Early warning method and related device

Abstract

The invention provides an early warning method and a related device, and relates to the field of early warning. According to the invention, early warning operation is realized based on mutual cooperation of the basic data layer, the decision analysis layer and the decision display layer. Specifically, the decision analysis layer carries out statistical analysis and early warning analysis operation on basic information collected by the basic data layer from three dimensions of an equipment early warning dimension, a mechanism early warning dimension and a personnel early warning dimension to obtain an early warning result, and then calls the decision display layer to carry out early warning operation on the early warning result in a preset early warning mode. According to the embodiment of the invention, artificial participation is not needed, so that the influence of artificial subjective factors is avoided, and the early warning accuracy is improved. In addition, early warning analysis is carried out from the three dimensions of the equipment early warning dimension, the mechanism early warning dimension and the personnel early warning dimension, and the comprehensiveness and reliability of early warning can be improved.

Description

Technical Field

[0001] The present invention relates to the field of early warning, and more specifically, to an early warning method and related devices. Background Art

[0002] With the rapid development of emerging technologies such as big data, cloud technology, and blockchain, the development environment of the financial industry has undergone tremendous changes, and the operational security and reliability of banks have received increasing attention.

[0003] At present, in order to improve the safety and reliability of bank operations, early warning analysis operations are carried out. When conducting early warning analysis, a manual early warning analysis method based on experience is adopted. This early warning method is easily affected by human subjective factors and has low accuracy. Summary of the invention

[0004] In view of this, the present invention provides an early warning method and related devices to solve the problem of low early warning accuracy.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] An early warning method is applied to a decision analysis layer in an early warning system, wherein the early warning system further comprises a basic data layer and a decision display layer; the basic data layer collects basic information through a device upload method and a data platform interface upload method; the decision analysis layer is implemented through a cloud Mysql server and a system cloud server, and is used to perform statistical analysis on the basic information to obtain an early warning result; the decision display layer comprises early warning devices of institutions at all levels, and is used to perform an early warning operation on the early warning result using a preset early warning method;

[0007] The early warning method comprises:

[0008] Acquire early warning statistical dimensions, wherein the early warning statistical dimensions include a device early warning dimension, an organization early warning dimension, and a personnel early warning dimension; the device early warning dimension and the organization early warning dimension each include a plurality of sub-dimensions;

[0009] Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension;

[0010] Performing warning analysis on the dimension values ​​corresponding to each warning statistical dimension to obtain a warning result;

[0011] The decision display layer is called to perform a warning operation on the warning result using a preset warning method.

[0012] Optionally, the device warning dimension includes a device operation status sub-dimension, a business transaction sub-dimension, a device type sub-dimension, and a device quantity sub-dimension;

[0013] Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension, including:

[0014] For the device operation status sub-dimension, obtain a first dimension value calculation formula corresponding to the device operation status sub-dimension;

[0015] The first dimension value calculation formula includes:

[0016]

[0017] Among them, S x is the dimension value corresponding to the device operation status sub-dimension, n x is the equipment life, α is the depreciation coefficient, m x is the number of equipment failure records obtained based on historical work order information statistics, β is the failure coefficient, and E x is the total number of all historical businesses handled by the device, and γ is the business wear coefficient;

[0018] Filter out first target data associated with the device operation status sub-dimension from the basic information collected by the basic data layer;

[0019] The first dimension value calculation formula is used to perform a calculation operation on the first target data to obtain a dimension value corresponding to the device operation status sub-dimension.

[0020] Optionally, a warning analysis is performed on the dimension values ​​corresponding to each warning statistical dimension to obtain a warning result, including:

[0021] Obtaining an early warning analysis rule, wherein the early warning analysis rule includes a correspondence between a dimension value of the device operation status sub-dimension, a dimension value of the business transaction sub-dimension, a dimension value of the device type sub-dimension, a dimension value of the device quantity sub-dimension, and an early warning result;

[0022] Based on the dimension value of the device operation status sub-dimension, the dimension value of the business transaction sub-dimension, the dimension value of the device type sub-dimension, and the dimension value of the device quantity sub-dimension, the early warning analysis rules are queried to obtain early warning results.

[0023] Optionally, the institutional warning dimension includes: an institutional risk level sub-dimension, an average warning clue quantum dimension of outlets, an average problem quantum dimension of outlets, and an average problem quantum dimension per capita of outlets;

[0024] Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension, including:

[0025] For the institutional risk level sub-dimension, obtaining a calculation formula for a second dimension value corresponding to the institutional risk level sub-dimension;

[0026] The second dimension value calculation formula includes:

[0027]

[0028] Among them, R x1 is the dimension value of the sub-dimension of the institution's risk level, n x1 is the total number of institutional issues, α i1 is the risk point weight corresponding to the i-th problem, m x1 is the total number of institutional interception risk events, β1 is the risk point weight corresponding to the jth institutional interception risk event, v x1 is the total number of institutional warning and clue missed detection problems, γ1 is the risk point weight corresponding to the kth institutional warning and clue missed detection problem;

[0029] Filter out second target data having a correlation relationship with the institutional risk level sub-dimension from the basic information collected by the basic data layer;

[0030] The second dimension value calculation formula is used to perform calculation operations on the second target data to obtain the dimension value corresponding to the institutional risk level sub-dimension.

[0031] Optionally, a warning analysis is performed on the dimension values ​​corresponding to each warning statistical dimension to obtain a warning result, including:

[0032] For each sub-dimension in the institutional warning dimension, all institutions are sorted according to the sub-dimension value to obtain a sorting result;

[0033] Filter out the institutions whose ranking values ​​are within a preset range in the ranking results;

[0034] The screened institutions will be used as warning institutions in the warning results.

[0035] Optionally, based on the early warning statistical dimension, a statistical analysis operation is performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension, including:

[0036] For the personnel warning dimension, obtain a calculation formula for a third dimension value corresponding to the personnel warning dimension;

[0037] The third dimension value calculation formula includes:

[0038]

[0039] Among them, R x2is the dimension value of the personnel warning dimension, n x2 is the total number of personnel issues, α i2 is the risk point weight corresponding to the oth problem, m x2 is the total number of personnel interception risk events, β2 is the risk point weight corresponding to the pth personnel interception risk event, v x2 is the total number of personnel warning and clue missed detection problems, γ2 is the risk point weight corresponding to the qth personnel warning and clue missed detection problem;

[0040] Filter out third target data associated with the personnel warning dimension from the basic information collected in the basic data layer;

[0041] The third dimension value calculation formula is used to perform calculation operations on the third target data to obtain the dimension value corresponding to the personnel warning dimension.

