of target objects under multiple data sources; A model determination module, used to determine the model parameters corresponding to the target object according to the target economic data, and determine the economic representation model according to the model parameters; A data processing module, used to obtain sensor data corresponding to the target object under real-time monitoring, and calculate the degree of membership between the sensor data and the economic representation model; A data fusion module, used for performing data fusion on the sensor data according to the membership degree to obtain the credibility corresponding to the sensor data; The data evaluation module is used to determine the weight information corresponding to the sensor data according to the membership degree and the credibility, and perform risk evaluation according to the weight information and the sensor data to obtain a target evaluation result.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the artificial intelligence-based economic risk assessment method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the economic risk assessment method based on artificial intelligence as described in any one of claims 1 to 7.