Business supervision and inspection data extraction method and device, equipment, medium and product

Abstract

The invention discloses a business supervision and inspection data extraction method and device, equipment, a medium and a product, and relates to the technical field of data sampling inspection, and the method comprises the steps: obtaining error-prone data and conventional data of a second terminal; obtaining a first extraction proportion between the extraction proportion and the error-prone data according to a pre-sampling inspection rule, and determining a first extraction number according to the first extraction proportion and the data size of the error-prone data; obtaining a second extraction proportion between the extraction proportion and preset conventional data according to a conventional sampling inspection rule, and determining a second extraction quantity according to the second extraction proportion and the data quantity of the conventional data; and determining a total extraction quantity according to the first extraction quantity and the second extraction quantity, if the total extraction quantity is not an integer, updating the total extraction quantity according to a preset extraction quantity average value to obtain a new total extraction quantity, and performing data extraction on the text data according to the new total extraction quantity. According to the invention, the business supervision check data extraction balance is enhanced.

Description

Technical Field

[0001] The present application relates to the field of data sampling technology, and in particular to methods, devices, equipment, media and products for extracting business supervision and inspection data. Background Art

[0002] In the financial industry, business supervision and inspection is an important part of ensuring business compliance and risk control, and data extraction and testing is an important means of business supervision and inspection. The traditional data extraction mechanism only ensures that the actual number of extracted data in the branch + business dimension is greater than or equal to 1. Some branch terminal-related business data has always occurred at a low frequency, but it is extracted by default due to the above principles, resulting in the actual extraction ratio being much higher than the expected extraction ratio, and thus has always been at a high extraction level. Even if data is randomly extracted under the user + institution dimension, there is still a probability that some branch terminals or some business data actually have business data but cannot be extracted. With the increase in the amount of business data and the diversification of business data types, this method of randomly sorting and extracting after calculating the number of extracts to be extracted cannot effectively cover all terminals and all data, resulting in an imbalance in the extraction of business, institutions, and users and insufficient fairness. Summary of the invention

[0003] The main purpose of this application is to provide a business supervision and inspection data extraction method, device, equipment, medium and product, aiming to solve the technical problem of imbalance in business supervision and inspection data extraction.

[0004] To achieve the above purpose, the present application proposes a business supervision and inspection data extraction method, which is applied to a first terminal corresponding to the head office, the first terminal is connected to a second terminal corresponding to a plurality of branches, and a first processor for running a pre-sampling rule and a second processor for running a conventional sampling rule are set in the first terminal, including:

[0005] Acquire text data of the second terminal, and determine error-prone data and regular data in the text data, wherein the text data includes business data, and an error rate of the error-prone data is greater than an error rate of the regular data;

[0006] Obtaining a first mapping relationship between a preset extraction ratio and preset error-prone data according to a pre-sampling rule running in the first processor, determining a first extraction ratio matching the error-prone data according to the first mapping relationship, and determining a first extraction quantity according to the first extraction ratio and the amount of the error-prone data;

[0007] Acquire a second mapping relationship between a preset extraction ratio and preset conventional data according to the conventional sampling rule running in the second processor, determine a second extraction ratio matching the conventional data according to the second mapping relationship, and determine a second extraction quantity according to the second extraction ratio and the data volume of the conventional data;

[0008] The total extraction number of the second terminal is determined based on the first extraction number and the second extraction number. If the total extraction number is a non-integer, the total extraction number is updated according to a preset extraction number average value to obtain a new total extraction number, and data extraction is performed on the text data according to the new total extraction number.

[0009] In one embodiment, the steps of obtaining a first mapping relationship between a preset extraction ratio and preset error-prone data according to a pre-sampling rule executed in a first processor, determining a first extraction ratio matching the error-prone data according to the first mapping relationship, and determining a first extraction quantity according to the first extraction ratio and the amount of the error-prone data include:

[0010] According to the pre-sampling rule, the error-prone data is layered to obtain layer information, and a first mapping relationship between the layer information and a preset extraction ratio is obtained;

[0011] The first extraction ratio information related to the hierarchical information is determined according to the first mapping relationship, and the first extraction quantity is determined according to the first extraction ratio information and the amount of error-prone data.

[0012] In one embodiment, the step of updating the total number of extractions according to a preset average number of extractions includes:

[0013] If the preset average of the number of draws is less than or equal to the total number of draws, the decimal part of the total number of draws is removed;

[0014] If the preset average of the number of draws is greater than the total number of draws, the decimal part of the total number of draws is removed and one is added to the integer part of the total number of draws.

[0015] In one embodiment, the step of extracting data from text data according to the new total extraction quantity includes:

[0016] Determine a plurality of preset extraction dimensions, wherein the extraction dimensions include an employee dimension, a network point dimension, and a branch dimension;

[0017] Data extraction is performed on the text data in sequence according to the extraction dimensions until the amount of extracted text data reaches a new total extraction amount.

[0018] In one embodiment, after the step of extracting data from the text data according to the new total extraction quantity, the method further includes:

[0019] Determine the job saturation according to the extracted quantity, wherein the extracted quantity includes a new total extraction quantity for data extraction of the text data;

[0020] If the job saturation is less than the preset saturation threshold, the text data is extracted again according to the preset priority extraction strategy, and the extracted quantity is updated according to the re-extracted text data;

[0021] The update operation saturation is calculated according to the updated extracted quantity. If the update operation saturation is less than the preset saturation threshold, the step of extracting a piece of data from the text data according to the preset priority extraction strategy is continued.

[0022] In one embodiment, the step of determining the operation saturation according to the extracted quantity includes:

[0023] If there is historically extracted text data corresponding to the second terminal within a preset time range before the current moment, determining the historically extracted quantity of the historically extracted text data;

[0024] The job saturation is determined based on the ratio of the total time spent processing the extracted quantity and the historically extracted quantity of text data to the total time of the time range.