[0042] Optionally, calling the decision presentation layer to perform a warning operation on the warning result using a preset warning method includes:

[0043] The decision display layer is controlled to display the warning results in the form of data lists or charts, and output the warning results to the terminal devices of preset personnel.

[0044] An early warning device is applied to a decision analysis layer in an early warning system, wherein the early warning system further comprises a basic data layer and a decision display layer; the basic data layer collects basic information through a device upload method and a data platform interface upload method; the decision analysis layer is implemented through a cloud Mysql server and a system cloud server, and is used to perform statistical analysis on the basic information to obtain an early warning result; the decision display layer comprises early warning devices of institutions at all levels, and is used to perform an early warning operation on the early warning result using a preset early warning method;

[0045] The early warning device comprises:

[0046] A dimension acquisition module, used to acquire early warning statistical dimensions, wherein the early warning statistical dimensions include equipment early warning dimensions, organization early warning dimensions, and personnel early warning dimensions; the equipment early warning dimensions and the organization early warning dimensions each include a plurality of sub-dimensions;

[0047] A statistical analysis module, used to perform statistical analysis operations on the basic information collected by the basic data layer based on the early warning statistical dimensions, and obtain dimension values ​​corresponding to each early warning statistical dimension;

[0048] An early warning analysis module is used to perform early warning analysis on the dimension values ​​corresponding to each early warning statistical dimension to obtain an early warning result;

[0049] The early warning display module is used to call the decision display layer and perform an early warning operation on the early warning result using a preset early warning method.

[0050] An electronic device comprises at least one processor and a memory connected to the processor, wherein:

[0051] The memory is used to store computer programs;

[0052] The processor is used to execute the computer program so that the electronic device can implement the above-mentioned early warning method.

[0053] A computer storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the above-mentioned early warning method.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention provides an early warning method and related devices. In the present invention, the early warning operation is realized based on the mutual cooperation of the basic data layer, the decision analysis layer and the decision display layer. Specifically, the decision analysis layer performs statistical analysis and early warning analysis operations on the basic information collected by the basic data layer from three dimensions: the equipment early warning dimension, the organization early warning dimension and the personnel early warning dimension, obtains the early warning result, and then calls the decision display layer to perform an early warning operation on the early warning result using a preset early warning method. Since the embodiment of the present invention does not require human participation, it avoids the influence of human subjective factors and improves the accuracy of the early warning. In addition, the present invention performs early warning analysis from three dimensions: the equipment early warning dimension, the organization early warning dimension and the personnel early warning dimension, which can improve the comprehensiveness and reliability of the early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0057] Figure 1 A flowchart of an early warning method provided by an embodiment of the present invention;

[0058] Figure 2 A flowchart of a method for determining a dimension value provided by an embodiment of the present invention;

[0059] Figure 3 A flowchart of another method for determining a dimension value provided by an embodiment of the present invention;

[0060] Figure 4 A schematic diagram of the structure of an early warning device provided by an embodiment of the present invention;

[0061] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] 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 only 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.

[0063] With the rapid development of emerging technologies such as big data, cloud technology, and blockchain, the development environment of the financial industry has undergone tremendous changes, forcing financial institutions to quickly adapt to the new situation of digital development. In the process of digital development, the operational security and reliability of banks have received increasing attention.

[0064] At present, in order to improve the security and reliability of bank operations, early warning analysis operations are carried out. When conducting early warning analysis, the early warning analysis method is used manually based on experience, such as manual report statistics and risk early warning notification operations. This early warning method is easily affected by human subjective factors and statistical omissions, and the early warning accuracy is low. In addition, there is a risk of time-consuming and labor-intensive work and sensitive data leakage.

[0065] Therefore, in order to change the current manual management-based operation management mode and risk monitoring and early warning mode, an intelligent early warning method is adopted, which can conduct early warning analysis from three dimensions: equipment early warning dimension, organization early warning dimension and personnel early warning dimension, and improve the comprehensiveness, reliability and accuracy of early warning. Since the whole process does not require human participation, it can save manpower and avoid the risk of manual leakage of sensitive data.

[0066] In addition, in the prior art, multiple systems in banks, such as personnel risk management systems, branch equipment management systems (which are divided into head office systems, branch systems, etc. according to levels), etc., have scattered and independent system data, lacking unified operational resources and system integration platforms and decision-making support platforms. To this end, the present invention, in order to improve the ability and level of using emerging technologies, constructs a bank's intelligent operation system and a digital integrated service platform. The platform is based on the existing standardized integrated management system, incorporates the bank's institutional, personnel and equipment information, uses hierarchical management and authority control as means, and takes "machine-based, manual as auxiliary, human-machine complementarity, multi-point integration" as the principle to create a unified operational resource and system integration platform, a decision-making support digital integrated platform, improves the efficiency of operational management, reduces the burden on bank grassroots personnel, reduces operating costs, and solves the problem of multiple systems lacking unified operational resources and system integration platforms and decision-making support platforms.

[0067] The early warning system in the embodiment of the present invention is implemented through the above-mentioned bank intelligent operation system and digital comprehensive service platform. From the hardware level, the early warning system can include a basic data layer, a decision analysis layer, and a decision display layer.

[0068] The basic data layer consists of the branch PC (Personal Computer) terminal, scanner, and head office data platform interface, through which data is collected. The branch PC terminal is any computer device in the branch that can be connected to the cloud server through the intranet, which is used for report filling and data uploading. The head office data platform interface includes basic data interfaces such as banking institutions, personnel, and operation data, which are used to synchronize the head office basic data.

[0069] When using branch PCs and scanners to collect data, the basic information is collected by the above-mentioned method of the equipment. When using the head office data platform interface to collect data, the basic information is collected by uploading the data platform interface.

[0070] The decision analysis layer is composed of a cloud Mysql server and a system cloud server (such as a cloud Suse server), and is used to perform statistical analysis on the basic information to obtain early warning results.

