A data early warning method and system based on indicator system

Abstract

The present invention provides a data early warning method and system based on an indicator system, which relates to the technical field of data analysis, and the method includes: obtaining historical business data of a business subject; establishing an indicator system of a business subject; weighting each business subject indicator by an entropy method to obtain the entropy weight of each business subject indicator; determining the dynamic early warning threshold of each business subject indicator by a fixed numerical method or a statistical method; updating the indicator system according to the entropy weight and the dynamic early warning threshold; obtaining the business data to be detected of the business subject; inputting the business data to be detected into the updated indicator system, and calculating the comprehensive score of the business data to be detected in combination with the entropy weight of each business subject indicator; outputting the business data to be detected whose comprehensive score exceeds the dynamic early warning threshold as abnormal data; and issuing early warning information about the business data to be detected. The present invention improves the accuracy and adaptability of data early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a data early warning method and system based on an indicator system. Background Art

[0002] The data early warning method based on the indicator system is an early warning method that dynamically analyzes and monitors different data sources in real time by building a comprehensive multi-dimensional indicator system. It uses indicator weights and dynamic thresholds, combined with the historical and real-time data of business entities, to identify potential abnormal situations and issue early warnings in a timely manner, so as to help enterprises or organizations more effectively manage risks and provide decision support.

[0003] With the advent of the big data era, the application of data in various industries has become more and more extensive. As an important asset of enterprises and organizations, data can be monitored in real time and early warning information can be provided in a timely manner through technical means and combined with actual business scenario analysis, which is of great significance for risk control, decision support and other aspects.

[0004] However, existing data early warning methods mostly rely on single or a small number of key indicators, lack of comprehensive monitoring of business entities, many potential risk signals are difficult to capture, lack comprehensiveness and flexibility, and are difficult to adapt to complex and changing application scenarios. In the big data environment, the amount of data is growing rapidly, and traditional early warning models are difficult to extract information with management value from large amounts of data, resulting in many valuable data being ignored, failing to achieve comprehensive monitoring and analysis, and resulting in insufficient accuracy and effectiveness of data early warnings. Summary of the invention

[0005] In order to solve the technical problems that the existing data early warning methods in the prior art mostly rely on single or a small number of key indicators, lack of comprehensive monitoring of business entities, many potential risk signals are difficult to capture, lack of comprehensiveness and flexibility, and are difficult to adapt to complex and changeable application scenarios. In the big data environment, the amount of data is growing rapidly, and the traditional early warning mode is difficult to extract information with management value from a large amount of data, resulting in many valuable data being ignored, failing to achieve comprehensive monitoring and analysis, and resulting in insufficient accuracy and effectiveness of data early warning, the present invention provides a data early warning method and system based on an indicator system.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect

[0008] An embodiment of the present invention provides a data early warning method based on an indicator system, comprising:

[0009] S1: Acquire historical business data of a business subject, wherein the historical business data includes multiple business subject indicators;

[0010] S2: Establish an indicator system for business entities, where the indicator system includes an indicator library, association relationships, and indicator system usage rules for indicators of different business entities;

[0011] S3: weight each business subject indicator through the entropy method to obtain the entropy weight of each business subject indicator;

[0012] S4: Determine the dynamic warning threshold of each business subject indicator by fixed numerical method or statistical method, where the statistical method includes z-score method and interquartile range method;

[0013] S5: Update the indicator system according to the entropy weight and dynamic warning threshold;

[0014] S6: Obtain the business data to be tested of the business subject;

[0015] S7: Input the business data to be tested into the updated indicator system, and calculate the comprehensive score of the business data to be tested by combining the entropy weights of the indicators of each business subject;

[0016] S8: Output the business data to be detected whose comprehensive score exceeds the dynamic warning threshold as abnormal data;

[0017] S9: Issue warning information about the business data to be detected.

[0018] Second aspect

[0019] An embodiment of the present invention provides a data early warning system based on an indicator system, comprising:

[0020] processor;

[0021] A memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the data early warning method based on the indicator system of the first aspect is implemented.

[0022] The third aspect

[0023] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the data early warning method based on the indicator system as in the first aspect is implemented.