[0025] In addition, to achieve the above purpose, the present application also proposes a business supervision and inspection data extraction device, which is arranged at a first terminal corresponding to the head office, and the first terminal is communicatively connected with second terminals corresponding to multiple branches, and the business supervision and inspection data extraction device includes:

[0026] A data acquisition module is used to acquire text data of the second terminal and determine error-prone data and regular data in the text data, wherein the text data includes business data and the error rate of the error-prone data is greater than the error rate of the regular data;

[0027] A first extraction quantity determination module is configured to obtain a first mapping relationship between a preset extraction ratio and preset error-prone data according to a pre-sampling rule running in the first processor, determine a first extraction ratio matching the error-prone data according to the first mapping relationship, and determine a first extraction quantity according to the first extraction ratio and the amount of the error-prone data;

[0028] A second extraction quantity determination module is configured to obtain a second mapping relationship between a preset extraction ratio and preset conventional data according to a conventional sampling rule executed in a second processor, determine a second extraction ratio matching the conventional data according to the second mapping relationship, and determine a second extraction quantity according to the second extraction ratio and the data volume of the conventional data;

[0029] The extraction balance module determines the total extraction number of the second terminal based on the first extraction number and the second extraction number. If the total extraction number is a non-integer, the total extraction number is updated according to a preset extraction number average value to obtain a new total extraction number, and data extraction is performed on the text data according to the new total extraction number.

[0030] In addition, to achieve the above-mentioned purpose, the present application also proposes a business supervision and inspection data extraction device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the business supervision and inspection data extraction method as described above.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the business supervision and inspection data extraction method as described above are implemented.

[0032] In addition, to achieve the above-mentioned purpose, the present application also provides a product, which is a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the business supervision and inspection data extraction method as described above are implemented.

[0033] One or more technical solutions proposed in this application have at least the following technical effects:

[0034] The present application is applied to a first terminal corresponding to a head office, the first terminal is communicatively connected with second terminals corresponding to a plurality of branches, a first processor for running a pre-sampling rule and a second processor for running a conventional sampling rule are arranged in the first terminal, text data of the second terminal is obtained, and error-prone data and conventional data in the text data are determined, wherein the text data includes business data, and the error rate of error-prone data is greater than the error rate of conventional data, and the sampling efficiency is significantly improved by classifying and processing the error-prone data and the conventional data; a first mapping relationship between a preset extraction ratio and preset error-prone data is obtained according to the pre-sampling rule running in the first processor, a first extraction ratio matching the error-prone data is determined according to the first mapping relationship, a first extraction quantity is determined according to the first extraction ratio and the data volume of the error-prone data, a second mapping relationship between a preset extraction ratio and preset conventional data is obtained according to the conventional sampling rule running in the second processor, a second extraction ratio matching the conventional data is determined according to the second mapping relationship, a second extraction quantity is determined according to the second extraction ratio and the data volume of the conventional data, and the sampling ratio and the extraction quantity are dynamically adjusted according to the classification and priority of the data, thereby achieving a precise balance of the sampling task. The total extraction quantity of the second terminal is determined based on the first extraction quantity and the second extraction quantity. If the total extraction quantity is not an integer, the total extraction quantity is updated according to a preset extraction quantity average value to obtain a new total extraction quantity. Data is extracted from the text data according to the new total extraction quantity. The total extraction quantity is balanced by using a preset extraction quantity average value, thereby ensuring the balance and fairness of the supervision work of each second terminal, avoiding imbalance in supervision effects due to excessive differences in extraction quantities, and enhancing the balance of data extraction for business supervision and inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is a flow chart of the first embodiment of the method for extracting business supervision and inspection data for this application;

[0038] Figure 2 This is a process diagram of Embodiment 2 of the method for extracting business supervision and inspection data for this application;

[0039] Figure 3 This is a process diagram of Embodiment 3 of the method for extracting business supervision and inspection data for this application;

[0040] Figure 4 This is a schematic diagram of the module structure of the business supervision and inspection data extraction device in the embodiment of the present application;

[0041] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the business supervision and inspection data extraction method in the embodiment of the present application.

[0042] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0044] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0045] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a terminal system, etc. The following takes the system as an example to illustrate this embodiment and the following embodiments.

[0046] Based on this, this embodiment provides a business supervision and inspection data extraction method, which is applied to a first terminal corresponding to the head office. The first terminal is communicatively connected to second terminals corresponding to multiple branches. A first processor that runs pre-sampling rules and a second processor that runs regular sampling rules are set in the first terminal.

[0047] It should be noted that, in this embodiment, the head office refers to the highest management body of a bank or financial institution, which is responsible for formulating overall strategies, policies and standards, and managing multiple branches under it. Correspondingly, the first terminal refers to the equipment or system used by the head office, which has the ability to communicate with the second terminals corresponding to multiple branches, and is used to receive, process and analyze data from each branch. The branch is a branch under the head office, which is responsible for providing financial services in a specific area or region, implementing the policies and standards of the head office, and reporting business conditions and data to the head office. The second terminal refers to the equipment or system used by each branch, which is responsible for generating, storing and transmitting data related to their respective businesses to the head office (i.e., the first terminal). The pre-sampling rules are a set of rules set in the first terminal, which are used to determine the sampling ratio and method when sampling error-prone data. The first processor is a device or module that runs these rules. The conventional sampling rules are another set of rules set in the first terminal, which are used to determine the sampling ratio and method when sampling conventional data. The second processor is a device or module that runs these rules.