[0071] The cloud MySQL server is a database server cluster deployed on the bank's intranet cloud server, which is used to deploy the MySQL distributed database used by the platform. The system cloud server is a server cluster that deploys the core system of the intelligent operation system and the digital comprehensive service platform on the bank's cloud for decision analysis.

[0072] The decision display layer is composed of early warning equipment (such as PC workstations) at all levels of institutions. The PC workstations at all levels of institutions are computer devices connected to the intranet of operating institutions at all levels. They are used to perform early warning operations on the early warning results using preset early warning methods, such as displaying decision information data lists or charts.

[0073] When the early warning system is in operation, data from different devices at grassroots outlets or the head office are collected into a cloud database to form a data warehouse covering all operational data of banking institutions. The platform system deployed on the cloud server then conducts statistical analysis for decision-making, providing risk monitoring, early warning and decision-making support for bank operations management.

[0074] In this embodiment, a three-layer architecture of basic data layer, decision analysis layer, and decision display layer is adopted to realize a unified operation resource and system integration platform and decision support platform. By using intelligent technology and means, the original manually processed business is transformed into machine autonomous processing or manual assisted processing, which improves the operation management efficiency and branch operation efficiency, provides integrated report display and operation decision support, changes the current operation management mode and risk monitoring and early warning mode dominated by manual management, creates a unified operation resource and system integration and decision support digital integrated platform, improves the efficiency of operation management, reduces the burden on grassroots bank personnel, and reduces operating costs.

[0075] In another implementation of the present invention, the early warning system may include, from the software implementation level:

[0076] System management module, network point information collection module, statistical analysis module, decision-making suggestion and graphical display module.

[0077] Specifically, the system management module includes system authority management, basic data management, message reminders and early warning management. Authority management means that users can customize roles and assign module authority, and users with relevant authority can assign roles. Basic data management means obtaining basic information of all bank institutions (management institutions, outlets, etc.) and personnel through the bank's data distribution platform. Message reminders and early warnings mean that the system has early warning and reminder functions for outlets, such as warnings that some equipment needs to be scrapped or replaced, and some outlets have greater risks. At the same time, users can also customize message reminders.

[0078] The branch information collection module includes comprehensive branch information collected through various methods. Multiple methods of collection refer to filling in reports and uploading files through the PC terminal of the intranet branch, scanning and scanning files through the scanner, and obtaining relevant data through the bank-wide data platform interface and the bank-wide data distribution platform at the basic data layer. Comprehensive branch information refers to the branch's operations, risks, equipment and other related information. Among them, risk information includes a list of intercepted external fraud incidents, branch personnel intercepting counter risk incidents, problem database registration issues, and risk data screening clues. Equipment information includes basic equipment information, equipment historical work order information, fixed asset card information, equipment whitelist, scrapping history information, and equipment ATM (Automatic Teller Machine) business portrait report.

[0079] The statistical analysis module includes a rule management module and a decision inference engine module. The rule management module refers to the management of equipment loss parameter formulas, equipment evaluation rules, branch personnel and institutional risk level rules and other decision rules and formula-related parameters. The decision inference engine uses the relevant data collected by the branch information collection module to infer and judge according to the decision formula and rules, and obtain equipment evaluation and branch risk recommendations.

[0080] The decision-making suggestion and graphical display module includes tabular display and graphical display. Tabular display and graphical display refer to the system visually displaying the analysis results of the statistical analysis module in the form of data lists or charts such as pie charts.

[0081] Based on the above hardware and software architecture, the administrative staff log in to the system to formulate decision-making analysis parameters and rules, and the branch staff log in to the system and fill in the report. The system stores the report data in the cloud database. The statistical analysis module analyzes the report data together with the data obtained through the head office data platform. According to the parameters and rules preset by the administrator, the equipment evaluation results and risk warning conditions are automatically calculated and inferred. In response to the risk monitoring results, the system sends SMS or email reminders to the relevant branch staff in batches at regular intervals.

[0082] During the entire process, branch employees or agency managers enter the system and can view report information, warning conditions, and operational decision information within the scope of the current personnel's organization based on different permissions.

[0083] Based on the above content, an embodiment of the present invention provides an early warning method, which is applied to the decision analysis layer in the early warning system. Figure 1 , the early warning method may include:

[0084] S11. Obtain early warning statistical dimensions.

[0085] Among them, the warning statistical dimensions include equipment warning dimension, organization warning dimension and personnel warning dimension.

[0086] The equipment warning dimension is a warning analysis from the perspective of equipment, the institution warning dimension is a warning analysis from the perspective of institution, and the institution in this embodiment may refer to a bank branch. The personnel warning dimension is a warning analysis from the perspective of personnel, and the personnel in this embodiment refers to personnel in the institution.

[0087] In practical applications, in order to improve the comprehensiveness of early warning, the equipment early warning dimension and the mechanism early warning dimension respectively include multiple sub-dimensions.

[0088] As described, the device early warning dimension includes the device operation status sub-dimension, the business transaction volume sub-dimension, the device type sub-dimension and the device quantity sub-dimension, and early warning analysis is performed from the aspects of operation status, transaction volume, device type and quantity.

[0089] The institutional early warning dimensions include: institutional risk level sub-dimension, branch average early warning clue quantum dimension, branch average problem quantum dimension and branch average problem quantum dimension, which respectively conduct early warning analysis operations from the perspectives of risk, early warning clue quantity, average problem quantity and average problem quantity.

[0090] It should be noted that the dimensions and sub-dimensions in this embodiment are manually configured, and can be added, deleted, or modified according to actual conditions to match them.

[0091] S12. Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension.

[0092] In actual applications, the above-mentioned basic data layer is used to collect basic information through device upload and data platform interface upload. The basic information includes information on the entire bank's organization (management agencies, outlets, etc.), personnel, equipment, etc. The specific information collected can be configured according to actual conditions.

[0093] For the above-mentioned equipment warning dimension, organization warning dimension and personnel warning dimension, when performing statistical analysis operations, the data related to the dimension itself will be extracted from the basic information, and then the statistical analysis operation will be performed according to the rules and formulas corresponding to the dimension to obtain the dimension value of the corresponding dimension.

[0094] The above three dimensions can be performed in parallel or sequentially when conducting statistical analysis, depending on the amount of resources in the actual scenario. If the amount of resources is sufficient, parallel statistics can be used; if the amount of resources is small, serial statistics can be used.

