Business data exception analysis method and device, electronic equipment and storage medium

Abstract

The invention provides a business data exception analysis method and device, electronic equipment and a storage medium. The business data exception analysis method comprises the following steps: acquiring business data; establishing a business analysis model; sorting the business data according to the business analysis model to generate sorted business data; obtaining a business data index; cleaning the sorted service data according to the service data index to generate cleaned service data; comparing the cleaned business data with business data indexes to generate abnormal index data; and analyzing the abnormal index data based on an attribution algorithm to generate an abnormal reason. By means of the method, an analysis mode depending on artificial experience can be replaced, automatic and accurate attribution analysis is achieved through a balance weight model and an algorithm, efficiency and accuracy are improved, attribution analysis can be conducted by integrating multiple factors, data can be updated in real time, abnormity can be found and processed in time, and potential risks are reduced.

Description

Technical Field

[0001] The present invention relates to the field of supply chain business processing, and in particular to a method, device, electronic device and storage medium for analyzing business data anomalies. Background Art

[0002] In enterprise business such as supply chain, a large amount of business data processing and analysis is usually involved. The traditional approach is to rely on manual experience and simple data analysis tools. This method can identify and handle common data anomalies to a certain extent, but it cannot quickly, accurately and comprehensively perform attribution analysis on complex abnormal business data.

[0003] Therefore, how to propose a general device for attribution analysis of abnormal business data, which can efficiently and accurately perform attribution analysis on various complex business data anomalies, and provide strong support for monitoring, early warning and auxiliary decision-making, and provide methods, devices, electronic equipment and storage media for business data anomaly analysis has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art or related art.

[0005] Therefore, the first object of the present invention is to provide a method for analyzing business data anomalies.

[0006] The second object of the present invention is to provide a device for analyzing business data anomalies.

[0007] A third object of the present invention is to provide an electronic device.

[0008] A fourth object of the present invention is to provide a readable storage medium.

[0009] To achieve the above-mentioned purpose, the technical solution of the first aspect of the present invention provides a method for analyzing business data anomalies, including: obtaining business data; establishing a business analysis model; organizing the business data according to the business analysis model to generate organized business data; obtaining business data indicators; cleaning the organized business data according to the business data indicators to generate cleaned business data; comparing the cleaned business data with the business data indicators to generate abnormal indicator data; analyzing the abnormal indicator data based on the attribution algorithm to generate the cause of the anomaly.

[0010] The method for analyzing business data anomalies provided by the technical solution of the present invention includes: first, the business data is sorted through the business analysis model, and the sorted business data is more organized than the business data before sorting, and then the data business indicators are obtained. The business data indicators can reflect the state of the business data. By obtaining different business data indicators, the rationality of the business data can be reflected from different angles, thereby generating whether the business data is abnormal. In some possible technical solutions, it is optional to clean up the sorted business data according to the business data indicators, remove the invalid parts, and reduce the amount of data processing. After cleaning the business data, the business data is compared with the business data indicators. The business data indicators include a reasonable range of business data indicators. By comparing the business data with the cleaned business data, unreasonable business data can be found as abnormal indicator data, and the abnormal indicator data is attributed, and then the abnormal cause of the abnormal indicator data is found. The abnormal cause can be other business data that affects the abnormal indicator data. The method in this application can replace the analysis mode that relies on manual experience and realize automated and accurate attribution analysis through the weight model and algorithm, thereby improving efficiency and accuracy. It can also integrate multiple factors for attribution analysis, and can update data in real time, detect and handle anomalies in a timely manner, and reduce potential risks.

[0011] In some possible technical solutions, optionally, the business data is sorted according to the business analysis model, and the steps of generating sorted business data include: obtaining business attributes of the business data; the business analysis model includes business analysis units generated according to the business attributes; the business data is added to the business analysis unit corresponding to the business attributes according to the business attributes, so as to sort the business data and generate sorted business data.