[0048] In this embodiment, refer to Figure 1 , Figure 1 This is a flow chart of the business supervision and inspection data extraction method of this application. The business supervision and inspection data extraction method includes steps S10 to S40:

[0049] Step S10, acquiring text data of the second terminal, and determining error-prone data and regular data in the text data, wherein the text data includes business data, and the error rate of the error-prone data is greater than the error rate of the regular data;

[0050] It should be noted that text data is information stored in text form, including business data, etc., which is used for subsequent data processing and analysis. Error-prone data refers to the data part in text data that is more prone to errors or anomalies than other data, and its error rate is higher than that of regular data. Regular data refers to the data other than error-prone data in text data, and its error rate is relatively low.

[0051] Text data containing business data is obtained from the second terminal. This data may include various types of information, such as transaction records, user information, etc. In the obtained text data, error-prone data and regular data are distinguished. This process usually relies on a comprehensive analysis of multiple factors. For example, it can be calculated by historical error rate, that is, the error frequency of various types of information in previous data is analyzed, and the data types with frequent errors are marked as error-prone data. In addition, factors such as the format standardization of the data, the integrity of the fields, and the correlation with other data are also considered. These features are used to establish models or rules to automatically or manually classify and identify data, so as to more effectively distinguish error-prone data from regular data.

[0052] Step S20, obtaining a first mapping relationship between a preset extraction ratio and preset error-prone data according to a pre-sampling rule executed in the first processor, determining a first extraction ratio matching the error-prone data according to the first mapping relationship, and determining a first extraction quantity according to the first extraction ratio and the amount of the error-prone data;

[0053] It should be noted that the pre-sampling rule is a rule running in the first processor, which is used to determine the extraction ratio of different types of data (such as error-prone data). The extraction ratio is the ratio of sample data to the overall data when the sample data is extracted from the overall data. The first mapping relationship is the relationship between the error-prone data and the corresponding extraction ratio preset in the pre-sampling rule. The first extraction ratio is the extraction ratio that matches the error-prone data based on the first mapping relationship. The first extraction quantity is the actual number of samples extracted calculated based on the first extraction ratio and the amount of error-prone data.

[0054] The pre-sampling rule is run in the first processor to obtain a first mapping relationship between a preset sampling ratio and the error-prone data. According to the first mapping relationship, a first sampling ratio matching the error-prone data is determined. According to the first sampling ratio and the amount of the error-prone data, a first sampling quantity is calculated, that is, the number of samples to be extracted from the error-prone data.

[0055] Step S30, obtaining a second mapping relationship between a preset extraction ratio and preset conventional data according to the conventional sampling rule executed in the second processor, determining a second extraction ratio matching the conventional data according to the second mapping relationship, and determining a second extraction quantity according to the second extraction ratio and the data volume of the conventional data;

[0056] It should be noted that the conventional sampling rule is a rule running in the second processor, which is used to determine the extraction ratio of the conventional data. The second mapping relationship is the relationship between the conventional data and the corresponding extraction ratio preset in the conventional sampling rule. The second extraction ratio is the extraction ratio matched with the conventional data according to the second mapping relationship. The second extraction quantity is the actual number of samples extracted calculated according to the second extraction ratio and the data volume of the conventional data.

[0057] Run the conventional sampling rules in the second processor to obtain the second mapping relationship between the preset extraction ratio and the conventional data. This mapping relationship is usually pre-set based on multiple factors such as the importance of the data, the historical error rate, and business needs. For example, for conventional data with low error rates and small business impact, a lower extraction ratio can be set; while for data with low error rates but high business importance, a higher extraction ratio may be set. According to the second mapping relationship, combined with the specific conventional data type or feature, the second extraction ratio matching the conventional data is determined. When specifically determined, the system will look up the ratio value corresponding to the conventional data category in the mapping table, or directly calculate it through an algorithm. Next, according to the second extraction ratio and the data volume of the conventional data, the second extraction quantity is calculated, that is, the number of samples to be extracted from the conventional data. This calculation process is relatively direct, usually the total number of conventional data is multiplied by the second extraction ratio, and the result is the second extraction quantity. If the data volume of the conventional data is a dynamically changing value, the system will update this value in real time or regularly, and recalculate the second extraction quantity to ensure the accuracy and effectiveness of the sampling.

[0058] Step S40, determining the total extraction number of the second terminal based on the first extraction number and the second extraction number, if the total extraction number is a non-integer, updating the total extraction number based on a preset extraction number average value to obtain a new total extraction number, and extracting data from the text data based on the new total extraction number.

[0059] It should be noted that the total extraction number is the sum of the first extraction number and the second extraction number, indicating the total number of samples to be extracted from the text data. The extraction number average is a preset value used to update the total extraction number when the total extraction number is not an integer.

[0060] Add the first extraction quantity and the second extraction quantity to get the total extraction quantity. If the total extraction quantity is not an integer and has a decimal part, the total extraction quantity is updated using the preset extraction quantity average value, not only to ensure that the extraction quantity is an integer, but also to balance the extraction quantity by comparing the average value to avoid imbalance caused by too few or too many. According to the updated total extraction quantity, extract the corresponding amount of sample data from the text data. These sample data will be used for subsequent analysis or processing.

[0061] In this embodiment, the average value of the number of samples drawn refers to the monthly average supervision ratio of the whole bank, which is the ratio between the average value of the number of samples drawn by all branches in a certain month and the total number of samples included in the quality supervision data of the whole bank, and is used as a comparison benchmark to evaluate whether the supervision ratio of each branch is balanced. The total number of samples drawn is the monthly supervision ratio of the branch, which is the ratio between the number of samples drawn by a branch in a certain month and the total number of samples included in the quality supervision data of the branch, and is used to measure the supervision intensity of the branch. For each branch, the monthly number of samples drawn is divided by the total number of samples included in the quality supervision data of the branch, and the monthly supervision ratio of the branch is obtained. The sum of the monthly number of samples drawn by all branches of the bank is divided by the total number of samples included in the quality supervision data of the bank, and the monthly average supervision ratio of the bank is obtained. The monthly supervision ratio of each branch is compared with the monthly average supervision ratio of the whole bank to identify which branches have a higher or lower supervision ratio. It is worth noting that the monthly standard mentioned in this embodiment is T-2 days of the previous month + this month, and this setting is to ensure long-term extraction balance.