[0095] S13. Perform warning analysis on the dimension values ​​corresponding to each warning statistical dimension to obtain a warning result.

[0096] After obtaining the dimension values ​​of each dimension, it is necessary to determine whether these dimension values ​​meet the warning conditions. This can be achieved through warning analysis operations to obtain the corresponding warning results. Warning results can be divided into two categories: warning and no warning. Warnings can be divided into warnings of different severity according to actual conditions.

[0097] S14: calling the decision display layer to perform a warning operation on the warning result using a preset warning method.

[0098] In actual application, only the warning results that need warning can be used for warning operation. When the warning operation is carried out, the warning results can be displayed to the warning devices of various levels of institutions, such as PC workstations, in the form of data lists or pie charts.

[0099] In this embodiment, the early warning operation is realized based on the mutual cooperation of the basic data layer, the decision analysis layer and the decision display layer. Specifically, the decision analysis layer performs statistical analysis and early warning analysis operations on the basic information collected by the basic data layer from three dimensions: the equipment early warning dimension, the organization early warning dimension and the personnel early warning dimension, obtains the early warning result, and then calls the decision display layer to perform an early warning operation on the early warning result using a preset early warning method. Since the embodiment of the present invention does not require human participation, it avoids the influence of human subjective factors and improves the accuracy of the early warning. In addition, the present invention performs early warning analysis from three dimensions: the equipment early warning dimension, the organization early warning dimension and the personnel early warning dimension, which can improve the comprehensiveness and reliability of the early warning.

[0100] The above embodiment mentions three dimensions: equipment warning dimension, organization warning dimension, and personnel warning dimension. In this embodiment, for each dimension, the corresponding statistical analysis process and warning analysis process are introduced respectively.

[0101] 1. Equipment warning dimension.

[0102] In actual applications, the device warning dimension includes the device operation status sub-dimension, the business transaction sub-dimension, the device type sub-dimension and the device quantity sub-dimension.

[0103] In actual applications, for each device, it is necessary to perform calculation operations on the device warning dimension, that is, to calculate the dimensional values ​​of the device operation status sub-dimension, business transaction sub-dimension, device type sub-dimension and device quantity sub-dimension respectively.

[0104] When calculating the dimension value, for a device, relevant information of the device can be retrieved from the database. The device related information includes basic device information, historical work order information of the device, fixed asset card information, device whitelist, scrap history information, device ATM business portrait report, etc.

[0105] Then, the rules and formulas are taken out from the rule base to calculate the matching. The report data is combined with the data obtained through the head office data platform for comprehensive statistical analysis using the rules and formulas, and the equipment evaluation results (maintaining the status quo, offline scrapping, scrapping and replacing, and relocation) are calculated and inferred based on the administrator's preset parameters.

[0106] The equipment evaluation results are stored and warned. If the equipment evaluation result is offline scrapping, scrap replacement, or transfer, the system will automatically send an email or SMS reminder to the equipment-related personnel.

[0107] If the calculation operation has been performed on all devices, the process ends.

[0108] The process of determining the dimension value of each sub-dimension is now introduced.

[0109] 1.1. Equipment operation status sub-dimension.

[0110] Reference Figure 2 Based on the early warning statistical dimension, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension, which may include:

[0111] S21. Obtain a calculation formula for a first dimension value corresponding to the device operation status sub-dimension.

[0112] The device operation status sub-dimension is an evaluation of the device from the perspective of the device status. For device x, the calculation formula for the first dimension value includes:

[0113]

[0114] Among them, S x is the dimension value corresponding to the device operation status sub-dimension, n x is the equipment life, α is the depreciation coefficient, m x is the number of equipment failure records obtained based on historical work order information statistics, β is the failure coefficient, and E x is the total number of all historical businesses handled by the device, and γ is the business wear coefficient, which is the fraction that decreases for every 1,000 businesses handled.

[0115] S22: Filter out first target data associated with the device operation status sub-dimension from the basic information collected by the basic data layer.

[0116] Specifically, from the basic information collected above, such as the basic information of the equipment, the historical work order information of the equipment, the fixed asset card information, the equipment whitelist, the scrap history information, the equipment ATM business portrait report, etc., the parameter values ​​of each parameter in the calculation formula of the first dimension value are screened out, that is, n is determined. x 、m x 、Ex Parameter values ​​of other parameters.

[0117] S23. Use the first dimension value calculation formula to perform a calculation operation on the first target data to obtain a dimension value corresponding to the device operation status sub-dimension.

[0118] Specifically, the parameter value collected in step S22 is substituted into the first dimension value calculation formula to calculate the dimension value corresponding to the device operation status sub-dimension.

[0119] After obtaining the dimension value S corresponding to the equipment operation status sub-dimension, if S>80 is considered good (parameter status good standard), S≥60&&S<80 is considered qualified (parameter status qualified standard), and S<60 is considered unqualified (parameter status unqualified standard).

[0120] 1.2. Business Transaction Quantum Dimension

[0121] The business transaction quantum dimension can also be called a contribution index. It is a statistic of the business transaction volume performed by the device. The business transaction volume is divided into two categories. The statistical methods of business transaction volume are different for different types of devices. In actual scenarios, the device types are divided into two categories: cash devices and super counters.

[0122] For cash devices, the business transaction quantum dimension counts the average daily number of financial transactions in the bank and the average daily number of financial transactions in off-bank cash devices since the beginning of this year.

[0123] If the average daily financial transactions in the bank this year are 150 or more, it is excellent; 120 or more, it is good; 80 or more, it meets the standard; and less than 80, it does not meet the standard; if the average daily financial transactions of off-bank cash devices are 60 or more, it meets the standard; and less than 60, it does not meet the standard.

[0124] For super counters, the business transaction quantum dimension counts the average daily transaction volume of the counter and the number of cash transactions at the cash counter.

[0125] If the daily average transaction volume is 150 or more, it is up to standard; if it is 100 or more, it is good; if it is 70 or more, it is up to standard; if it is less than 67, it is not up to standard. For cash transactions, 10 or more cash transactions are up to standard; if it is less than 10 transactions, it is not up to standard.

[0126] 1.3. Device Type Sub-Dimension

[0127] The device type sub-dimension can be divided into whitelist devices, non-whitelist devices, devices within the network point type configuration, etc., which can be determined based on actual configuration.