[0012] In this technical solution, first, the business attributes of the business data are obtained, while the business analysis unit in the business analysis model has blank attributes. By assigning the business attributes of the business data to the blank attributes in the business analysis unit, a relationship mapping between the business attributes of the business data and the blank attributes in the business analysis unit is formed. The attributes of the business analysis unit are singular, that is, multiple identical business attributes correspond to one business analysis unit, so that the business attributes can be deduplicated, and different business data can be organized and defined through one model, thereby supporting different business scenarios.

[0013] In some possible technical solutions, optionally, the cleaned business data is compared with business data indicators, and the step of generating abnormal indicator data includes: obtaining a threshold value of the business data indicator; comparing the cleaned business data with the threshold value, and treating the cleaned business data that does not meet the threshold value as abnormal indicator data.

[0014] In this technical solution, the cleaned business data is compared with the business data indicators, and the step of generating abnormal indicator data includes: obtaining the threshold of the business data indicator; comparing the cleaned business data with the threshold, and using the cleaned business data that does not meet the threshold as abnormal indicator data. First, it is necessary to obtain the threshold of the business data indicator, that is, the standard used to determine whether the business data is abnormal. By marking the cleaned business data and the threshold, it is possible to generate whether the business data is abnormal, and define the business data that does not meet the threshold as abnormal indicator data. Automatic generation of abnormal indicator data is achieved.

[0015] In some possible technical solutions, optionally, the attribution algorithm includes one or more of a propensity score matching method, a double difference method, a regression analysis method, a gradient-based attribution algorithm, and an attribution algorithm based on layer-by-layer back-propagation.

[0016] In some possible technical solutions, optionally, the sorted business data is cleaned according to the business data indicators, and the steps of generating the cleaned business data include: correcting the sorted business data according to the definition of the business data indicators to remove invalid, duplicate, missing or erroneous data; and using the remaining data as the cleaned business data.

[0017] In this technical solution, since the definition of business data indicators often limits the type, size and rationality of business data, the business data can be cleaned up through the definition of business data indicators to remove invalid, duplicate, missing or erroneous data; the remaining data is used as cleaned business data, thereby reducing the amount of data processing in subsequent processing and improving the rationality of data analysis. In some possible technical solutions, optionally, after analyzing the abnormal indicator data based on the attribution algorithm to obtain the abnormal cause, the method for analyzing business data anomaly also includes: comparing the abnormal cause with the business data indicator to generate auxiliary decisions.

[0018] In this technical solution, the cause of the anomaly may be multiple business data. By comparing the business data and the business data indicators, the direction of improvement can be analyzed. For example, if the parameters of the business data are smaller than the business data indicators, it means that the parameters of the business data need to be increased, thereby proposing auxiliary decisions.

[0019] The technical solution of the second aspect of the present invention provides a business data anomaly analysis device including: a business data acquisition unit, used to acquire business data; a business analysis model establishment unit, used to establish a business analysis model; a business analysis model unit, used to organize the business data according to the business analysis model to generate organized business data; an indicator acquisition unit, used to acquire business data indicators; an abnormal data analysis unit, used to clean the organized business data according to the business data indicators to generate cleaned business data, compare the cleaned business data with the business data indicators to generate abnormal indicator data, analyze the abnormal indicator data based on the attribution algorithm, and generate abnormal causes.

[0020] In this technical solution, a business data anomaly analysis device includes: a business data acquisition unit for acquiring business data; a business analysis model establishment unit for establishing a business analysis model; a business analysis model unit for arranging business data according to the business analysis model to generate arranged business data; an indicator acquisition unit for acquiring business data indicators; an abnormal data analysis unit for cleaning the arranged business data according to the business data indicators to generate cleaned business data, comparing the cleaned business data with the business data indicators to generate abnormal indicator data, analyzing the abnormal indicator data based on the attribution algorithm to generate the abnormal cause. Then, the method for analyzing business data anomaly provided by any one of the technical solutions of the first aspect of the present application is realized.

[0021] In some possible technical solutions, optionally, the abnormal data analysis unit is also used to compare the abnormal cause with the business data indicator to generate auxiliary decision.