[0062] This embodiment is applied to a first terminal corresponding to a head office, and the first terminal is communicatively connected with second terminals corresponding to a plurality of branches. A first processor for running a pre-sampling rule and a second processor for running a conventional sampling rule are arranged in the first terminal, and text data of the second terminal is obtained, and error-prone data and conventional data in the text data are determined, wherein the text data includes business data, and the error rate of the error-prone data is greater than the error rate of the conventional data. By classifying and processing the error-prone data and the conventional data, the sampling efficiency is significantly improved; a first mapping relationship between a preset extraction ratio and preset error-prone data is obtained according to the pre-sampling rule running in the first processor, a first extraction ratio matching the error-prone data is determined according to the first mapping relationship, a first extraction quantity is determined according to the first extraction ratio and the data volume of the error-prone data, a second mapping relationship between a preset extraction ratio and preset conventional data is obtained according to the conventional sampling rule running in the second processor, a second extraction ratio matching the conventional data is determined according to the second mapping relationship, a second extraction quantity is determined according to the second extraction ratio and the data volume of the conventional data, and the sampling ratio and the extraction quantity are dynamically adjusted according to the classification and priority of the data, thereby achieving a precise balance of the sampling task. The total extraction quantity of the second terminal is determined based on the first extraction quantity and the second extraction quantity. If the total extraction quantity is not an integer, the total extraction quantity is updated according to a preset extraction quantity average value to obtain a new total extraction quantity. Data is extracted from the text data according to the new total extraction quantity. The total extraction quantity is balanced by using a preset extraction quantity average value, thereby ensuring the balance and fairness of the supervision work of each second terminal, avoiding imbalance in supervision effects due to excessive differences in extraction quantities, and enhancing the balance of data extraction for business supervision and inspection.

[0063] In a feasible implementation manner, the steps in step S20 may include steps T10 to T20:

[0064] Step T10, stratifying the error-prone data according to the pre-sampling rule to obtain hierarchical information, and obtaining a first mapping relationship between the hierarchical information and a preset extraction ratio;

[0065] It should be noted that hierarchical information is the result of classifying error-prone data into different levels or categories according to the pre-checking rules. These levels may be divided based on factors such as data error type, error frequency, and business impact.

[0066] First, according to the preset pre-sampling rules, the error-prone data is carefully analyzed. According to factors such as the error type, error frequency, and business impact of the data, the error-prone data is divided into different levels or categories. The purpose of this step is to classify data with similar characteristics into one category for subsequent targeted sampling. After the stratification is completed, according to the preset rules or strategies, an extraction ratio is set for the error-prone data of each level (or category). This ratio is obtained after comprehensive consideration of factors such as the error rate of the data at this level and the importance of the business. Finally, the first mapping relationship between the hierarchical information and the extraction ratio is formed to guide the subsequent data extraction work.

[0067] Step T20, determining first extraction ratio information with respect to the hierarchical information according to the first mapping relationship, and determining a first extraction quantity according to the first extraction ratio information and the amount of error-prone data.

[0068] It should be noted that the first extraction ratio information is all first extraction ratios determined for error-prone data of a specific level (or category) according to the first mapping relationship. These ratios determine how much data is extracted from the level as samples.

[0069] After determining the first mapping relationship, for each level (or category) of error-prone data, the corresponding extraction ratio can be found according to the mapping relationship. This ratio is the first extraction ratio information, which determines how much data is extracted from the level as a sample. After obtaining the first extraction ratio information, it is also necessary to know the amount of error-prone data at the level. Based on the extraction ratio and the amount of data, the number of samples that need to be extracted from the level can be calculated, that is, the first extraction number. This number will be used to guide subsequent data extraction operations to ensure that a sufficient number of sample data can be extracted from each level according to the predetermined ratio.

[0070] In this embodiment, by scientifically stratifying the error-prone data according to the pre-sampling rules and establishing the first mapping relationship between the hierarchical information and the preset extraction ratio, not only the detailed division of the error-prone data is achieved, but also the data at each level is ensured to receive reasonable sampling attention based on factors such as its error type, frequency, and business impact. Subsequently, based on the first mapping relationship, the first extraction ratio information of each level is accurately determined, and the first extraction quantity is calculated in combination with the data volume of the error-prone data. This process not only ensures the pertinence and effectiveness of the sampling work, but also realizes balanced sampling of error-prone data at different levels by dynamically adjusting the sampling ratio and quantity, effectively strengthening the balance of the sampling.

[0071] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction, and will not be repeated hereafter. On this basis, the steps of step S40 also include steps A10 to A20:

[0072] Step A10, if the preset average value of the number of draws is less than or equal to the total number of draws, then remove the decimal part of the total number of draws;

[0073] First, calculate or obtain the preset average number of draws and the total number of draws. These two values ​​may be determined based on a variety of factors such as the total amount of data, the characteristics of the data, and the needs of sampling. Then, compare the two values. If the preset average number of draws is less than or equal to the total number of draws, directly remove the decimal part of the total number of draws and retain its integer part.

