Business monitoring method and device, and computer device

Abstract

The application relates to a business supervision method and device and computer equipment. The method comprises the following steps: performing attribute clustering processing on a plurality of to-be-supervised enterprises according to enterprise data of the plurality of to-be-supervised enterprises, obtaining a clustering result, determining a supervision priority of each to-be-supervised enterprise according to the clustering result in the case that a measurement index value of the clustering result meets a standard, and supervising a target resource business of each to-be-supervised enterprise according to the clustering result and the supervision priority. The above method can determine the supervision priority of each to-be-supervised enterprise according to the clustering result in the case that the measurement index value of the attribute clustering result of the plurality of to-be-supervised enterprises meets the standard, so that the determined supervision priority of each to-be-supervised enterprise is more accurate, the target resource business of each to-be-supervised enterprise is effectively supervised based on the obtained supervision priority of different to-be-supervised enterprises, and the timeliness of supervising the target resource business of different to-be-supervised enterprises is improved.

Description

Technical Field

[0001] This application relates to the field of business management technology, and in particular to a business supervision method, apparatus and computer equipment. Background Technology

[0002] With the development of the Internet, big data technology has been widely applied to various business operations of enterprises, such as finance, telecommunications, e-commerce, and construction.

[0003] Taking financial services as an example, the financial operations of various enterprises may involve certain risks. Therefore, in order to reduce the incidence of risks, it is particularly important to regulate the financial services of these enterprises. Related technologies primarily utilize the financial big data of each enterprise to regulate its financial operations, thereby improving the regulatory capacity for financial services.

[0004] However, the relevant technologies may result in untimely supervision when regulating the financial business of various enterprises. Summary of the Invention

[0005] Therefore, it is necessary to provide a business supervision method, device, and computer equipment to address the aforementioned technical issues, enabling timely supervision of the financial business of various enterprises.

[0006] In a first aspect, embodiments of this application provide a business supervision method, the method comprising:

[0007] Based on enterprise data from multiple enterprises awaiting regulation, attribute clustering was performed on these enterprises to obtain clustering results.

[0008] If the clustering results meet the target metrics, the regulatory priority for each enterprise to be regulated will be determined based on the clustering results.

[0009] Based on the clustering results and regulatory priorities, the target resource businesses of each enterprise to be regulated are subject to regulation.

[0010] The technical solution in this application embodiment performs attribute clustering processing on multiple enterprises to be regulated based on their enterprise data, obtaining clustering results. If the measurement index values ​​of the clustering results meet the standards, the regulatory priority of each enterprise to be regulated is determined based on the clustering results. Then, based on the clustering results and each regulatory priority, the target resource business of each enterprise to be regulated is regulated. This method determines the regulatory priority of each enterprise to be regulated only when the measurement index values ​​of the attribute clustering results of multiple enterprises to be regulated meet the standards, making the determined regulatory priorities of each enterprise to be regulated more accurate. Furthermore, based on the obtained regulatory priorities of different enterprises to be regulated, the regulatory priorities of each enterprise to be regulated are further adjusted. Effective supervision of target resource businesses can improve the timeliness of supervision over different enterprises seeking supervision. Furthermore, the above method requires no additional operations and can promptly process the target resource businesses of different enterprises based on their supervisory priorities, thereby reducing the cost of target resource business supervision. Moreover, the method can also conduct real-time supervision of the target resource businesses of each enterprise seeking supervision according to their supervisory priorities, enabling proactive risk prevention and reducing the risk rate of such risks. Additionally, the method has no limitations on the magnitude of changes in enterprise data, thus expanding the application scenarios for target resource business supervision.

[0011] In one embodiment, based on enterprise data from multiple enterprises to be regulated, attribute clustering is performed on the multiple enterprises to be regulated to obtain clustering results, including:

[0012] The enterprise data of multiple enterprises to be regulated are input into a second-order clustering model to perform attribute clustering processing on multiple enterprises to obtain clustering results.

[0013] The technical solution in this application embodiment inputs enterprise data of multiple enterprises to be regulated into a second-order clustering model to perform attribute clustering processing on the multiple enterprises to be regulated to obtain clustering results. The above method can perform attribute clustering processing on multiple enterprises to be regulated to obtain clustering results, providing reference information for accurately determining the regulatory priority of each enterprise to be regulated in the future. At the same time, the second-order clustering model in the above method can be applied to scenarios with large amounts of data. The above process uses the second-order clustering model to perform attribute clustering processing, which can not only improve the efficiency of attribute clustering processing, but also the second-order clustering model has strong robustness to data, which can improve the accuracy of clustering results.

[0014] In one embodiment, enterprise data from multiple enterprises to be regulated are input into a second-order clustering model to perform attribute clustering processing on the multiple enterprises to be regulated, resulting in clustering results, including:

[0015] Based on multiple enterprise operation evaluation indicators, the enterprise data of each enterprise to be regulated is clustered to obtain the indicator data of different enterprise operation evaluation indicators for each enterprise to be regulated.

[0016] Based on multiple different enterprise attribute parameters, the indicator data of different enterprise operation evaluation indicators corresponding to each enterprise to be regulated are subjected to secondary clustering processing to obtain clustering results.