[0128] 1.4. Device Quantity Sub-Dimension

[0129] The sub-dimension of equipment quantity is divided into network type configuration exceeding the standard, etc.

[0130] Exceeding the configuration limit for a network point type means that the number of devices configured at the same network point exceeds the limit. Generally, three core devices, two backbone devices, and one light device are configured. If the number exceeds this, it is considered to be exceeded.

[0131] After obtaining the equipment operation status sub-dimension, business transaction sub-dimension, equipment type sub-dimension and equipment quantity sub-dimension through statistics, a warning analysis can be performed on the dimension values ​​corresponding to each warning statistical dimension to obtain a warning result.

[0132] To elaborate, early warning analysis rules can be obtained, and the early warning analysis rules include the dimension value of the device operation status sub-dimension, the dimension value of the business transaction sub-dimension, the dimension value of the device type sub-dimension, the dimension value of the device quantity sub-dimension and the correspondence between the early warning results.

[0133] Specifically, the content of the early warning analysis rules can be as follows:

[0134] If the equipment operation status sub-dimension is good and the business transaction sub-dimension is above the standard, the warning result is: maintain the status quo;

[0135] If the device operation status sub-dimension is good, the business transaction sub-dimension is not up to standard, and the device type sub-dimension is a whitelist device, the warning result is: maintain the status quo;

[0136] If the device operation status sub-dimension is not up to standard, the device type sub-dimension is not a whitelist device, and the device quantity sub-dimension is that the network type configuration exceeds the standard, the warning result is: offline and scrapped;

[0137] If the device operation status sub-dimension is not up to standard, and the device type sub-dimension is a whitelist device or a device in the network type configuration, the warning result is: scrap and replace;

[0138] If the device operation status sub-dimension is good, the business transaction quantity sub-dimension is substandard, the device type sub-dimension is non-whitelisted equipment, and the device quantity sub-dimension is that the branch type configuration exceeds the standard, the warning result is: relocation.

[0139] After obtaining the early warning analysis rules, the early warning analysis rules can be queried based on the dimension values ​​of the device operation status sub-dimension, the dimension values ​​of the business transaction sub-dimension, the dimension values ​​of the device type sub-dimension, and the dimension values ​​of the device quantity sub-dimension to obtain the early warning results. The early warning results will automatically send emails or SMS reminders to the relevant personnel of the equipment.

[0140] 2. Institutional warning dimension

[0141] In actual applications, the institutional early warning dimensions include: institutional risk level sub-dimension, average warning clue quantum dimension of outlets, average problem quantum dimension of outlets, and average problem quantum dimension per capita of outlets.

[0142] When calculating the institutional warning dimension, each branch needs to calculate the institutional warning dimension. The specific process is as follows:

[0143] The risk-related information of a branch (identified by ID (Identity document, account number)) is retrieved from the database. The risk-related information includes a list of intercepted external fraud incidents, branch personnel intercepted counter risk incidents, problems registered in the problem database, and risk data screening clues.

[0144] Take out rules and formulas from the rule base to calculate matches. Use rules and formulas to conduct comprehensive statistical analysis on report data and data obtained through the head office data platform, and calculate and deduce the risk level of personnel and institutions based on the parameters preset by the administrator.

[0145] The risk level results of branch personnel and institutions are stored and warned. If the risk level of personnel and institutions is in the top 10%, the system automatically sends emails or text messages to relevant managers.

[0146] Now we will introduce the calculation process of the institutional risk level sub-dimension, the average warning clue quantum dimension of outlets, the average problem quantum dimension of outlets, and the average problem quantum dimension per capita of outlets.

[0147] 2.1. Institutional risk level sub-dimension

[0148] Reference Figure 3 Based on the early warning statistical dimension, a statistical analysis operation is performed on the basic information collected by the basic data layer to obtain the dimension value corresponding to each early warning statistical dimension, including:

[0149] S31. Obtain a calculation formula for the second dimension value corresponding to the institutional risk level sub-dimension.

[0150] The second dimension value calculation formula includes:

[0151]

[0152] Among them, for institution X1, R x1 is the dimension value of the sub-dimension of the institution's risk level, n x1 is the total number of institutional issues of the institution, α i1 is the risk point weight corresponding to the i-th question (different questions have different weights, which are stored in the question library), m x1 is the total number of institutional interception risk events, β1 is the risk point weight corresponding to the jth institutional interception risk event (initialized to 1), vx1 is the total number of institutional warnings and clues missed detection problems, γ1 is the risk point weight corresponding to the kth institutional warning and clues missed detection problem, and is initialized to 3.

[0153] S32. Filter out second target data that is associated with the institutional risk level sub-dimension from the basic information collected from the basic data layer.

[0154] S33. Use the second dimension value calculation formula to perform calculation operations on the second target data to obtain the dimension value corresponding to the institutional risk level sub-dimension.

[0155] Specifically, similar to the above-mentioned equipment operation status sub-dimension, the second target data is obtained from basic information such as the list of intercepted external fraud events, counter risk events intercepted by branch personnel, problems registered in the problem database, and risk data screening clues, such as n x1 、m x1 Substituting it into the second dimension value calculation formula, we can get the dimension value corresponding to the institutional risk level sub-dimension.

[0156] 2.2. The average warning clue quantum dimension of outlets, the average problem quantum dimension of outlets, and the average problem quantum dimension per capita of outlets

[0157] Based on the bank's early warning and risk data screening clues and problem database registration, statistics are collected on the total amount, average number of points, and average number of people in each level of institutions' early warning clues and problem databases, providing data support for monitoring, analysis, and assessment management for managers at all levels. The statistical formulas for the average early warning clue quantum dimension of outlets, the average problem quantum dimension of outlets, and the average problem quantum dimension of outlets are as follows:

[0158]

[0159] For the average warning clue quantum dimension of the network point, f x is the dimension value of the average warning clue quantum dimension of the network point, S x is the total amount of early warning clues of the institution (including subordinate institutions, such as second-level branches, first-level sub-branches and business outlets), and N represents the number of business outlets of the institution and its subordinate institutions. That is, the average warning clue quantum dimension of outlets (second-level branches, first-level sub-branches and business outlets) = total amount of early warning clues / number of business outlets (second-level branches, first-level sub-branches and business outlets).