[0022] In this technical solution, the cause of the anomaly may be multiple business data. By comparing the business data and the business data indicators, the direction of improvement can be analyzed. For example, if the parameters of the business data are smaller than the business data indicators, it means that the parameters of the business data need to be increased, thereby proposing auxiliary decisions.

[0023] The technical solution of the third aspect of the present invention provides an electronic device, a memory and a processor, wherein the memory stores a program, and when the processor executes the program, the steps of the method for analyzing business data anomalies provided by any technical solution of the first aspect of the present application are implemented. Therefore, the electronic device provided by the present invention has all the beneficial effects of the method for analyzing business data anomalies provided by any technical solution of the first aspect of the present invention.

[0024] The technical solution of the fourth aspect of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed, the steps of the method for analyzing business data anomaly provided by any technical solution of the first aspect of the present application are implemented. Therefore, the readable storage medium provided by the present invention has all the beneficial effects of the method for analyzing business data anomaly provided by any technical solution of the first aspect of the present invention.

[0025] Additional aspects and advantages of the present invention will become apparent from the following description or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 This is one of the principle schematic diagrams of the method for analyzing business data anomalies provided by an embodiment of the present invention; Figure 2 This is the second principle schematic diagram of the method for analyzing business data anomalies provided by an embodiment of the present invention; Figure 3 This is the third principle schematic diagram of the method for analyzing business data anomalies provided by an embodiment of the present invention; Figure 4 This is the fourth principle schematic diagram of the method for analyzing business data anomalies provided by an embodiment of the present invention; Figure 5 This is the fifth principle schematic diagram of the method for analyzing business data anomalies provided by an embodiment of the present invention; Figure 6 is a block diagram of a device for analyzing abnormality of business data provided by an embodiment of the present invention; Figure 7 is a block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0028] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0029] Refer to the following Figures 1 to 7 To describe the method, device, electronic device and storage medium for business data anomaly analysis provided by the present invention.

[0030] like Figure 1 To achieve the above-mentioned purpose, an embodiment of the first aspect of the present invention provides a method for analyzing business data anomalies, including: S101: Acquire business data; S103: Establish business analysis model; S105: Arrange the business data according to the business analysis model to generate arranged business data; S107: Obtain business data indicators; S109: Cleaning the sorted business data according to the business data indicators to generate cleaned business data; S111: Compare the cleaned business data with the business data indicators to generate abnormal indicator data; S113: Analyze the abnormal indicator data based on the attribution algorithm to generate the abnormal cause.

[0031] According to the method for analyzing business data anomalies provided by an embodiment of the present invention, the method comprises: firstly, arranging business data through a business analysis model, wherein the arranging business data is more organized than the business data before arranging, and then obtaining data business indicators, wherein the business data indicators can reflect the state of the business data, and by obtaining different business data indicators, the rationality of the business data can be reflected from different angles, thereby generating whether the business data is abnormal. In some possible embodiments, optionally, it is necessary to clean up the arranging business data according to the business data indicators, remove the invalid parts, and reduce the amount of data processing. After cleaning the business data, the business data is compared with the business data indicators, and the business data indicators include a reasonable range of the business data indicators. By comparing the business data with the cleaned business data, unreasonable business data can be found as abnormal indicator data, and the abnormal indicator data is attributed, thereby finding out the abnormal cause of the abnormal indicator data, and the abnormal cause can be other business data that affects the abnormal indicator data. The method in this application can replace the analysis mode that relies on manual experience and realize automated and accurate attribution analysis through the weight model and algorithm, thereby improving efficiency and accuracy. It can also integrate multiple factors for attribution analysis, and can update data in real time, detect and handle anomalies in a timely manner, and reduce potential risks.

[0032] In some possible embodiments, optionally, the business data is sorted according to the business analysis model, and the steps of generating sorted business data include: obtaining business attributes of the business data; the business analysis model includes a business analysis unit generated according to the business attributes; and the business data is added to the business analysis unit corresponding to the business attributes according to the business attributes to sort the business data and generate sorted business data.