[0017] The technical solution in this application embodiment performs a first clustering process on the enterprise data of each enterprise to be regulated based on multiple enterprise operation evaluation indicators, obtaining indicator data for each enterprise to be regulated corresponding to different enterprise operation evaluation indicators. Then, based on multiple different enterprise attribute parameters, a second clustering process is performed on the indicator data for each enterprise to be regulated corresponding to different enterprise operation evaluation indicators to obtain the clustering result. This method simplifies the complex problem through two clustering processes, providing reference information for accurately determining the regulatory priority of each enterprise to be regulated. Simultaneously, this method does not require complex algorithms, making the processing relatively simple, thus reducing the complexity of the second-order clustering process and improving its speed and efficiency. Furthermore, this method allows for flexible adjustment of enterprise operation evaluation indicators and enterprise attribute parameters, making the application scenarios of attribute clustering more flexible.

[0018] In one embodiment, the method further includes:

[0019] Obtain the performance metrics for the clustering results; the performance metrics include the performance metrics of the clustering model used for attribute clustering and / or the quality metrics of the clustering results.

[0020] If the performance measurement index value is less than the first preset threshold, and / or the quality measurement index value is greater than the second preset threshold, then the measurement index value of the clustering result is determined to meet the standard.

[0021] The technical solution in this application embodiment obtains the performance measurement index value of the clustering model used for attribute clustering processing and / or the quality measurement index value of the clustering result. If the performance measurement index value is less than a first preset threshold and / or the quality measurement index value is greater than a second preset threshold, then it is determined that the measurement index value of the clustering result meets the standard. The above method does not require the participation of complex algorithms, the processing process is relatively simple, it can improve the speed of determining whether the measurement index value of the clustering result meets the standard, and on this basis, it can provide a reference for accurately determining the regulatory priority of each enterprise to be regulated.

[0022] In one embodiment, the clustering results include multiple cluster categories; the regulatory priority of each enterprise to be regulated is determined based on the clustering results, including:

[0023] Obtain the number of enterprises with at least one enterprise to be regulated in each cluster category;

[0024] Sort the number of each enterprise and obtain the sorting results;

[0025] Based on the ranking results, the regulatory priority of each enterprise to be regulated is determined; among them, different enterprises to be regulated in the same cluster have the same regulatory priority.

[0026] The technical solution in this application embodiment obtains the number of enterprises to be regulated in each cluster category of the clustering results, sorts the number of enterprises to obtain the sorting results, and determines the regulatory priority of each enterprise to be regulated based on the sorting results. Among them, different enterprises to be regulated in the same cluster category have the same regulatory priority. The above method does not require the participation of complex algorithms, the processing process is relatively simple, it can improve the speed of determining the regulatory priority of each enterprise to be regulated, and on this basis, it can provide a reference for timely supervision of the target resource business of each enterprise to be regulated.

[0027] In one embodiment, the regulatory priority of each enterprise to be regulated is determined based on the ranking results, including:

[0028] Based on the ranking of the number of companies in the results from largest to smallest, each company to be regulated is assigned a regulatory priority from highest to lowest.

[0029] The technical solution in this embodiment assigns a regulatory priority from high to low to each enterprise to be regulated in descending order of the number of enterprises in the sorting results. The processing in the above method is relatively simple and requires manual intervention, which can improve the speed and efficiency of assigning regulatory priorities, reduce human intervention errors, and improve the accuracy of the assigned regulatory priorities.

[0030] In one embodiment, the target resource business of each enterprise to be regulated is regulated based on clustering results and regulatory priorities, including:

[0031] The target resource businesses of each enterprise to be regulated will be regulated in descending order of regulatory priority.

[0032] The technical solution in this application embodiment supervises the target resource business of each enterprise to be supervised in descending order of regulatory priority; the above method can supervise the target resource business of each enterprise to be supervised in a timely and effective manner according to the regulatory priority of each enterprise to be supervised.

[0033] In one embodiment, before performing attribute clustering processing on multiple enterprises to be regulated based on their enterprise data, the method further includes:

[0034] Obtain raw enterprise data from multiple companies awaiting supervision;

[0035] Preprocessing is performed on multiple original enterprise data to obtain enterprise data for multiple enterprises to be regulated; the preprocessing includes at least one of abnormal data compensation processing, data type conversion and normalization processing.

[0036] The technical solution in this application embodiment obtains original enterprise data of multiple enterprises to be regulated, preprocesses the original enterprise data to obtain enterprise data of multiple enterprises to be regulated, wherein the preprocessing includes at least one of abnormal data compensation processing, data type conversion and normalization processing; the above method can obtain the preprocessed enterprise data to provide dependent information for subsequent accurate attribute clustering data; at the same time, the preprocessing process in the above method does not require the participation of complex algorithms, thereby reducing the complexity of preprocessing and improving the accuracy of preprocessing results.

[0037] Secondly, embodiments of this application provide a business monitoring device, which includes:

[0038] The clustering module is used to perform attribute clustering on multiple enterprises to be regulated based on their enterprise data, and obtain clustering results.