[0024] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0025] In the present invention, by constructing an indicator system, a comprehensive analysis of internal and external enterprise data, personal information and event data is conducted to ensure the comprehensiveness of the early warning, avoiding the problem of missing key information due to a single indicator in traditional methods. The entropy method is used to assign weights to each indicator, highlighting the key indicators that have a greater impact on abnormal early warnings, so that the system can focus on the indicators with the greatest risk indications, improve the accuracy and efficiency of early warnings, and determine the dynamic early warning thresholds for the indicators of each business entity. It can adapt to different data characteristics and real-time changing business needs, improve the applicability and sensitivity of early warnings, and reduce false alarms and omissions. After the data to be detected is input into the updated indicator system, the system can judge the degree of abnormality of the data based on the comprehensive score, identify abnormal data in real time, take timely countermeasures, avoid risk diffusion, and effectively improve the accuracy and effectiveness of data early warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A flow chart of a data early warning method based on an indicator system provided by an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of the structure of a data early warning system based on an indicator system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0030] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0031] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0032] Reference Manual Attached Figure 1 , which shows a flow chart of a data early warning method based on an indicator system provided in an embodiment of the present invention.

[0033] The embodiment of the present invention provides a data early warning method based on an indicator system, the method comprising:

[0034] S1: Obtain historical business data of a business entity, wherein the historical business data includes multiple business entity indicators.

[0035] Among them, business entities refer to the core objects in data analysis or business activities, such as enterprises, individuals, departments, etc., which are usually the main objects of data collection and monitoring. Historical business data refers to a collection of data related to the past behavior, operation, performance, etc. of the business entity, including financial records, operational data, market performance, etc., which reflects the historical status of the business entity. Business entity indicators are quantitative standards for measuring the performance of business entities in different aspects, such as financial indicators (revenue, profit), market indicators (market share), etc., which are used to specifically describe the various characteristics of the business entity.

[0036] In a possible implementation, the historical business data includes internal enterprise data, external enterprise data, basic personal information data, and event detection data.

[0037] Enterprise external data includes basic enterprise information data, enterprise branch overseas investment information data, enterprise operation abnormality information data, enterprise equity pledge information data, enterprise petition data, and enterprise social security payment data.

[0038] Internal enterprise data includes market trend data and competitor data.

[0039] Personal basic information data includes family status data, education data, marital status data, social security and employment data, and domestic violence incident data.

[0040] Event monitoring data include petition data, public opinion data, conflict mediation event data, 12345 telephone hotline data, labor arbitration event data and garbage classification event data.

[0041] In a possible implementation manner, after S1, the following steps are further included:

[0042] Pre-process historical business data including data cleaning, data integration, data reduction and data transformation.

[0043] Specifically, data preprocessing includes: checking the integrity of the data, identifying missing values ​​and handling missing values ​​by filling (such as mean, median or mode filling), interpolating or deleting records with too many missing values, evaluating the accuracy of the data, correcting obvious errors or outliers caused by entry errors or measurement errors, ensuring data consistency, that is, data from different sources or different time points should follow the same format and definition, handling duplicate data, identifying and deleting identical duplicate rows by comparing records in the data set, or merging records that have slight differences but essentially represent the same entity.

[0044] In addition, the positive and negative indicators have different meanings (the higher the positive indicator value, the better, and the lower the negative indicator value, the better). Therefore, different algorithms are needed to standardize the data for positive and negative indicators:

[0045] If it is a positive indicator X i , :

[0046]

[0047] Among them, x i represents the i-th positive indicator X i The standardized value of X max and X min They represent the maximum possible value and the minimum possible value of the business subject indicator respectively.

[0048] If it is a negative indicator x i , :

[0049]

[0050] Among them, x` i Represents i negative indicators X` i The standardized value of X` max and X` min They represent the maximum possible value and the minimum possible value of the business subject indicator respectively.

[0051] It should be noted that obtaining historical business data of business entities can provide a data basis for the current early warning system and help establish accurate behavioral models. By analyzing patterns and trends in historical data, the early warning system can more accurately identify abnormal situations, reduce false alarm and missed alarm rates, and contribute to more effective risk management and decision support.

[0052] S2: Establish an indicator system for business entities, where the indicator system includes an indicator library, association relationships and indicator system usage rules for indicators of different business entities.