[0074] In this embodiment, the calculated monthly supervision ratio of the branch is compared with the monthly average supervision ratio of the whole bank to obtain a comparison result, which is divided into two types: the monthly supervision ratio of the branch is greater than the monthly average supervision ratio of the whole bank, or the monthly supervision ratio of the branch is less than or equal to the monthly average supervision ratio of the whole bank. If the monthly supervision ratio of the branch is greater than the monthly average supervision ratio of the whole bank, it means that the branch is relatively frequent in the sampling of this business type. If the number to be sampled has a decimal part, the decimal part is directly discarded and the integer part is taken as the actual number to be sampled.

[0075] Step A20: If the preset average value of the number of draws is greater than the total number of draws, remove the decimal part of the total number of draws and add one to the integer part of the total number of draws.

[0076] In this embodiment, if the monthly supervision ratio of a branch is less than or equal to the monthly average supervision ratio of the whole bank, it means that the branch is relatively insufficient in the sampling inspection of this business type. In order to increase the coverage of the sampling inspection, if the number to be sampled has a decimal part, the decimal part is discarded and the integer part is added by 1 as the actual number of samples. However, in either case, it must be ensured that the number of samples is greater than or equal to 1, so as to ensure that at least one sample of each business type is sampled for monitoring in each branch.

[0077] For example, refer to Figure 2 , Figure 2 This is a process diagram of the second embodiment. The system will first extract and balance the text data by business type, use the pre-sampling rule to obtain the first extraction quantity, use the conventional sampling rule to obtain the second extraction quantity, add the first extraction quantity and the second extraction quantity to obtain the total extraction quantity, and compare it with the average extraction quantity. If the total extraction quantity is greater than the average extraction quantity, the truncation method is used, that is, the decimal part of the total extraction quantity is removed. If the total extraction quantity is less than or equal to the average extraction quantity, the addition method is used, that is, the decimal part of the total extraction quantity is removed and the integer part is retained. Then, one is added to the integer part of the total extraction quantity.

[0078] In this embodiment, when the preset average value of the number of draws is less than or equal to the total number of draws, the decimal part of the total number of draws is directly removed to ensure that no excessive draws are made. When the preset average value of the number of draws is greater than the total number of draws, the decimal part is removed and one is added to the integer part, which not only ensures the integrity of the number of draws, but also increases the coverage of the random inspection, especially in the case of relatively insufficient random inspections, effectively improving the balance and comprehensiveness of the random inspections.

[0079] In a feasible implementation manner, step S40 further includes steps B10 to B20:

[0080] Step B10, determining a plurality of preset extraction dimensions, wherein the extraction dimensions include an employee dimension, a network point dimension, and a branch dimension;

[0081] It should be noted that, in the data extraction process, the extraction dimension is used to determine the standard or classification of the direction and scope of data extraction. In the present embodiment, the extraction dimension includes the employee dimension, the outlet dimension and the branch dimension, which respectively represent data extraction from three different angles of employees, outlets and branches. The employee dimension refers to the dimension in which data is extracted based on employees. Under this dimension, data extraction may involve employees' work performance, performance data, etc. The outlet dimension refers to the dimension in which data is extracted based on outlets (such as bank outlets, sales outlets, etc.). Under this dimension, data extraction may involve the operation of outlets, the number of customers, the transaction volume, etc. The branch dimension refers to the dimension in which data is extracted based on branches (such as bank branches, company branches, etc.). Under this dimension, data extraction may involve the overall performance, market share, customer structure, etc. of the branch.

[0082] The system can first determine the key data in the extracted dimensions to determine the distribution of the extracted data in each dimension. For example, according to the preset time period (such as last month + T-2 of this month), calculate the monthly supervision ratio of all business types of each branch employee and the monthly supervision ratio of a single business type of each outlet. This usually involves the collation and analysis of historical data, including the business volume of employees and outlets in different business types, the number of extracted supervisions, etc.

[0083] Step B20, extracting text data in sequence according to the extraction dimensions until the amount of extracted text data reaches a new total extraction amount.

[0084] After determining the extraction dimensions, it is necessary to extract data from the text data in sequence according to these dimensions. In this embodiment, a rolling extraction method is adopted according to a preset priority strategy. According to the monthly supervision ratio of all business types, the data of employees whose monthly supervision ratio of all business types is zero are preferentially extracted; at the same time, according to the monthly supervision ratio of a single business type, the data of outlets whose monthly supervision ratio of a single business type is zero are preferentially extracted. This helps to make up for the lack of supervision of these employees and outlets. After the priority extraction, if the amount of data extracted has not reached the balanced extraction amount, the data of employees whose monthly supervision ratio of all business types is lower than the average of the whole bank, and the data of outlets whose monthly supervision ratio of a single business type is lower than the average of the whole bank are extracted. This helps to balance the overall supervision ratio and reduce the imbalance of extraction.

[0085] During the data extraction process, the amount of text data that has been extracted needs to be constantly monitored. When the amount of text data that has been extracted reaches a preset new total extraction amount, the data extraction process ends.

[0086] For example, assuming that the preset time period is last month + T-2 days of this month, when data is extracted on October 15, the time period is from September 1 to October 13. If the average monthly supervision ratio of all business types in the bank is 5% at this time. A branch has employees A and B. The monthly supervision ratio of all business types of employee A is 0% (that is, no business was extracted for supervision last month), and the ratio of employee B is 3% (lower than the average of the whole bank). At the same time, the branch has outlets A and B. The monthly supervision ratio of a single business type of outlet A is 0%, and the ratio of outlet B is 4% (lower than the average of the whole bank). When extracting data with balanced extraction volume, the data of employee A and outlet A will be extracted first to make up for their lack of supervision. Then, the data of employee B and outlet B will be extracted to balance the overall supervision ratio. In the whole process, it is necessary to ensure that each employee and outlet has at least a certain amount of business extracted for supervision.