[0039] The priority determination module is used to determine the regulatory priority of each enterprise to be regulated based on the clustering results, provided that the measurement index values ​​of the clustering results meet the standards.

[0040] The regulatory module is used to supervise the target resource businesses of each enterprise to be regulated based on clustering results and regulatory priorities.

[0041] Thirdly, embodiments of this application also provide a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any of the embodiments of the first aspect described above.

[0042] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0043] Fifthly, embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0044] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0045] Figure 1 This is a diagram illustrating the application environment of a business supervision method in one embodiment;

[0046] Figure 2 This is a flowchart illustrating a business supervision method in one embodiment;

[0047] Figure 3 This is a flowchart illustrating the business supervision method in another embodiment;

[0048] Figure 4 This is a flowchart illustrating the business supervision method in another embodiment;

[0049] Figure 5 This is a flowchart illustrating the business supervision method in another embodiment;

[0050] Figure 6 This is a flowchart illustrating the business supervision method in another embodiment;

[0051] Figure 7 This is a structural block diagram of a business monitoring device in one embodiment;

[0052] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] In the financial sector, the financial operations of various enterprises may involve certain risks. Therefore, in order to reduce the incidence of risks, it is particularly important to regulate the financial services of these enterprises. Related technologies primarily utilize the financial big data of each enterprise to regulate its financial operations, thereby improving regulatory capabilities. However, these technologies suffer from the problem of untimely regulation. Therefore, this application provides a business regulation method that enables timely regulation of the financial operations of various enterprises, improving the effectiveness of financial business regulation.

[0055] The business supervision method provided in this application embodiment can be applied to... Figure 1The business monitoring system shown includes computer equipment and management equipment for the financial data of each enterprise. Optionally, the computer equipment and each management system can be connected via communication, such as through Wi-Fi, mobile network, or Bluetooth. Optionally, the computer equipment can be, but is not limited to, personal computers, desktop computers, laptops, iPads, or other electronic devices with data processing capabilities, and each management device can be, but is not limited to, personal computers, desktop computers, laptops, iPads, databases, or other electronic devices with data storage capabilities. Figure 1 The following example uses a business supervision system comprising three management devices (management device 1, management device 2, and management device 3) for illustration. The specific process of the business supervision method is described below using a computer device as the executing entity.

[0056] like Figure 2 The diagram shown is a flowchart of the business supervision method provided in this application embodiment. The method can be implemented through the following steps:

[0057] S100. Based on the enterprise data of multiple enterprises to be regulated, perform attribute clustering processing on the multiple enterprises to be regulated to obtain clustering results.

[0058] In practical applications, the aforementioned enterprises to be regulated can be of any category, such as telecommunications companies, transportation companies, construction companies, healthcare companies, wholesale and retail companies, and financial companies. The computer equipment can acquire enterprise data for each enterprise to be regulated within a historical time period. Optionally, the aforementioned time period can be the time corresponding to the current time and a consecutive time period preceding it.

[0059] Optionally, the enterprise data of the aforementioned enterprises to be regulated may include employee social security information, credit information, qualification information such as business licenses, case information such as disputes, cash flow and transaction information, tax credit information, and identification information; the aforementioned employee social security information may include, but is not limited to, the employee's name, ID number, social security information, social security period, social security status, social security institution, and the social security institution's unified social credit code; the aforementioned credit information may include, but is not limited to, the enterprise's unified credit code, credit rating, credit score, and penalty information; the aforementioned qualification information such as business licenses may include, but is not limited to, the business license, business scope, business period, and unified social credit code; the aforementioned case information may include, but is not limited to, records of financial cases involving the enterprise to be regulated, court lawsuits, administrative penalties, case types, and penalty information; the aforementioned identification information may include, but is not limited to, the enterprise type, business scope, and unified social credit code.

[0060] In practical applications, computer equipment can perform attribute clustering on multiple enterprises to be regulated based on their enterprise data, obtaining clustering results. Optionally, the attributes of the enterprises to be regulated can include their business scope, enterprise type, industry type, development stage, etc. In this embodiment, the clustering results can be represented in the form of a summary graph.

[0061] In one embodiment, the computer device can pre-train an algorithm model, and then input the enterprise data of each enterprise to be regulated into the algorithm model. The algorithm model performs attribute clustering processing on each enterprise to be regulated based on the enterprise data and outputs the clustering results.

[0062] In another embodiment, the computer device can perform matching, comparison, and classification operations based on the enterprise data of each enterprise to be regulated, so as to complete the attribute clustering processing of each enterprise to be regulated and obtain the clustering result.

[0063] S200. If the clustering results meet the required performance indicators, determine the regulatory priority for each enterprise to be regulated based on the clustering results.

[0064] The achievement of the above clustering result measurement index can be understood as the number of cluster categories in the clustering result being equal to the target number.

[0065] Specifically, if the above-mentioned clustering results meet the required metrics, the regulatory priority of each enterprise to be regulated can be determined based on the clustering results.