[0053] Among them, the indicator system refers to a set of carefully designed indicators used to measure the status and performance of business entities. The indicator library contains a database of all relevant business indicators, including data from different aspects such as finance, operations, and markets, to comprehensively evaluate various dimensions of business entities. The association relationship refers to the logical relationship or mutual influence relationship between different business indicators. These relationships help the system understand the dependency or correlation between indicators. The indicator system uses rules to define how to use the indicator system in different scenarios or purposes, including analysis methods, calculation rules, threshold settings, etc., to ensure the correct application of the indicator system.

[0054] For example, the indicator library can be profit, turnover, and operating cost. The correlation relationship can be profit = revenue - cost. The indicator system usage rules can be year-on-year, month-on-month, compared with competition, or compared with targets.

[0055] In a possible implementation, the indicator library includes multiple related business subject indicators, each business subject indicator has a corresponding business subject indicator weight; the association relationship is the logical relationship between the various business subject indicators; the indicator system usage rules are the usage methods relative to the purpose of each business subject indicator.

[0056] It should be noted that establishing an indicator system for business entities can systematically collect and organize multi-dimensional data and provide a comprehensive view of business performance. By setting associations, the indicator system can identify potential connections between different indicators and improve the depth and accuracy of analysis. The use of rules ensures that the indicator system can be flexibly and accurately applied in different situations, providing stable and reliable decision-making support for the early warning system.

[0057] S3: Weight each business subject indicator through the entropy method to obtain the entropy weight of each business subject indicator.

[0058] Among them, the entropy method is a weighting method based on information entropy, which is used to calculate the weight of each indicator. The entropy method determines the importance of the indicator by analyzing the degree of discreteness of each indicator. The higher the degree of discreteness of the indicator, the greater the amount of information and the higher the weight. The entropy weight refers to the indicator weight obtained using the entropy method, which indicates the relative importance of each indicator in the overall evaluation. The higher the weight, the greater the role of the indicator in the evaluation system.

[0059] In a possible implementation, S3 specifically includes:

[0060] Normalize the business subject indicators:

[0061]

[0062] Among them, x represents the business subject indicator value, x max and x minRespectively represent the maximum and minimum values ​​of the business subject indicators, x * Indicates the normalized value of the business entity indicator value x.

[0063] Calculate the probability of each business subject indicator:

[0064]

[0065] Among them, p ij Indicates that the i-th business subject indicator has a value of x in the j-th indicator library ij The probability of x ij It represents the business subject indicator value of the i-th business subject indicator in the j-th indicator library, i=1,2,...,n, and n represents the total number of business subject indicators.

[0066] Calculate the entropy value of each business subject indicator based on probability:

[0067]

[0068] Among them, e i represents the entropy value of the ith business entity indicator, ln represents the natural logarithm function, and ∑ represents the sum.

[0069] According to the entropy value, the entropy weight of each business subject indicator is calculated:

[0070]

[0071] Among them, w i Represents the entropy weight of the j-th business entity indicator.

[0072] It should be noted that the use of the entropy method to weight indicators can effectively avoid the interference of human subjective factors and ensure the objectivity and scientificity of weight distribution. Through the entropy weights, the system can highlight the indicators that contribute the most information to the early warning system, thereby optimizing the effect of data analysis, improving the accuracy and effectiveness of early warnings, and accurately identifying potential risks.

[0073] S4: Determine the dynamic warning threshold of each business entity indicator through fixed numerical method or statistical method, among which the statistical method includes z-score method and interquartile range method.

[0074] In a possible implementation, the process of determining the dynamic warning threshold specifically includes:

[0075] The process of determining the dynamic warning threshold by the fixed value method is as follows:

[0076] Set preset fixed values ​​based on historical data as dynamic warning thresholds.

[0077] The process of determining the dynamic warning threshold by the z-score method is as follows:

[0078] Calculate the deviation between the business subject indicator value and the mean value, and use the deviation as the dynamic warning threshold. The specific calculation method of the deviation is as follows:

[0079]

[0080] Among them, Z represents deviation, x represents the business subject indicator value, σ represents the standard deviation of the business subject indicator value, and μ represents the mean value of the business subject indicator value.

[0081] The process of determining the dynamic warning threshold by the interquartile range method is as follows:

[0082] Calculate the first quartile Q1 and the third quartile Q3 of the business entity indicator value, and determine the dynamic warning threshold based on the first quartile and the third quartile:

[0083] IQR=Q3-Q1

[0084] Q3+1.5×IQR

[0085] Q1-1.5×IQR

[0086] Among them, IQR represents the intermediate variable, Q3+1.5×IQR and Q1-1.5×IQR represent the upper limit and lower limit of the dynamic warning threshold respectively.