[0033] In this embodiment, first, the business attributes of the business data are obtained, while the business analysis unit in the business analysis model has blank attributes. By assigning the business attributes of the business data to the blank attributes in the business analysis unit, a relationship mapping between the business attributes of the business data and the blank attributes in the business analysis unit is formed. The attributes of the business analysis unit are singular, that is, multiple identical business attributes correspond to one business analysis unit, so that the business attributes can be deduplicated, and different business data can be sorted and defined through one model, thereby supporting different business scenarios.

[0034] In some possible embodiments, optionally, the cleaned business data is compared with business data indicators, and the step of generating abnormal indicator data includes: obtaining a threshold value of the business data indicator; comparing the cleaned business data with the threshold value, and treating the cleaned business data that does not meet the threshold value as abnormal indicator data.

[0035] In this embodiment, the cleaned business data is compared with the business data index, and the step of generating abnormal index data includes: obtaining the threshold of the business data index; comparing the cleaned business data with the threshold, and using the cleaned business data that does not meet the threshold as abnormal index data. First, it is necessary to obtain the threshold of the business data index, that is, the standard used to determine whether the business data is abnormal. By marking the cleaned business data and the threshold, it is possible to generate whether the business data is abnormal, and define the business data that does not meet the threshold as abnormal index data. Automatic generation of abnormal index data is achieved.

[0036] In some possible embodiments, optionally, the attribution algorithm includes one or more of a propensity score matching method, a double difference method, a regression analysis method, a gradient-based attribution algorithm, and an attribution algorithm based on layer-by-layer back-propagation.

[0037] In some possible embodiments, optionally, the sorted business data is cleaned according to the business data indicators, and the steps of generating the cleaned business data include: correcting the sorted business data according to the definition of the business data indicators to remove invalid, duplicate, missing or erroneous data; and using the remaining data as the cleaned business data.

[0038] In this embodiment, since the definition of business data indicators often limits the type, size and rationality of business data, the business data can be cleaned up through the definition of business data indicators to remove invalid, duplicate, missing or erroneous data; the remaining data is used as cleaned business data, thereby reducing the amount of data processing in subsequent processing and improving the rationality of data analysis.

[0039] In some possible embodiments, optionally, after the step of analyzing the abnormal indicator data based on the attribution algorithm to obtain the abnormal cause, the method for analyzing business data anomaly also includes: comparing the abnormal cause with the business data indicator to generate an auxiliary decision.

[0040] In this embodiment, the cause of the abnormality may be multiple business data. By comparing the business data and the business data indicators, the direction of improvement can be analyzed. For example, if the parameters of the business data are smaller than the business data indicators, it means that the parameters of the business data need to be increased, thereby proposing auxiliary decisions.

[0041] In some possible embodiments, optionally, the business system unit data is collected into the business data collection unit through the data collection task, and then data cleaning is performed. The business abnormal data attribution analysis unit will analyze the collected data to find abnormal data, and then use the business abnormal data attribution algorithm to analyze and process it to provide auxiliary decision-making and suggestions to the user. Figure 2 In the process, you can publish collection tasks for business data unit A and business data unit B, then perform cleanup processing tasks on the business data in business data unit A and business data unit B, and perform business anomaly attribution analysis on the cleaned business data.

[0042] The business system unit uses the relational model mapping to map the business system unit data attributes with the business data analysis unit attributes, generates a data collection task after publishing, and then collects the data into the business data unit. Figure 3 In the data analysis unit, business unit A has attributes A and B, while business unit B has attributes A, B, and C. That is, business units A and B have the same attributes A and B, which will be deduplicated when mapped to the business data analysis unit through the relational model. Therefore, only attributes A, B, and C will be reflected in the data analysis unit, rather than attributes A, A, B, B, and C. These attributes are defined by using one model. This method allows one underlying model to support different business scenarios. Then, different data collection tasks are generated through relational model mapping to collect data into the business data analysis unit.