[0066] In one embodiment, the clustering results can be analyzed, sorted, and / or compared to obtain the regulatory priority of each enterprise to be regulated.

[0067] S300. Based on the clustering results and regulatory priorities, supervise the target resource business of each enterprise to be regulated.

[0068] In practical applications, computer equipment can pre-train a business supervision model, and then input the clustering results and various supervision priorities into the business supervision model. This model then sequentially supervises the target resource businesses of each enterprise to be regulated, thereby improving the timeliness of supervision over the target resource businesses of different enterprises. In this embodiment, the aforementioned target resource business can be a financial business.

[0069] The technical solution in this application embodiment performs attribute clustering processing on multiple enterprises to be regulated based on their enterprise data, obtaining clustering results. If the measurement index values ​​of the clustering results meet the standards, the regulatory priority of each enterprise to be regulated is determined based on the clustering results. Then, based on the clustering results and each regulatory priority, the target resource business of each enterprise to be regulated is regulated. This method determines the regulatory priority of each enterprise to be regulated only when the measurement index values ​​of the attribute clustering results of multiple enterprises to be regulated meet the standards, making the determined regulatory priorities of each enterprise to be regulated more accurate. Furthermore, based on the obtained regulatory priorities of different enterprises to be regulated, the regulatory priorities of each enterprise to be regulated are further adjusted. Effective supervision of target resource businesses can improve the timeliness of supervision over different enterprises seeking supervision. Furthermore, the above method requires no additional operations and can promptly process the target resource businesses of different enterprises based on their supervisory priorities, thereby reducing the cost of target resource business supervision. Moreover, the method can also conduct real-time supervision of the target resource businesses of each enterprise seeking supervision according to their supervisory priorities, enabling proactive risk prevention and reducing the risk rate of such risks. Additionally, the method has no limitations on the magnitude of changes in enterprise data, thus expanding the application scenarios for target resource business supervision.

[0070] The following describes the process of obtaining clustering results by performing attribute clustering on multiple enterprises to be regulated based on their enterprise data. In one embodiment, the step S100 above may include: inputting the enterprise data of multiple enterprises to be regulated into a second-order clustering model to perform attribute clustering on the multiple enterprises to be regulated to obtain clustering results.

[0071] In this embodiment of the application, the computer device can input the enterprise data of each enterprise to be regulated into a second-order clustering model to perform attribute clustering processing on multiple enterprises to be regulated to obtain clustering results.

[0072] Optionally, the above-mentioned second-order clustering model can be implemented by at least one of the following: convolutional neural network model, fully connected neural network model, recurrent neural network model, long short-term memory neural network model, and residual neural network model. Alternatively, the above-mentioned second-order clustering model can also be an algorithmic model built based on a second-order clustering algorithm.

[0073] It should be noted that the above-mentioned second-order clustering model can achieve secondary clustering, two-step clustering, or two-layer clustering.

[0074] The technical solution in this application embodiment inputs enterprise data of multiple enterprises to be regulated into a second-order clustering model to perform attribute clustering processing on the multiple enterprises to be regulated to obtain clustering results. The above method can perform attribute clustering processing on multiple enterprises to be regulated to obtain clustering results, providing reference information for accurately determining the regulatory priority of each enterprise to be regulated in the future. At the same time, the second-order clustering model in the above method can be applied to scenarios with large amounts of data. The above process uses the second-order clustering model to perform attribute clustering processing, which can not only improve the efficiency of attribute clustering processing, but also the second-order clustering model has strong robustness to data, which can improve the accuracy of clustering results.

[0075] In one embodiment, such as Figure 3 As shown, the steps described above, which involve inputting enterprise data from multiple enterprises to be regulated into a second-order clustering model to perform attribute clustering processing on these enterprises and obtain the clustering results, can be implemented in the following way:

[0076] S110. Based on multiple enterprise operation evaluation indicators, perform a clustering process on the enterprise data of each enterprise to be regulated to obtain indicator data for different enterprise operation evaluation indicators corresponding to each enterprise to be regulated.

[0077] The aforementioned enterprise operation evaluation indicators may include production capacity, market sales capacity, and operation-related indicators. In this embodiment, these enterprise operation evaluation indicators may include indicators such as enterprise service scope, enterprise financial strength, enterprise technological level, enterprise service quality, and enterprise risk control capabilities.

[0078] Specifically, for any enterprise to be regulated, the computer equipment can use the operational evaluation indicators of each enterprise as the clustering objects for a first clustering, and perform similarity matching, classification, comparison and other processing on the enterprise data of the enterprise to be regulated in order to complete a clustering process and obtain the indicator data of different enterprise operational evaluation indicators corresponding to the enterprise to be regulated.

[0079] S120. Based on multiple different enterprise attribute parameters, perform secondary clustering on the indicator data of different enterprise operation evaluation indicators corresponding to each enterprise to be regulated, and obtain the clustering results.

[0080] Optionally, the aforementioned different enterprise attribute parameters can be capacity utilization, market share, market growth rate, etc. In the embodiments of this application, the aforementioned multiple different enterprise attribute parameters may include multiple different enterprise sizes.