[0087] It should be noted that by setting dynamic warning thresholds through fixed numerical methods or statistical methods, the system can adapt to different data characteristics more flexibly and avoid false alarms or omissions caused by fixed thresholds. The introduction of statistical methods further enhances the sensitivity of the early warning system to data anomalies, making the early warning more accurate, able to identify potential risks in a timely manner, and improve the effectiveness of risk management.

[0088] S5: Update the indicator system according to the entropy weight and dynamic warning threshold.

[0089] Specifically, in the process of updating the indicator system, the dynamic weighted balance loss function, dynamic weighting algorithm and regularization term can be used to dynamically adjust the weights of business subject indicators and optimize the weight distribution. The formula of the dynamic weighted balance loss function is specifically:

[0090]

[0091] Among them, L represents the dynamic weighted balance loss function, w j The weight of category j, j = 1, 2, ..., c, c represents the number of categories, y ijrepresents the label of sample i generated by one-hot encoding, i = 1, 2, ..., n, n represents the number of training samples, p ij It represents the predicted probability that sample i belongs to category j, and Regularization Term represents the regularization term.

[0092] It should be noted that by updating the indicator system based on entropy weights and dynamic warning thresholds, we can always adapt to changes in data and business environment and maintain the accuracy and adaptability of the early warning system. The entropy weights enable the early warning system to focus on key indicators, while the dynamic warning thresholds improve the system's responsiveness and can more effectively identify potential anomalies and risks, providing continuous optimization support for management and decision-making.

[0093] S6: Obtain the business data to be tested of the business subject.

[0094] Among them, the business data to be detected refers to the real-time or newly generated data collected from the business entity at the current time point or within a specific detection cycle, which is used for monitoring and early warning analysis.

[0095] It should be noted that obtaining the business data to be tested of the business entity enables the early warning system to respond quickly based on real-time information. Compared with relying solely on historical data, real-time data input improves the system's dynamic monitoring capabilities, helps to detect potential risks in a timely manner, and enhances the system's predictive accuracy and decision-making support capabilities, thereby more effectively protecting the stability and security of the business.

[0096] S7: Input the business data to be tested into the updated indicator system, and calculate the comprehensive score of the business data to be tested based on the entropy weights of the indicators of each business entity.

[0097] Among them, the comprehensive score is a score calculated by combining the business data to be tested with the entropy value weight, which reflects the overall risk level or health status of the current data status of the business entity.

[0098] In a possible implementation, the calculation formula of the comprehensive score is specifically:

[0099]

[0100] Among them, S represents the comprehensive score, x i and w i They respectively represent the indicator value and indicator weight of the i-th business entity.

[0101] It should be noted that inputting the business data to be detected into the updated indicator system and calculating the comprehensive score in combination with the entropy weight can ensure that the early warning system can accurately evaluate the latest data. The comprehensive score integrates the importance of different indicators and provides a comprehensive risk picture of the business entity, allowing managers to identify abnormal situations faster and more accurately, take timely response measures, and improve risk warning and management efficiency.

[0102] S8: Output the business data to be detected whose comprehensive score exceeds the dynamic warning threshold as abnormal data.

[0103] The specific process of early warning judgment is as follows: receiving historical business data, entering the early warning judgment stage by setting weights for indicators of various business entities; when the early warning conditions are met, that is, the comprehensive score exceeds the dynamic early warning threshold, the system generates early warning information and is confirmed by relevant personnel; if the conditions are not met, new historical business data is received again for cyclic judgment, thereby achieving real-time and dynamic risk monitoring.

[0104] It should be noted that marking the business data to be detected whose comprehensive score exceeds the dynamic warning threshold as abnormal data output can effectively identify potential risks and abnormal situations. In this way, the system can list the abnormal data separately, making it easier for managers to pay attention to key issues in a timely manner and improve the pertinence and efficiency of risk monitoring.

[0105] S9: Issue warning information about the business data to be detected.

[0106] Among them, early warning information refers to the notification or alarm information generated by the system when abnormal data is detected, which is used to remind managers of possible risks or abnormal situations, usually including the specific indicators, degree and recommended handling measures of the abnormality.

[0107] In a possible implementation manner, after S9, the method further includes:

[0108] Update the indicator system at preset intervals.