[0087] In this embodiment, by determining multiple extraction dimensions such as employee dimension, outlet dimension and branch dimension, the direction and scope of data extraction are clarified, making data extraction more accurate and comprehensive. According to these dimensions, the text data is extracted in turn, and the priority strategy is adopted for rolling extraction, which not only makes up for the lack of supervision of employees and outlets, but also balances the overall supervision ratio and reduces the imbalance of extraction. At the same time, by continuously monitoring the amount of extracted data, the timeliness and accuracy of the data extraction process are ensured. This refined data extraction strategy not only improves the efficiency of data extraction, but also provides more reliable and accurate data support for subsequent data analysis and decision-making.

[0088] Based on the first or second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first or second embodiment can be referred to the above introduction, and will not be described in detail later. Step S40 also includes steps C10 to C30:

[0089] Step C10, determining the job saturation according to the extracted quantity, wherein the extracted quantity includes a new total extracted quantity for data extraction of the text data;

[0090] It should be noted that the job saturation is a measure of the ratio of extracted data to the total text data within a specified time range, which is used to measure the progress and efficiency of the current extraction work. The extracted quantity is the total amount of data that has been successfully extracted at a certain point in the process of extracting text data.

[0091] The job saturation can be obtained by dividing the amount of data extracted from the entire row (including the results of the first round of extraction) by the total amount of data that can be extracted from the entire row.

[0092] Step C20, if the operation saturation is less than the preset saturation threshold, extract the text data again according to the preset priority extraction strategy, and update the extracted quantity according to the re-extracted text data;

[0093] It should be noted that the saturation threshold is a preset job saturation value used to determine whether a second round of extraction is needed. When the job saturation is lower than the saturation threshold, it indicates that the current extraction work has not yet reached the predetermined goal and a second round of extraction is required. The priority extraction strategy is a strategy that determines the order of data extraction based on specific rules or conditions (such as data importance, time order, etc.).

[0094] The job saturation is compared with a preset saturation threshold. The saturation threshold is usually determined based on business requirements, resource constraints, and other factors. In this embodiment, the saturation threshold can be 100%. If the job saturation is lower than the saturation threshold, it means that the current extraction work has not yet reached the predetermined goal, and a second round of extraction is required. According to the preset priority extraction strategy (such as extracting business types with serious problems first, extracting branches with larger data volumes first, etc.), a second round of extraction is performed in the remaining data.

[0095] Step C30, calculating the update operation saturation according to the updated extracted quantity, if the update operation saturation is less than the preset saturation threshold, then continuing to execute the step of extracting a piece of data from the text data according to the preset priority extraction strategy.

[0096] Each time data is extracted according to the priority extraction strategy, the system will update the extracted quantity, that is, increase the amount of newly extracted data. Then, the system will recalculate the job saturation based on the updated extracted quantity. The system will again determine whether the updated job saturation is less than the saturation threshold. If it is still less than the saturation threshold, the system will continue to extract the next piece of data from the text data according to the preset priority extraction strategy, and repeat the above steps until the job saturation reaches or exceeds the saturation threshold.

[0097] For example, refer to Figure 3 , Figure 3 : is a schematic diagram of the process of the third embodiment. After the business type extraction balance is performed, the system will perform saturation measurement. If the saturation is less than the saturation threshold, the system will make up the extraction according to the priority extraction strategy. The priority extraction strategy is as follows: Figure 3As shown, it is divided into the branch employee dimension A1. Draw 1 more transaction from the branch with 0 business number, A2. Draw 1 more transaction from the employee with 0 business number, and the business dimension B1. Draw 1 more transaction from the branch with the highest error rate last month, B2. Draw 1 more transaction from the branch with high risk. The priority extraction strategy extracts comprehensively based on these two dimensions and runs in the following priority order: A1+B1, A1+B2, A1, A2+B1, A2+B2, A2. The saturation is calculated each time the extraction is done until the saturation threshold is reached.

[0098] In this embodiment, the operation saturation is determined according to the extracted quantity, which can reflect the progress of the data extraction work in real time and provide a reliable basis for subsequent operations. When the operation saturation is less than the preset saturation threshold, the text data is extracted again according to the preset priority extraction strategy, which not only ensures the comprehensiveness of data extraction, but also improves the pertinence of data extraction. By continuously updating the extracted quantity and operation saturation, and continuously extracting data according to the priority extraction strategy until the operation saturation reaches or exceeds the saturation threshold, this circulation mechanism ensures the continuity and integrity of the data extraction work. This data extraction strategy not only improves the efficiency of data extraction, but also ensures the balance of data extraction.

[0099] In a feasible implementation manner, step C10 further includes steps D10 to D20:

[0100] Step D10, if there is historically extracted text data corresponding to the second terminal within a preset time range before the current moment, determining the historically extracted quantity of the historically extracted text data;

[0101] It should be noted that historically extracted text data refers to text data that has been extracted or processed and is related to a specific terminal (the second terminal in this example) in a certain period of time in the past. The number of historical extractions refers to the total number of text data extracted for a specific terminal in the above historical period of time.

[0102] First, clarify the time range of the analysis, such as selecting a certain month or quarter as the analysis period to determine whether the data extraction has reached saturation. Then, through the bank's data system or database, query and obtain the historical extracted text data that has been extracted and processed by the entire bank within the time range, so as to obtain the historical extraction quantity.

[0103] Step D20, determining the job saturation according to the ratio of the total time taken to process the extracted quantity and the historically extracted quantity of text data to the total time of the time range.

[0104] It should be noted that the total time is the total time it takes to complete the amount of data extracted from the entire row. The total time is the total duration within a specified time range, such as 24 hours a day, the number of days in a month multiplied by the number of hours per day, etc. Job saturation is a measure of the ratio of the workload of processing data to the total available time within a specified time range, reflecting the ability and efficiency of processing data.