[0081] In practical applications, computer equipment can use the attribute parameters of each enterprise as the clustering objects for secondary clustering. It can perform similarity matching, classification, and comparison on the indicator data of each enterprise under supervision corresponding to different enterprise operation evaluation indicators to complete the secondary clustering process and obtain the indicator data of the enterprise under supervision corresponding to different enterprise operation evaluation indicators.

[0082] The technical solution in this application embodiment performs a first clustering process on the enterprise data of each enterprise to be regulated based on multiple enterprise operation evaluation indicators, obtaining indicator data for each enterprise to be regulated corresponding to different enterprise operation evaluation indicators. Then, based on multiple different enterprise attribute parameters, a second clustering process is performed on the indicator data for each enterprise to be regulated corresponding to different enterprise operation evaluation indicators to obtain the clustering result. This method simplifies the complex problem through two clustering processes, providing reference information for accurately determining the regulatory priority of each enterprise to be regulated. Simultaneously, this method does not require complex algorithms, making the processing relatively simple, thus reducing the complexity of the second-order clustering process and improving its speed and efficiency. Furthermore, this method allows for flexible adjustment of enterprise operation evaluation indicators and enterprise attribute parameters, making the application scenarios of attribute clustering more flexible.

[0083] The process for determining whether the clustering results meet the required metric values ​​will be explained below. In one embodiment, before performing the steps in S200 above, as follows: Figure 4 As shown, the above method may further include the following steps:

[0084] S210. Obtain the performance metrics for the clustering results. These metrics include performance metrics of the clustering model used in the attribute clustering process and / or quality metrics of the clustering results.

[0085] In practical applications, the metrics for evaluating the clustering results can include performance metrics of the clustering model used in the attribute clustering process and / or quality metrics of the clustering results. Optionally, the performance metrics can be the Schwarz-Bayes criterion (BIC) value; the quality metrics can be the silhouette coefficient value.

[0086] Specifically, computer devices can obtain metric values ​​for clustering results. In one implementation, the metric value can be obtained by comparing the number of clusters in the current clustering result with the expected number of clusters. In another implementation, the clustering results can be validated, and then the metric value can be determined based on the validation results.

[0087] In the embodiments of this application, after the second-order clustering model performs attribute clustering processing, it can automatically obtain performance measurement index values ​​and / or quality measurement index values.

[0088] S220. If the performance measurement index value is less than the first preset threshold and / or the quality measurement index value is greater than the second preset threshold, then the measurement index value of the clustering result is determined to meet the standard.

[0089] Specifically, the computer equipment can determine whether the performance measurement index value is less than a first preset threshold, and / or determine whether the quality measurement index value is greater than a second preset threshold. If the performance measurement index value is less than the first preset threshold, and / or the quality measurement index value is greater than the second preset threshold, the measurement index value of the clustering result can be determined to meet the standard.

[0090] Optionally, both the first and second preset thresholds can be user-defined or determined based on historical experience values. In this embodiment, the smaller the performance measurement index value, the higher the quality of the clustering result; the larger the quality measurement index value, the higher the quality of the clustering result.

[0091] The technical solution in this application embodiment obtains the performance measurement index value of the clustering model used for attribute clustering processing and / or the quality measurement index value of the clustering result. If the performance measurement index value is less than a first preset threshold and / or the quality measurement index value is greater than a second preset threshold, then it is determined that the measurement index value of the clustering result meets the standard. The above method does not require the participation of complex algorithms, the processing process is relatively simple, it can improve the speed of determining whether the measurement index value of the clustering result meets the standard, and on this basis, it can provide a reference for accurately determining the regulatory priority of each enterprise to be regulated.

[0092] The process of determining the regulatory priority of each enterprise to be regulated based on the clustering results is described below. In one embodiment, the clustering results include multiple cluster categories; such as... Figure 5 As shown, the steps in S200 above may include:

[0093] S210. Obtain the number of enterprises with at least one enterprise to be regulated in each cluster category.

[0094] In practical applications, computer equipment can use statistical methods to count the number of all enterprises to be regulated in each cluster of the clustering results. Optionally, the number of all enterprises to be regulated in each cluster can be greater than or equal to 1.

[0095] S220. Sort the number of each enterprise and obtain the sorting results.

[0096] Specifically, the computer equipment can sort the number of enterprises corresponding to each cluster category in ascending or descending order to obtain the sorting results.

[0097] S230. Based on the ranking results, determine the regulatory priority of each enterprise to be regulated. Enterprises within the same cluster category have the same regulatory priority.

[0098] In practical applications, computer equipment can pre-train an algorithm model, and then input the ranking results into the algorithm model, which outputs the regulatory priority of each enterprise to be regulated.

[0099] In addition, computer equipment can also determine the regulatory priority of each enterprise to be regulated according to a preset priority configuration strategy and the sorting results.

[0100] In one embodiment, the step of determining the regulatory priority of each enterprise to be regulated in S230 above based on the sorting result may include: assigning a regulatory priority from high to low to each corresponding enterprise to be regulated in descending order of the number of enterprises in the sorting result.