[0109] It should be noted that issuing early warning information can enable managers to receive timely reminders of key risks, enabling them to quickly respond to and deal with potential problems, thereby reducing losses and enhancing the timeliness and initiative of risk management. This early warning mechanism can help companies detect problems at an early stage and provide decision makers with important prevention and handling basis.

[0110] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0111] In the present invention, by constructing an indicator system, a comprehensive analysis of internal and external enterprise data, personal information and event data is conducted to ensure the comprehensiveness of the early warning, avoiding the problem of missing key information due to a single indicator in traditional methods. The entropy method is used to assign weights to each indicator, highlighting the key indicators that have a greater impact on abnormal early warnings, so that the system can focus on the indicators with the greatest risk indications, improve the accuracy and efficiency of early warnings, and determine the dynamic early warning thresholds for the indicators of each business entity. It can adapt to different data characteristics and real-time changing business needs, improve the applicability and sensitivity of early warnings, and reduce false alarms and omissions. After the data to be detected is input into the updated indicator system, the system can judge the degree of abnormality of the data based on the comprehensive score, identify abnormal data in real time, take timely countermeasures, avoid risk diffusion, and effectively improve the accuracy and effectiveness of data early warnings.

[0112] Reference Manual Attached Figure 2 , showing a schematic structural diagram of a data early warning system based on an indicator system provided by the present invention.

[0113] The present invention further provides a data early warning system 20 based on an indicator system, which is applied to the above-mentioned data early warning method based on an indicator system, and comprises:

[0114] Processor 201.

[0115] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the data early warning method based on the indicator system in the method embodiment is implemented.

[0116] The indicator system-based data early warning system 20 provided by the present invention can execute the above-mentioned indicator system-based data early warning method and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0117] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0118] In the present invention, by constructing an indicator system, a comprehensive analysis of internal and external enterprise data, personal information and event data is conducted to ensure the comprehensiveness of the early warning, avoiding the problem of missing key information due to a single indicator in traditional methods. The entropy method is used to assign weights to each indicator, highlighting the key indicators that have a greater impact on abnormal early warnings, so that the system can focus on the indicators with the greatest risk indications, improve the accuracy and efficiency of early warnings, and determine the dynamic early warning thresholds for the indicators of each business entity. It can adapt to different data characteristics and real-time changing business needs, improve the applicability and sensitivity of early warnings, and reduce false alarms and omissions. After the data to be detected is input into the updated indicator system, the system can judge the degree of abnormality of the data based on the comprehensive score, identify abnormal data in real time, take timely countermeasures, avoid risk diffusion, and effectively improve the accuracy and effectiveness of data early warnings.

[0119] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may 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 gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0120] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0121] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0122] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0123] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0124] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0125] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0130] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0131] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the data early warning method based on an indicator system as in the method embodiment is implemented.

[0132] A computer-readable storage medium provided by the present invention can implement the steps and effects of the data early warning method based on the indicator system of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0133] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0134] In the present invention, by constructing an indicator system, a comprehensive analysis of internal and external enterprise data, personal information and event data is conducted to ensure the comprehensiveness of the early warning, avoiding the problem of missing key information due to a single indicator in traditional methods. The entropy method is used to assign weights to each indicator, highlighting the key indicators that have a greater impact on abnormal early warnings, so that the system can focus on the indicators with the greatest risk indications, improve the accuracy and efficiency of early warnings, and determine the dynamic early warning thresholds for the indicators of each business entity. It can adapt to different data characteristics and real-time changing business needs, improve the applicability and sensitivity of early warnings, and reduce false alarms and omissions. After the data to be detected is input into the updated indicator system, the system can judge the degree of abnormality of the data based on the comprehensive score, identify abnormal data in real time, take timely countermeasures, avoid risk diffusion, and effectively improve the accuracy and effectiveness of data early warnings.