[0160] For the quantum dimension of the point average problem, where f x is the dimension value of the quantum dimension of the average problem of the network point, S x= is the total number of problems of the institution (including subordinate institutions), and N represents the number of business institutions of the institution and its subordinate institutions. That is, the average problem quantum dimension of outlets (second-level branches, first-level sub-branches and business outlets) = total number of problems / number of business institutions (second-level branches, first-level sub-branches and business outlets)

[0161] For the quantum dimension of the network point per capita problem, f x is the dimension value of the quantum dimension of the average problem per outlet, S x is the total number of problems of the institution (including subordinate institutions), and N represents the number of business outlets of the institution and its subordinate institutions (positions include back-office president, counter manager, and lobby manager). That is, the quantum dimension of problems per capita in outlets (second-level branches, first-level sub-branches, and business outlets) = total number of problems / number of second-level branches, first-level sub-branches, and business outlets (including positions include back-office president, counter manager, and lobby manager)

[0162] In actual application, users can select different institutional levels and time periods to view the dimension values ​​of the institutional risk level sub-dimension, the average warning clue quantum dimension of the outlets, the average problem quantum dimension of the outlets, and the per capita problem quantum dimension of the outlets within the scope of the current user's authority. Then, the dimension values ​​corresponding to each warning statistical dimension are analyzed for warning to obtain warning results. Specifically, for each sub-dimension in the institutional warning dimension, all institutions are sorted according to the sub-dimension value to obtain the sorting result, that is, the institutions are sorted according to the dimension values ​​of the institutional risk level sub-dimension, the average warning clue quantum dimension of the outlets, the average problem quantum dimension of the outlets, and the per capita problem quantum dimension of the outlets, and four sorting results can be obtained. In the sorting results, the dimension values ​​are sorted from large to small. The larger the dimension value, the more serious the problem.

[0163] For each ranking result, the institutions whose ranking values ​​are within a preset interval in the ranking result are screened out. In this embodiment, the preset interval may be the first 10%, that is, the 10% institutions with the most serious severity are screened out and used as the warning institutions in the warning results.

[0164] It should be noted that the early warning results include the institutional risk level sub-dimension, the average warning clue quantum dimension of outlets, the average problem quantum dimension of outlets and the average problem quantum dimension per capita of outlets. The corresponding early warning agencies are, for example, the early warning agency corresponding to the institutional risk level sub-dimension is XXX..., the early warning agency corresponding to the average warning clue quantum dimension of outlets is YYY..., the early warning agency corresponding to the average problem quantum dimension of outlets is WWW..., and the early warning agency corresponding to the average problem quantum dimension per capita of outlets is VVV...

[0165] 3. Personnel warning dimension

[0166] The implementation logic of the personnel warning dimension is similar to that of the institutional risk level sub-dimension. Specifically, based on the warning statistical dimension, the basic information collected by the basic data layer is statistically analyzed to obtain the dimension values ​​corresponding to each warning statistical dimension, including:

[0167] 1) For the personnel warning dimension, obtain a calculation formula for the third dimension value corresponding to the personnel warning dimension;

[0168] The third dimension value calculation formula includes:

[0169]

[0170] Among them, for person X2, R x2 is the dimension value of the personnel warning dimension, n x2 The total number of personnel questions for this person registered for the question bank, α i2 is the risk point weight corresponding to the oth question (different questions have different weights, which are stored in the question library), m x2 is the total number of personnel interception risk events, β2 is the risk point weight corresponding to the pth personnel interception risk event, initialized to 1, v x2 is the total number of personnel warnings and clue missed detection problems, γ2 is the risk point weight corresponding to the qth personnel warning and clue missed detection problem, initialized to 1.

[0171] 2) Filter out third target data that is associated with the personnel warning dimension from the basic information collected by the basic data layer, and use the third dimension value calculation formula to perform calculation operations on the third target data to obtain the dimension value corresponding to the personnel warning dimension.

[0172] For the specific implementation of this step, please refer to the corresponding instructions above.

[0173] After calculating the dimension value corresponding to the above-mentioned personnel warning dimension, you can refer to the institutional warning dimension and sort by dimension value. The larger the dimension value, the more serious it is. The top 10% of personnel are screened out as warning personnel in the warning results and warning operations are performed.

[0174] On the basis of this embodiment, when an early warning is issued, the decision display layer is called, and an early warning operation is performed on the early warning result using a preset early warning method.

[0175] For example, the decision display layer is controlled to display the warning result in the form of a data list or a chart.

[0176] Taking personnel warning as an example, based on the personnel positions and risk codes of the imported risk data, the risk points and the distribution of the positions of the violators are summarized and analyzed. The main screen of this module is presented in a list and pie chart. The proportion of the person responsible for this violation is displayed in real time, accumulated on a monthly basis, and the calculation cycle is calculated based on the date the problem was entered. When querying and downloading, administrators at all levels do not enter the risk type, branch business institutions and personnel, but query all risk types and all outlets risk data within their jurisdiction.

[0177] In addition to display, the decision display layer can also be controlled to output the warning results to the terminal devices of preset personnel, such as pushing to relevant personnel in PC workstations, and sending them by email or SMS.

[0178] In this embodiment, early warning analysis is performed from different angles to improve the comprehensiveness and reliability of early warning. In addition, in the present invention, based on the collaboration of the decision analysis layer, the basic data layer and the decision display layer, early warning analysis operations can be performed in an orderly manner to improve the standardization of early warning analysis.

[0179] Based on the above-mentioned embodiment of the early warning method, another embodiment of the present invention provides an early warning device, which is applied to the decision analysis layer in the early warning system, and the early warning system also includes a basic data layer and a decision display layer; the basic data layer collects basic information through device upload method and data platform interface upload method; the decision analysis layer is implemented by a cloud Mysql server and a system cloud server, and is used to perform statistical analysis on the basic information to obtain early warning results, and the decision display layer includes early warning devices of institutions at all levels, which are used to perform early warning operations on the early warning results using a preset early warning method.

[0180] Reference Figure 4 , the early warning device comprises:

[0181] A dimension acquisition module 11 is used to acquire warning statistical dimensions, wherein the warning statistical dimensions include equipment warning dimensions, organization warning dimensions, and personnel warning dimensions; the equipment warning dimensions and the organization warning dimensions each include a plurality of sub-dimensions;

[0182] A statistical analysis module 12 is used to perform statistical analysis operations on the basic information collected by the basic data layer based on the early warning statistical dimensions to obtain dimension values ​​corresponding to each early warning statistical dimension;

[0183] The early warning analysis module 13 is used to perform early warning analysis on the dimension values ​​corresponding to each early warning statistical dimension to obtain an early warning result;

[0184] The early warning display module 14 is used to call the decision display layer and perform an early warning operation on the early warning result using a preset early warning method.