[0101] The processing in this embodiment is relatively simple and requires human intervention, which can improve the speed and efficiency of assigning regulatory priorities, reduce human intervention errors, and improve the accuracy of assigned regulatory priorities.

[0102] The technical solution in this application embodiment obtains the number of enterprises to be regulated in each cluster category of the clustering results, sorts the number of enterprises to obtain the sorting results, and determines the regulatory priority of each enterprise to be regulated based on the sorting results. Among them, different enterprises to be regulated in the same cluster category have the same regulatory priority. The above method does not require the participation of complex algorithms, the processing process is relatively simple, it can improve the speed of determining the regulatory priority of each enterprise to be regulated, and on this basis, it can provide a reference for timely supervision of the target resource business of each enterprise to be regulated.

[0103] In one embodiment, the step of supervising the target resource business of each enterprise to be supervised according to the clustering results and each regulatory priority in S300 above may include: supervising the target resource business of each enterprise to be supervised in order of regulatory priority from high to low.

[0104] In practical applications, the target resource businesses of each enterprise to be regulated can be regulated sequentially according to their regulatory priorities, from highest to lowest. The order of regulation for the target resource businesses of different enterprises to be regulated may be the same or different.

[0105] It should be noted that when different companies under supervision have the same regulatory priority, the regulatory order of their target resource businesses is the same.

[0106] The technical solution in this application embodiment supervises the target resource business of each enterprise to be supervised in descending order of regulatory priority; the above method can supervise the target resource business of each enterprise to be supervised in a timely and effective manner according to the regulatory priority of each enterprise to be supervised.

[0107] In one embodiment, before performing the steps in S100, such as Figure 6 As shown, the above method may further include the following steps:

[0108] S400: Obtain raw enterprise data from multiple companies awaiting regulation.

[0109] In practical applications, computer equipment can send enterprise data retrieval commands to the management devices of each enterprise under supervision and receive raw enterprise data from these devices. Additionally, the computer equipment can receive raw enterprise data from the management devices of each enterprise under supervision in real time. Furthermore, the computer equipment can also retrieve raw enterprise data from storage locations such as local storage, cloud storage, disks, hard drives, and databases. It should be noted that the aforementioned raw enterprise data and enterprise data are of the same type.

[0110] In addition, computer equipment can acquire the original enterprise data of each enterprise to be regulated in either a full-scale or incremental manner.

[0111] S500: Preprocess multiple original enterprise data sets to obtain enterprise data for multiple enterprises to be regulated. Preprocessing includes at least one of the following: anomaly compensation processing, data type conversion, and normalization processing.

[0112] In practical applications, the above-mentioned abnormal data compensation processing can include abnormal data removal, missing data imputation (such as imputation of mean, median, mode, etc.), and duplicate data removal. Among them, missing data imputation can be achieved by collecting data from other dimensions to fill in the missing data, or by filling in the missing data based on knowledge in the field, or by manual or automatic methods.

[0113] It should be noted that the normalization of the original enterprise data is to ensure consistency across different scales and prevent inaccurate results in subsequent processing.

[0114] Furthermore, before performing data type conversion, it can be determined whether the original enterprise data is numeric or non-numeric. Non-numeric data can include both categorical and non-categorical (i.e., string) data. Categorical data can include ordinal and typed data. Further, if the original enterprise data is non-numeric, it can be converted to numeric type for subsequent processing.

[0115] Specifically, ordinal encoding can be used to convert the data type of ordered raw enterprise data. For example, enterprise credit ratings are divided into three levels: medium, high, and low. Ordinal encoding can assign an ID to each level of the ordered enterprise credit rating, such as 1 for medium, 2 for high, and 3 for mid. The size of the enterprise credit rating is still preserved after the data type conversion. Alternatively, one-hot encoding can be used to convert the data type of categorical raw enterprise data. It is important to note that when there are many categorical values ​​in the raw enterprise data, sparse vectors can be used to represent the raw enterprise data to save space. If the raw enterprise data is non-categorical, the appropriate method can be used to convert the data type based on different use cases and the advantages and disadvantages of different conversion methods.

[0116] The technical solution in this application embodiment obtains original enterprise data of multiple enterprises to be regulated, preprocesses the original enterprise data to obtain enterprise data of multiple enterprises to be regulated, wherein the preprocessing includes at least one of abnormal data compensation processing, data type conversion and normalization processing; the above method can obtain the preprocessed enterprise data to provide dependent information for subsequent accurate attribute clustering data; at the same time, the preprocessing process in the above method does not require the participation of complex algorithms, thereby reducing the complexity of preprocessing and improving the accuracy of preprocessing results.