[0135] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0136] There are a few points to note:

[0137] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0138] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0139] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0140] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A data early warning method based on an indicator system, characterized in that: include: S1: Acquire historical business data of a business subject, wherein the historical business data includes multiple business subject indicators; S2: Establishing an indicator system for the business subject, wherein the indicator system includes an indicator library, association relationships and indicator system usage rules for indicators of different business subjects; S3: weight each business subject indicator through the entropy method to obtain the entropy weight of each business subject indicator; S4: Determine the dynamic warning threshold of each business subject indicator by a fixed numerical method or a statistical method, wherein the statistical method includes a z-score method and an interquartile range method; S5: updating the indicator system according to the entropy value weight and the dynamic warning threshold; S6: Acquire the business data to be detected of the business subject; S7: input the business data to be detected into the updated indicator system, and calculate the comprehensive score of the business data to be detected in combination with the entropy weights of the indicators of each business subject; S8: Outputting the service data to be detected whose comprehensive score exceeds the dynamic warning threshold as abnormal data; S9: Issue warning information about the service data to be detected.

2. The data early warning method based on the indicator system according to claim 1 is characterized in that: The historical business data includes internal enterprise data, external enterprise data, personal basic information data and event detection data; The enterprise external data includes enterprise basic information data, enterprise branch foreign investment information data, enterprise operation abnormality information data, enterprise equity pledge information data, enterprise petition data, and enterprise social security payment data; The enterprise internal data includes market trend data and competitor data; The basic personal information data includes family status data, education data, marital status data, social security and employment data, and domestic violence incident data; The event monitoring data includes petition data, public opinion data, conflict mediation event data, 12345 telephone hotline data, labor arbitration event data and garbage classification event data.

3. The data early warning method based on the indicator system according to claim 1 is characterized in that: After S1, the following is also included: The historical business data is preprocessed including data cleaning, data integration, data reduction and data transformation.

4. The data early warning method based on the indicator system according to claim 1 is characterized in that: The indicator library includes multiple related business subject indicators, each business subject indicator has a corresponding business subject indicator weight; the association relationship is the logical relationship between the various business subject indicators; the indicator system usage rules are the usage methods relative to the purpose of each business subject indicator.

5. The data early warning method based on the indicator system according to claim 1 is characterized in that: The S3 specifically includes: Normalize the business subject indicators: Among them, x represents the business entity indicator value, x max and x min Respectively represent the maximum and minimum values ​​of the business subject indicators, x * Indicates the normalized value of the business subject indicator value x; Calculate the probability of each business subject indicator: Among them, p ij Indicates that the i-th business subject indicator has a value of x in the j-th indicator library ij The probability of x ij Indicates the business subject indicator value of the i-th business subject indicator in the j-th indicator library, i = 1, 2, ..., n, n represents the total number of business subject indicators; Calculate the entropy value of each business subject indicator based on the probability: Among them, e i represents the entropy value of the i-th business subject indicator, ln represents the natural logarithm function, and ∑ represents the sum; According to the entropy value, the entropy weight of each business subject indicator is calculated: Among them, w i Represents the entropy weight of the j-th business entity indicator.

6. The data early warning method based on the indicator system according to claim 1 is characterized in that: The process of determining the dynamic warning threshold specifically includes: The process of determining the dynamic warning threshold by the fixed value method is specifically as follows: Setting a preset fixed value based on the historical data as the dynamic warning threshold; The process of determining the dynamic warning threshold by the z-score method is specifically as follows: Calculate the deviation between the business subject indicator value and the mean value, and use the deviation as the dynamic warning threshold. The calculation method of the deviation is specifically as follows: Among them, Z represents deviation, x represents the business subject indicator value, σ represents the standard deviation of the business subject indicator value, and μ represents the mean of the business subject indicator value; The process of determining the dynamic warning threshold by the quartile range method is specifically as follows: Calculate the first quartile Q1 and the third quartile Q3 of the business subject indicator value, and determine the dynamic warning threshold based on the first quartile and the third quartile: IQR=Q3-Q1 Q3+1.5×IQR Q1-1.5×IQR Among them, IQR represents the intermediate variable, Q3+1.5×IQR and Q1-1.5×IQR represent the upper limit and lower limit of the dynamic warning threshold respectively.

7. The data early warning method based on the indicator system according to claim 1 is characterized in that: The calculation formula of the comprehensive score is specifically: Wherein, S represents the comprehensive score, x i and w i They respectively represent the indicator value and indicator weight of the i-th business entity.

8. The data early warning method based on the indicator system according to claim 1 is characterized in that: After S9, the method further includes: The indicator system is updated at preset time intervals.

9. A data early warning system based on an indicator system, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the data early warning method based on the indicator system as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the data early warning method based on the indicator system as described in any one of claims 1 to 8 is implemented.

Images