[0105] By recording or estimating the total time spent on processing the extracted amount and the historically extracted amount of text data, in this embodiment, the total time can be obtained by multiplying the amount of extracted data in the entire row by the standard time (the average time to complete a piece of business data), and then divided by the total time of the time range (the number of days or seconds in the time range) to obtain job saturation.

[0106] For example, assuming that the time range is the 5 working days before the sampling day (including today), and the total time is in seconds, then the total time for the entire bank's extracted data is equal to the entire bank's extracted data in these 5 working days multiplied by the standard time, and the total time for the time range is equal to 5 multiplied by 3600 (seconds). Finally, the job saturation = the entire bank's extracted data * standard time / 5 / 3600.

[0107] In this embodiment, by querying and determining the historically extracted text data and the historically extracted quantity corresponding to the second terminal, an important reference is provided for evaluating the saturation of the current data extraction work. By calculating the ratio of the total time spent processing the text data of the extracted quantity and the historically extracted quantity to the total time of the time range, the job saturation is accurately measured. This indicator intuitively reflects the actual load and efficiency of the data processing work within the specified time range, which helps to balance the long-term supervision ratio and reduce the imbalance of extraction.

[0108] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the business supervision and inspection data extraction method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0109] This application also provides a business supervision and inspection data extraction device, please refer to Figure 4 , the business supervision and inspection data extraction device includes:

[0110] The data acquisition module 10 acquires text data of the second terminal and determines error-prone data and regular data in the text data, wherein the text data includes business data and the error rate of the error-prone data is greater than the error rate of the regular data;

[0111] A first extraction quantity determination module 20 obtains a first mapping relationship between a preset extraction ratio and preset error-prone data according to a pre-sampling rule running in the first processor, determines a first extraction ratio matching the error-prone data according to the first mapping relationship, and determines a first extraction quantity according to the first extraction ratio and the amount of the error-prone data;

[0112] The second extraction quantity determination module 30 obtains a second mapping relationship between a preset extraction ratio and preset conventional data according to the conventional sampling rule running in the second processor, determines a second extraction ratio matching the conventional data according to the second mapping relationship, and determines a second extraction quantity according to the second extraction ratio and the data volume of the conventional data;

[0113] The extraction balance module 40 determines the total extraction number of the second terminal based on the first extraction number and the second extraction number. If the total extraction number is not an integer, the total extraction number is updated according to a preset extraction number average value to obtain a new total extraction number, and data extraction is performed on the text data according to the new total extraction number.

[0114] The business supervision and inspection data extraction device provided by the present application adopts the business supervision and inspection data extraction method in the above embodiment, which can solve the technical problem of imbalanced business supervision and inspection data extraction. Compared with the prior art, the beneficial effects of the business supervision and inspection data extraction device provided by the present application are the same as the beneficial effects of the business supervision and inspection data extraction method provided by the above embodiment, and other technical features in the business supervision and inspection data extraction device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0115] The present application provides a business supervision and inspection data extraction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the business supervision and inspection data extraction method in the above-mentioned embodiment one.

[0116] Reference below Figure 5, which shows a schematic diagram of the structure of a business supervision and inspection data extraction device suitable for implementing the embodiment of the present application. The business supervision and inspection data extraction device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The business supervision and inspection data extraction 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.

[0117] like Figure 5 As shown, the business supervision and inspection data extraction device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the business supervision and inspection data extraction device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the business supervision and inspection data extraction device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a business supervision and inspection data extraction device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0118] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0119] The business supervision and inspection data extraction device provided by the present application adopts the business supervision and inspection data extraction method in the above embodiment, which can solve the technical problem of imbalanced business supervision and inspection data extraction. Compared with the prior art, the beneficial effects of the business supervision and inspection data extraction device provided by the present application are the same as the beneficial effects of the business supervision and inspection data extraction method provided by the above embodiment, and other technical features in the business supervision and inspection data extraction device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0120] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0121] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0122] The present application provides a medium, which is a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the business supervision and inspection data extraction method in the above-mentioned embodiment.

[0123] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0124] The above-mentioned computer-readable storage medium may be included in the business supervision and inspection data extraction device; or it may exist independently without being assembled into the business supervision and inspection data extraction device.

[0125] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the business supervision and inspection data extraction device, the business supervision and inspection data extraction device:

[0126] The number of items to be extracted is determined from the quality control data of the branch through preset extraction rules, wherein the quality control data belongs to the same business category, and the extraction rules include pre-extraction rules and regular extraction rules. The pre-extraction rules include stratifying the quality control data according to the severity of the problem and determining the number of items to be extracted according to different proportions at different levels, and the regular extraction rules include determining the number of items to be extracted according to preset proportions in the quality control data;

[0127] Determine the monthly supervision ratio of the branch according to the number to be drawn, and compare the monthly supervision ratio of the branch with the monthly average supervision ratio of the whole bank to obtain the comparison result. According to the comparison result, use the preset balance rule to process the corresponding number of draws to obtain the balanced draw quantity, conduct the first round of draws in the quality supervision data, and extract the data of the balanced draw quantity, among which the monthly supervision ratio of the branch is the ratio of the number to be drawn to the amount of quality supervision data included, and the balance rule includes the truncation method and the round-up method;

[0128] The operation saturation is determined based on the amount of data extracted from the entire bank. If the operation saturation is lower than the preset saturation threshold, a second round of extraction is performed according to the preset priority extraction strategy, where the amount of data extracted from the entire bank includes the amount of data that has been extracted from all banks within a preset time range.

[0129] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0131] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0132] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned business supervision and inspection data extraction method, and can solve the technical problem of imbalanced business supervision and inspection data extraction. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the business supervision and inspection data extraction method provided by the above-mentioned embodiment, and will not be repeated here.