[0185] In one implementation, the device warning dimension includes a device operation status sub-dimension, a business transaction sub-dimension, a device type sub-dimension, and a device quantity sub-dimension;

[0186] The statistical analysis module 12 includes:

[0187] A first acquisition submodule, configured to acquire, for the device operation status sub-dimension, a first dimension value calculation formula corresponding to the device operation status sub-dimension;

[0188] The first dimension value calculation formula includes:

[0189]

[0190] Among them, S x is the dimension value corresponding to the device operation status sub-dimension, n x is the equipment life, α is the depreciation coefficient, m x is the number of equipment failure records obtained based on historical work order information statistics, β is the failure coefficient, and E x is the total number of all historical businesses handled by the device, and γ is the business wear coefficient;

[0191] A first screening submodule, configured to screen out first target data associated with the device operation status sub-dimension from the basic information collected by the basic data layer;

[0192] The first calculation submodule is used to perform a calculation operation on the first target data using the first dimension value calculation formula to obtain a dimension value corresponding to the device operation status sub-dimension.

[0193] In one implementation, the early warning analysis module 13 includes:

[0194] A rule acquisition submodule, used to acquire an early warning analysis rule, wherein the early warning analysis rule includes a corresponding relationship between the dimension value of the device operation status sub-dimension, the dimension value of the business transaction sub-dimension, the dimension value of the device type sub-dimension, the dimension value of the device quantity sub-dimension and the early warning result;

[0195] The rule query submodule is used to query the early warning analysis rules based on the dimension value of the device operation status sub-dimension, the dimension value of the business transaction sub-dimension, the dimension value of the device type sub-dimension, and the dimension value of the device quantity sub-dimension to obtain the early warning result.

[0196] In one implementation, the institutional warning dimension includes: an institutional risk level sub-dimension, an average warning clue quantum dimension of outlets, an average problem quantum dimension of outlets, and an average problem quantum dimension per capita of outlets;

[0197] The statistical analysis module 12 includes:

[0198] A second acquisition submodule is used to acquire, for the institutional risk level sub-dimension, a second dimension value calculation formula corresponding to the institutional risk level sub-dimension;

[0199] The second dimension value calculation formula includes:

[0200]

[0201] Among them, R x1 is the dimension value of the sub-dimension of the institution's risk level, n x1 is the total number of institutional issues, α i1 is the risk point weight corresponding to the i-th problem, m x1 is the total number of institutional interception risk events, β1 is the risk point weight corresponding to the jth institutional interception risk event, v x1 is the total number of institutional warning and clue missed detection problems, γ1 is the risk point weight corresponding to the kth institutional warning and clue missed detection problem;

[0202] A second screening submodule, used to screen out second target data having an associated relationship with the institutional risk level sub-dimension from the basic information collected in the basic data layer;

[0203] The second calculation submodule is used to use the second dimension value calculation formula to perform calculation operations on the second target data to obtain the dimension value corresponding to the institutional risk level sub-dimension.

[0204] In one implementation, the early warning analysis module 13 includes:

[0205] A sorting submodule is used to sort all institutions according to the sub-dimension values ​​in the institution warning dimension to obtain a sorting result;

[0206] An institution screening submodule, used to screen out institutions whose ranking values ​​are within a preset range in the ranking results;

[0207] The result determination submodule is used to use the screened institutions as warning institutions in the warning results.

[0208] In one implementation, the statistical analysis module 12 includes:

[0209] A third acquisition submodule is used to obtain a calculation formula for a third dimension value corresponding to the personnel warning dimension for the personnel warning dimension;

[0210] The third dimension value calculation formula includes:

[0211]

[0212] Among them, Rx2 is the dimension value of the personnel warning dimension, n x2 is the total number of personnel issues, α i2 is the risk point weight corresponding to the oth problem, m x2 is the total number of personnel interception risk events, β2 is the risk point weight corresponding to the pth personnel interception risk event, v x2 is the total number of personnel warning and clue missed detection problems, γ2 is the risk point weight corresponding to the qth personnel warning and clue missed detection problem;

[0213] A third screening submodule is used to screen out third target data associated with the personnel warning dimension from the basic information collected by the basic data layer;

[0214] The third calculation submodule is used to use the third dimension value calculation formula to perform calculation operations on the third target data to obtain the dimension value corresponding to the personnel warning dimension.

[0215] In one implementation, the warning display module 14 is specifically used for:

[0216] The decision display layer is controlled to display the warning results in the form of data lists or charts, and output the warning results to the terminal devices of preset personnel.

[0217] In this embodiment, the early warning operation is realized based on the mutual cooperation of the basic data layer, the decision analysis layer and the decision display layer. Specifically, the decision analysis layer performs statistical analysis and early warning analysis operations on the basic information collected by the basic data layer from three dimensions: the equipment early warning dimension, the organization early warning dimension and the personnel early warning dimension, obtains the early warning result, and then calls the decision display layer to perform an early warning operation on the early warning result using a preset early warning method. Since the embodiment of the present invention does not require human participation, it avoids the influence of human subjective factors and improves the accuracy of the early warning. In addition, the present invention performs early warning analysis from three dimensions: the equipment early warning dimension, the organization early warning dimension and the personnel early warning dimension, which can improve the comprehensiveness and reliability of the early warning.

[0218] It should be noted that, for the working process of each module and sub-module in this embodiment, please refer to the corresponding description in the above embodiment, which will not be repeated here.

[0219] An embodiment of the present application also provides an electronic device, including at least one processor and a memory connected to the processor, wherein:

[0220] The memory is used to store computer programs;

[0221] The processor is used to execute the computer program so that the electronic device can implement the above-mentioned early warning method.

[0222] refer to Figure 5 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include but is not limited to fixed terminals such as mobile phones, notebook computers, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0223] like Figure 5 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0224] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0225] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the early warning methods provided in the embodiments of the present application.

[0226] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any early warning method provided in the embodiment of the present application.