[0117] In one embodiment, this application also provides a business monitoring method applied to a computer device, the method comprising the following processes:

[0118] (1) Obtain original enterprise data from multiple enterprises to be regulated;

[0119] (2) Preprocess multiple original enterprise data to obtain enterprise data of multiple enterprises to be regulated; the preprocessing includes at least one of abnormal data compensation processing, data type conversion and normalization processing;

[0120] (3) Based on multiple enterprise operation evaluation indicators, the enterprise data of each enterprise to be regulated is clustered once to obtain the indicator data of each enterprise to be regulated corresponding to different enterprise operation evaluation indicators;

[0121] (4) Based on multiple different enterprise attribute parameters, the indicator data of different enterprise operation evaluation indicators corresponding to each enterprise to be supervised are subjected to secondary clustering to obtain clustering results;

[0122] (5) Obtain the performance metrics of the clustering results; the performance metrics include the performance metrics of the clustering model used in the attribute clustering process and / or the quality metrics of the clustering results;

[0123] (6) If the performance measurement index value is less than the first preset threshold and / or the quality measurement index value is greater than the second preset threshold, then the measurement index value of the clustering result is determined to meet the standard.

[0124] (7) If the clustering results meet the target, obtain the number of enterprises in each cluster category that are at least one enterprise to be regulated;

[0125] (8) Sort the number of each enterprise and obtain the sorting results;

[0126] (9) According to the order of the number of enterprises in the ranking results from large to small, assign the corresponding enterprises to be regulated with the highest to lowest regulatory priority; among them, different enterprises to be regulated in the same cluster category have the same regulatory priority;

[0127] (10) The target resource business of each enterprise to be regulated shall be regulated in order of the priority of each regulation from high to low.

[0128] The specific execution process of (1) to (10) above can be found in the description of the above embodiments. The implementation principle and technical effect are similar, and will not be repeated here.

[0129] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0130] Based on the same inventive concept, this application also provides a business supervision device for implementing the business supervision method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more business supervision device embodiments provided below can be found in the limitations of the business supervision method described above, and will not be repeated here.

[0131] In one embodiment, Figure 7 This is a schematic diagram of the structure of a business monitoring device in one embodiment of this application. The business monitoring device provided in this embodiment can be applied to computer equipment. Figure 7As shown, the business monitoring device in this application embodiment may include: a clustering processing module 11, a priority determination module 12, and a monitoring module 13, wherein:

[0132] Clustering module 11 is used to perform attribute clustering on multiple enterprises to be regulated based on their enterprise data to obtain clustering results.

[0133] Priority determination module 12 is used to determine the regulatory priority of each enterprise to be regulated based on the clustering results, provided that the measurement index values ​​of the clustering results meet the standards.

[0134] The supervision module 13 is used to supervise the target resource business of each enterprise to be supervised based on the clustering results and the supervision priorities.

[0135] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0136] In one embodiment, the clustering processing module 11 includes: a second-order clustering unit, wherein:

[0137] The second-order clustering unit is used to input enterprise data of multiple enterprises to be regulated into the second-order clustering model in order to perform attribute clustering processing on multiple enterprises to be regulated and obtain clustering results.

[0138] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0139] In one embodiment, the second-order clustering unit is specifically used for:

[0140] Based on multiple enterprise operation evaluation indicators, the enterprise data of each enterprise to be regulated is clustered to obtain the indicator data of different enterprise operation evaluation indicators for each enterprise to be regulated.

[0141] Based on multiple different enterprise attribute parameters, the indicator data of different enterprise operation evaluation indicators corresponding to each enterprise to be regulated are subjected to secondary clustering processing to obtain clustering results.

[0142] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0143] In one embodiment, the business monitoring device further includes: an indicator value acquisition module and an indicator value compliance determination module, wherein:

[0144] The indicator value acquisition module is used to acquire the measurement indicator values ​​of the clustering results; the measurement indicator values ​​include the performance measurement indicator values ​​of the clustering model used for attribute clustering processing and / or the quality measurement indicator values ​​of the clustering results;

[0145] The indicator value attainment determination module is used to determine whether the clustering results meet the performance indicator value when the performance indicator value is less than a first preset threshold and / or the quality indicator value is greater than a second preset threshold.

[0146] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0147] In one embodiment, the clustering result includes multiple cluster categories; the priority determination module 12 includes: an enterprise number acquisition unit, a sorting unit, and a priority determination unit, wherein:

[0148] The enterprise number acquisition unit is used to acquire the number of enterprises with at least one enterprise to be regulated in each cluster category;

[0149] The sorting unit is used to sort the quantity of each enterprise and obtain the sorting result;

[0150] The priority determination unit is used to determine the regulatory priority of each enterprise to be regulated based on the ranking results; among them, different enterprises to be regulated in the same cluster category have the same regulatory priority.

[0151] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0152] In one embodiment, the priority determination unit is specifically used for:

[0153] Based on the ranking of the number of companies in the results from largest to smallest, each company to be regulated is assigned a regulatory priority from highest to lowest.

[0154] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0155] In one embodiment, the monitoring module 13 is specifically used for:

[0156] The target resource businesses of each enterprise to be regulated will be regulated in descending order of regulatory priority.

[0157] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0158] In one embodiment, the business monitoring device further includes: an enterprise data acquisition module and a preprocessing module, wherein:

[0159] The enterprise data acquisition module is used to acquire raw enterprise data from multiple enterprises to be regulated.

[0160] The preprocessing module is used to preprocess multiple original enterprise data to obtain enterprise data of multiple enterprises to be regulated; the preprocessing includes at least one of abnormal data compensation processing, data type conversion and normalization processing.