[0043] Based on the data collected by the business data analysis unit, the corresponding indicators are defined, and the indicator summary model task is automatically generated based on the indicators. After release, the data will be automatically cleaned according to the indicator definition and then the indicator data will be generated. Figure 4 In the business data analysis unit, there are attributes A, B and C. However, after the indicator is created, attribute C is not needed, that is, attribute C is an invalid attribute. Therefore, the data in the model can be cleaned up by indicator creation, and attribute C can be cleaned up. At the same time, duplicate and redundant data can also be cleaned up to obtain indicators A and B, and then the cleaned data is automatically generated according to the indicator summary model.

[0044] Based on the indicator data generated after processing by the indicator model unit, the business abnormal data attribution model will find abnormal indicators according to the indicator definition, and then use the business data abnormal attribution algorithm to analyze the abnormal cause and provide auxiliary decision-making to the user. Figure 5 As shown in , the indicator model unit includes indicator A, indicator B, indicator C and indicator D. According to the data anomaly analysis attribution algorithm model, the abnormal indicators are found to be abnormal indicator A and abnormal indicator D. The attribution algorithm analyzes the causes based on the abnormal indicators and guides users to make decisions.

[0045] The existing technologies have the following problems: 1. Manual analysis is inefficient and difficult to handle with massive business data, prone to omissions and errors. 2. Fixed data analysis processes lack flexibility and cannot adapt to complex and changing business scenarios and data characteristics. 3. Traditional methods are difficult to fully consider various relevant factors, resulting in inaccurate and incomplete attribution analysis results. 4. Traditional methods lack effective identification and processing capabilities for emerging abnormal business data patterns, and are unable to detect potential risks in a timely manner.

[0046] The method in this application is different from the traditional methods and analysis modes in existing patents that rely on manual experience. This application can realize automated and accurate attribution analysis by configuring models and algorithms, thereby improving efficiency and accuracy.

[0047] Different from the fixed and inflexible data analysis processes in traditional methods and existing patents, the present invention can flexibly recommend applicable algorithms based on the business system and adapt to complex scenarios.

[0048] Different from the limitations of traditional methods and existing patents that are difficult to fully consider relevant factors, the present invention can integrate multiple factors for attribution analysis and provide more complete and accurate results.

[0049] Different from the traditional methods and existing patents that are insufficient in processing new abnormal data patterns, the present invention can detect and process them in a timely manner, thereby reducing potential risks.

[0050] The embodiment of the second aspect of the present invention provides a business data anomaly analysis device 600 including: Figure 6 As shown, a business data acquisition unit 601 is used to acquire business data; a business analysis model establishment unit 603 is used to establish a business analysis model; a business analysis model unit 605 is used to organize business data according to the business analysis model to generate organized business data; an indicator acquisition unit 607 is used to acquire business data indicators; an abnormal data analysis unit 609 is used to clean the organized business data according to the business data indicators to generate cleaned business data, compare the cleaned business data with the business data indicators to generate abnormal indicator data, analyze the abnormal indicator data based on the attribution algorithm, and generate abnormal causes.

[0051] In this embodiment, a business data anomaly analysis device 600 includes: a business data acquisition unit 601, used to acquire business data; a business analysis model establishment unit 603, used to establish a business analysis model; a business analysis model unit 605, used to organize business data according to the business analysis model and generate organized business data; an indicator acquisition unit 607, used to acquire business data indicators; an abnormal data analysis unit 609, used to clean up the organized business data according to the business data indicators, generate cleaned business data, compare the cleaned business data with the business data indicators, generate abnormal indicator data, analyze the abnormal indicator data based on the attribution algorithm, and generate the abnormal cause. Then, the method for analyzing business data anomaly provided by any embodiment of the first aspect of the present application is realized.

[0052] In some possible embodiments, optionally, the abnormal data analysis unit 609 is also used to compare the abnormal cause with the business data indicator to generate an auxiliary decision.

[0053] In this embodiment, the cause of the abnormality may be multiple business data. By comparing the business data and the business data indicators, the direction of improvement can be analyzed. For example, if the parameters of the business data are smaller than the business data indicators, it means that the parameters of the business data need to be increased, thereby proposing auxiliary decisions.