[0133] The present application also provides a product, which is a computer program product, including a computer program, which implements the steps of the business supervision and inspection data extraction method as described above when the computer program is executed by a processor.

[0134] The computer program product provided by this application can solve the technical problem of unbalanced business supervision and inspection data extraction. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the business supervision and inspection data extraction method provided by the above embodiment, which will not be repeated here.

[0135] The above are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for extracting business supervision and inspection data, characterized in that: Applied to a first terminal corresponding to a head office, the first terminal is in communication connection with second terminals corresponding to a plurality of branches, a first processor for running a pre-sampling rule and a second processor for running a conventional sampling rule are arranged in the first terminal, and the business supervision and inspection data extraction method includes: Acquire text data of the second terminal, and determine error-prone data and regular data in the text data, wherein the text data includes business data, and an error rate of the error-prone data is greater than an error rate of the regular data; Acquire a first mapping relationship between a preset extraction ratio and preset error-prone data according to the pre-sampling rule running in the first processor, determine a first extraction ratio matching the error-prone data according to the first mapping relationship, and determine a first extraction quantity according to the first extraction ratio and the amount of the error-prone data; Acquire a second mapping relationship between a preset extraction ratio and preset conventional data according to the conventional sampling rule running in the second processor, determine a second extraction ratio matching the conventional data according to the second mapping relationship, and determine a second extraction quantity according to the second extraction ratio and the data volume of the conventional data; The total extraction number of the second terminal is determined based on the first extraction number and the second extraction number. If the total extraction number is not an integer, the total extraction number is updated according to a preset extraction number average value to obtain a new total extraction number, and data extraction is performed on the text data according to the new total extraction number.

2. The business supervision and inspection data extraction method according to claim 1, characterized in that: The steps of obtaining a first mapping relationship between a preset extraction ratio and preset error-prone data according to the pre-sampling rule running in the first processor, determining a first extraction ratio matching the error-prone data according to the first mapping relationship, and determining a first extraction quantity according to the first extraction ratio and the amount of the error-prone data include: According to the pre-sampling rule, the error-prone data is layered to obtain layer information, and a first mapping relationship between the layer information and a preset extraction ratio is obtained; The first extraction ratio information of the hierarchical information is determined according to the first mapping relationship, and the first extraction quantity is determined according to the first extraction ratio information and the data amount of the error-prone data.

3. The business supervision and inspection data extraction method according to claim 1, characterized in that: The step of updating the total extraction quantity according to the preset extraction quantity average value comprises: If the preset average value of the number of draws is less than or equal to the total number of draws, then the decimal part of the total number of draws is removed; If the preset average value of the number of extractions is greater than the total number of extractions, the decimal part of the total number of extractions is removed, and one is added to the integer part of the total number of extractions.

4. The business supervision and inspection data extraction method according to claim 1, characterized in that: The step of extracting data from the text data according to the new total extraction quantity comprises: Determine a plurality of preset extraction dimensions, wherein the extraction dimensions include an employee dimension, a network point dimension, and a branch dimension; Data extraction is performed on the text data in sequence according to the extraction dimensions until the amount of the extracted text data reaches the new total extraction amount.

5. The business supervision and inspection data extraction method according to claim 1, characterized in that: After the step of extracting data from the text data according to the new total extraction quantity, the method further comprises: Determining the job saturation according to the extracted quantity, wherein the extracted quantity includes a new total extracted quantity for data extraction of the text data; If the job saturation is less than a preset saturation threshold, extracting the text data again according to a preset priority extraction strategy, and updating the extracted quantity according to the re-extracted text data; The update operation saturation is calculated according to the updated extracted quantity. If the update operation saturation is less than a preset saturation threshold, the step of extracting a piece of data from the text data according to the preset priority extraction strategy is continued.

6. The method for extracting business supervision and inspection data according to claim 5, characterized in that: The step of determining the operation saturation according to the extracted quantity comprises: If there is historically extracted text data corresponding to the second terminal within a preset time range before the current moment, determining the historically extracted quantity of the historically extracted text data; The job saturation is determined according to the ratio of the total time taken to process the extracted quantity and the historically extracted quantity of text data to the total time of the time range.

7. A business supervision and inspection data extraction device, characterized in that: The first terminal is arranged at a first terminal corresponding to the head office, and the first terminal is connected to a second terminal corresponding to a plurality of branches in communication. The business supervision and inspection data extraction device comprises: A data acquisition module is used to acquire text data of the second terminal and determine error-prone data and regular data in the text data, wherein the text data includes business data and the error rate of the error-prone data is greater than the error rate of the regular data; a first extraction quantity determination module, which obtains a first mapping relationship between a preset extraction ratio and preset error-prone data according to a pre-sampling rule running in the first processor, determines a first extraction ratio matching the error-prone data according to the first mapping relationship, and determines a first extraction quantity according to the first extraction ratio and the amount of the error-prone data; a second extraction quantity determination module, which obtains a second mapping relationship between a preset extraction ratio and preset conventional data according to a conventional sampling rule running in the second processor, determines a second extraction ratio matching the conventional data according to the second mapping relationship, and determines a second extraction quantity according to the second extraction ratio and the data volume of the conventional data; The extraction balance module determines the total extraction number of the second terminal according to the first extraction number and the second extraction number. If the total extraction number is a non-integer, the total extraction number is updated according to a preset extraction number average value to obtain a new total extraction number, and the text data is extracted according to the new total extraction number.

8. A business supervision and inspection data extraction device, characterized in that: The business supervision and inspection data extraction device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the business supervision and inspection data extraction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the business supervision and inspection data extraction method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the business supervision and inspection data extraction method as described in any one of claims 1 to 6 are implemented.

Images