[0161] The business monitoring device provided in this application embodiment can be used to execute the technical solutions in the above-described business monitoring method embodiments of this application. Its implementation principle and technical effects are similar, and will not be repeated here.

[0162] Specific limitations regarding the business monitoring device can be found in the limitations of the business monitoring method described above, and will not be repeated here. Each module in the aforementioned business monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0163] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides processing power. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores original enterprise data and enterprise data for each enterprise under supervision. The network interface communicates with external endpoints via a network connection. When executed by the processor, the computer program implements a business supervision method.

[0164] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0165] In one embodiment, a computer device is also provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the technical solutions in the above-described business supervision method embodiments of this application. The implementation principle and technical effects are similar, and will not be repeated here.

[0166] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the technical solution of the business supervision method described above in this application. Its implementation principle and technical effect are similar, and will not be repeated here.

[0167] In one embodiment, a computer program product is also provided, including a computer program that, when executed by a processor, implements the technical solution of the business supervision method described above in this application. Its implementation principle and technical effects are similar and will not be repeated here.

[0168] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0169] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0170] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A business supervision method, characterized in that, The method includes: Based on the enterprise data of multiple enterprises awaiting supervision, attribute clustering processing is performed on the multiple enterprises awaiting supervision to obtain clustering results; Obtain the performance metrics of the clustering results; the performance metrics include the performance metrics of the clustering model used for attribute clustering and / or the quality metrics of the clustering results. If the performance measurement index value is less than a first preset threshold, and / or the quality measurement index value is greater than a second preset threshold, then the measurement index value of the clustering result is determined to meet the standard; the clustering result includes multiple clustering categories; If the performance indicators for each cluster category meet the target, the number of enterprises to be regulated in each cluster category is obtained, the number of enterprises to be regulated is sorted to obtain a ranking result, and the regulatory priority of each enterprise to be regulated is determined based on the ranking result; wherein, different enterprises to be regulated in the same cluster category have the same regulatory priority. Based on the clustering results and the respective regulatory priorities, the target resource businesses of each of the enterprises to be regulated are subject to regulation.

2. The method according to claim 1, characterized in that, The step involves performing attribute clustering on multiple enterprises to be regulated based on their enterprise data to obtain clustering results, including: The enterprise data of the multiple enterprises to be regulated are input into a second-order clustering model to perform attribute clustering processing on the multiple enterprises to be regulated to obtain the clustering results.

3. The method according to claim 2, characterized in that, The step of inputting the enterprise data of the multiple enterprises to be regulated into a second-order clustering model to perform attribute clustering processing on the multiple enterprises to be regulated to obtain the clustering result includes: Based on multiple enterprise operation evaluation indicators, the enterprise data of each enterprise to be regulated is clustered to obtain the indicator data of different enterprise operation evaluation indicators for each enterprise to be regulated. Based on multiple different enterprise attribute parameters, the indicator data of each enterprise to be regulated corresponding to different enterprise operation evaluation indicators are subjected to secondary clustering processing to obtain the clustering results.

4. The method according to any one of claims 1-3, characterized in that, The step of determining the regulatory priority of each of the enterprises to be regulated based on the sorting results includes: Based on the ranking of the number of enterprises in the results from largest to smallest, each enterprise to be regulated is assigned a regulatory priority from highest to lowest.

5. The method according to any one of claims 1-3, characterized in that, The step of supervising the target resource business of each enterprise to be regulated based on the clustering results and the respective regulatory priorities includes: The target resource businesses of each enterprise to be regulated will be regulated in descending order of regulatory priority.

6. The method according to any one of claims 1-3, characterized in that, Before performing attribute clustering on the multiple enterprises to be regulated based on their enterprise data, the method further includes: Obtain the original enterprise data of the multiple enterprises to be regulated; Multiple original enterprise data are preprocessed to obtain enterprise data of the multiple enterprises to be regulated; the preprocessing includes at least one of abnormal data compensation processing, data type conversion and normalization processing.

7. A business monitoring device, characterized in that, The device includes: The clustering module is used to perform attribute clustering on the multiple enterprises to be regulated based on their enterprise data, and obtain clustering results. The indicator value acquisition module is used to acquire the measurement indicator values ​​of the clustering results; the measurement indicator values ​​include the performance measurement indicator values ​​of the clustering model used for attribute clustering processing and / or the quality measurement indicator values ​​of the clustering results; The indicator value compliance determination module is used to determine whether the clustering result meets the standard when the performance measurement indicator value is less than a first preset threshold and / or the quality measurement indicator value is greater than a second preset threshold; the clustering result includes multiple clustering categories; The priority determination module is used to obtain the number of enterprises to be regulated in each cluster category when the measurement index value of each cluster category meets the standard, sort the number of enterprises to obtain the sorting result, and determine the regulatory priority of each enterprise to be regulated based on the sorting result; wherein, different enterprises to be regulated in the same cluster category have the same regulatory priority. The supervision module is used to supervise the target resource business of each of the enterprises to be supervised based on the clustering results and the supervision priorities.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.

Images