[0227] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An early warning method, characterized in that: The decision analysis layer applied to the early warning system also includes a basic data layer and a decision display layer; the basic data layer collects basic information through device upload and data platform interface upload; the decision analysis layer is implemented through a cloud Mysql server and a system cloud server, and is used to perform statistical analysis on the basic information to obtain early warning results, and the decision display layer includes early warning devices of institutions at all levels, and is used to perform early warning operations on the early warning results using a preset early warning method; The early warning method comprises: Acquire early warning statistical dimensions, wherein the early warning statistical dimensions include a device early warning dimension, an organization early warning dimension, and a personnel early warning dimension; the device early warning dimension and the organization early warning dimension each include a plurality of sub-dimensions; Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension; Performing warning analysis on the dimension values ​​corresponding to each warning statistical dimension to obtain a warning result; The decision display layer is called to perform a warning operation on the warning result using a preset warning method.

2. The early warning method according to claim 1, characterized in that: The device warning dimension includes the device operation status sub-dimension, the business transaction sub-dimension, the device type sub-dimension and the device quantity sub-dimension; Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension, including: For the device operation status sub-dimension, obtain a first dimension value calculation formula corresponding to the device operation status sub-dimension; The first dimension value calculation formula includes: Among them, s x is the dimension value corresponding to the device operation status sub-dimension, n x is the equipment life, α is the depreciation coefficient, m x is the number of equipment failure records obtained based on historical work order information statistics, β is the failure coefficient, and E x is the total number of all historical businesses handled by the device, and γ is the business wear coefficient; Filter out first target data associated with the device operation status sub-dimension from the basic information collected by the basic data layer; The first dimension value calculation formula is used to perform a calculation operation on the first target data to obtain a dimension value corresponding to the device operation status sub-dimension.

3. The early warning method according to claim 2, characterized in that: Perform warning analysis on the dimension values ​​corresponding to each warning statistical dimension to obtain warning results, including: Obtaining an early warning analysis rule, wherein the early warning analysis rule includes a correspondence between a dimension value of the device operation status sub-dimension, a dimension value of the business transaction sub-dimension, a dimension value of the device type sub-dimension, a dimension value of the device quantity sub-dimension, and an early warning result; Based on the dimension value of the device operation status sub-dimension, the dimension value of the business transaction sub-dimension, the dimension value of the device type sub-dimension, and the dimension value of the device quantity sub-dimension, the early warning analysis rules are queried to obtain early warning results.

4. The early warning method according to claim 1, characterized in that: The institutional warning dimensions include: institutional risk level sub-dimension, average warning clue sub-dimension of outlets, average problem sub-dimension of outlets, and average problem sub-dimension per capita of outlets; Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension, including: For the institutional risk level sub-dimension, obtaining a calculation formula for a second dimension value corresponding to the institutional risk level sub-dimension; The second dimension value calculation formula includes: Among them, R x1 is the dimension value of the sub-dimension of the institution's risk level, n x1 is the total number of institutional issues, α i1 is the risk point weight corresponding to the i-th problem, m x1 is the total number of institutional interception risk events, β1 is the risk point weight corresponding to the jth institutional interception risk event, v x1 is the total number of institutional warning and clue missed detection problems, γ1 is the risk point weight corresponding to the kth institutional warning and clue missed detection problem; Filter out second target data having a correlation relationship with the institutional risk level sub-dimension from the basic information collected by the basic data layer; The second dimension value calculation formula is used to perform calculation operations on the second target data to obtain the dimension value corresponding to the institutional risk level sub-dimension.

5. The early warning method according to claim 4, characterized in that: Perform warning analysis on the dimension values ​​corresponding to each warning statistical dimension to obtain warning results, including: For each sub-dimension in the institutional warning dimension, all institutions are sorted according to the sub-dimension value to obtain a sorting result; Filter out the institutions whose ranking values ​​are within a preset range in the ranking results; The screened institutions will be used as warning institutions in the warning results.

6. The early warning method according to claim 1, characterized in that: Based on the early warning statistical dimensions, statistical analysis operations are performed on the basic information collected by the basic data layer to obtain dimension values ​​corresponding to each early warning statistical dimension, including: For the personnel warning dimension, obtain a calculation formula for a third dimension value corresponding to the personnel warning dimension; The third dimension value calculation formula includes: Among them, R x2 is the dimension value of the personnel warning dimension, n x2 is the total number of personnel issues, α i2 is the risk point weight corresponding to the oth problem, m x2 is the total number of personnel interception risk events, β2 is the risk point weight corresponding to the pth personnel interception risk event, v x2 is the total number of personnel warning and clue missed detection problems, γ2 is the risk point weight corresponding to the qth personnel warning and clue missed detection problem; Filter out third target data associated with the personnel warning dimension from the basic information collected in the basic data layer; The third dimension value calculation formula is used to perform calculation operations on the third target data to obtain the dimension value corresponding to the personnel warning dimension.

7. The early warning method according to claim 1, characterized in that: The decision display layer is called to perform a warning operation on the warning result using a preset warning method, including: The decision display layer is controlled to display the warning results in the form of data lists or charts, and output the warning results to the terminal devices of preset personnel.

8. An early warning device, characterized in that: The decision analysis layer applied to the early warning system also includes a basic data layer and a decision display layer; the basic data layer collects basic information through device upload and data platform interface upload; the decision analysis layer is implemented through a cloud Mysql server and a system cloud server, and is used to perform statistical analysis on the basic information to obtain early warning results, and the decision display layer includes early warning devices of institutions at all levels, and is used to perform early warning operations on the early warning results using a preset early warning method; The early warning device comprises: A dimension acquisition module, used to acquire early warning statistical dimensions, wherein the early warning statistical dimensions include equipment early warning dimensions, organization early warning dimensions, and personnel early warning dimensions; the equipment early warning dimensions and the organization early warning dimensions each include a plurality of sub-dimensions; A statistical analysis module, used to perform statistical analysis operations on the basic information collected by the basic data layer based on the early warning statistical dimensions, and obtain dimension values ​​corresponding to each early warning statistical dimension; An early warning analysis module is used to perform early warning analysis on the dimension values ​​corresponding to each early warning statistical dimension to obtain an early warning result; The early warning display module is used to call the decision display layer and perform an early warning operation on the early warning result using a preset early warning method.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the early warning method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the early warning method as described in any one of claims 1 to 7.

Images