[0054] The embodiment of the third aspect of the present invention provides an electronic device 700, such as Figure 7 As shown, the memory 701 and the processor 703, the memory 701 stores a program, and the processor 703 implements the steps of the method for analyzing business data anomalies provided by any embodiment of the first aspect of the present application when executing the program. Therefore, the electronic device 700 provided by the present invention has all the beneficial effects of the method for analyzing business data anomalies in any embodiment of the first aspect of the present invention.

[0055] The embodiment of the fourth aspect of the present invention provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed, the steps of the method for analyzing business data anomaly provided by any embodiment of the first aspect of the present application are implemented. Therefore, the readable storage medium provided by the present invention has all the beneficial effects of the method for analyzing business data anomaly provided by any embodiment of the first aspect of the present invention.

[0056] In the description of this specification, the terms "connection", "installation", "fixation" and the like should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0058] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for analyzing business data anomalies, characterized in that: include: Get business data; Build business analysis models; Arrange the business data according to the business analysis model to generate arranged business data; Get business data indicators; Cleaning the sorted business data according to the business data indicators to generate cleaned business data; Comparing the cleaned business data with the business data indicators to generate abnormal indicator data; The abnormal indicator data is analyzed based on an attribution algorithm to generate abnormal causes.

2. The method for analyzing business data anomalies according to claim 1, characterized in that: The step of arranging the business data according to the business analysis model to generate the arranged business data comprises: Acquire the business attributes of the business data; The business analysis model includes a business analysis unit generated according to the business attributes; The business data is added to the business analysis unit corresponding to the business attribute according to the business attribute, so as to organize the business data and generate the organized business data.

3. The method for analyzing business data anomalies according to claim 1, characterized in that: The step of comparing the cleaned business data with the business data index to generate abnormal index data includes: Obtaining a threshold value of the business data indicator; The cleaned business data is compared with the threshold, and the cleaned business data that does not meet the threshold is used as the abnormal indicator data.

4. The method for analyzing business data anomalies according to claim 1, characterized in that: The attribution algorithm includes one or more of a propensity score matching method, a double difference method, a regression analysis method, a gradient-based attribution algorithm, and an attribution algorithm based on layer-by-layer back-propagation.

5. The method for analyzing business data anomalies according to any one of claims 1 to 4, characterized in that: The step of cleaning the sorted business data according to the business data indicators to generate cleaned business data comprises: Correct the collated business data according to the definition of the business data indicator to remove invalid, duplicate, missing or erroneous data; The remaining data is used as the cleaned business data.

6. The method for analyzing business data anomalies according to any one of claims 1 to 4, characterized in that: After the step of analyzing the abnormal indicator data based on the attribution algorithm to generate the abnormal cause, the method for analyzing business data abnormality further includes: Compare the abnormal cause with the business data indicator to generate auxiliary decision.

7. A device for analyzing abnormality of business data, characterized in that: include: A business data acquisition unit, used to acquire business data; A business analysis model building unit, used to build a business analysis model; A business analysis model unit, used to organize the business data according to the business analysis model to generate organized business data; An indicator acquisition unit, used to acquire business data indicators; The abnormal data analysis unit is used to clean the sorted business data according to the business data indicators to generate cleaned business data, compare the cleaned business data with the business data indicators to generate abnormal indicator data, analyze the abnormal indicator data based on the attribution algorithm, and generate the cause of the abnormality.

8. The business data anomaly analysis device according to claim 7, characterized in that: The abnormal data analysis unit is also used to compare the abnormal cause with the business data indicator to generate an auxiliary decision.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a program, and when the processor executes the program, the steps of the method for analyzing business data anomalies as described in any one of claims 1 to 6 are implemented.

10. A readable storage medium, characterized in that: A program or instruction is stored thereon, and when the program or the instruction is executed, the steps defined in the method for analyzing business data anomalies as described in any one of claims 1 to 6 are implemented.

Images