Data processing method and device, electronic equipment and storage medium

Abstract

The invention provides a data processing method, and relates to the technical field of artificial intelligence, in particular to the technical fields of large models, software technologies, risk early warning and the like. According to the specific implementation scheme, the method comprises the steps of analyzing target service data of a service, and determining a plurality of exception recognition results; in response to a confirmation result for the plurality of exception recognition results, determining an exception early warning template corresponding to a target exception recognition result based on the target exception recognition result indicated by the confirmation result, the exception early warning template comprising a to-be-filled field and a fixed field, and the target exception node comprising at least one of a plurality of pieces of early warning information; based on the business basic data and the target business data, determining field content used for filling the to-be-filled field, and obtaining early warning data; and obtaining a business exception solving strategy based on the early warning data, the business basic data and the target business data. The invention further provides a data processing device, electronic equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to technical fields such as large models, software technology, and risk warning, and specifically to data processing methods, devices, electronic devices, storage media, and program products. Background Art

[0002] The execution process of software development business is complex and has a significant impact. Various problems may occur during the development process. Therefore, business anomaly identification and resolution is an important part of software development. Summary of the invention

[0003] The present disclosure provides a data processing method, device, electronic device, storage medium and program product.

[0004] According to one aspect of the present disclosure, a data processing method is provided, comprising: parsing target business data of a business to determine a plurality of exception identification results, wherein the business target data represents the expected execution requirements of the business; in response to confirmation results for the plurality of exception identification results, determining an exception warning template corresponding to the target exception identification result based on the target exception identification result indicated by the confirmation result, wherein the exception warning template includes fields to be filled in and fixed fields, and the target exception node includes at least one of a plurality of warning data; based on business basic data and target business data, determining field content for filling in the fields to be filled in to obtain warning data, wherein the business basic data includes resource data for processing the business; and obtaining a business exception resolution strategy based on the warning data, the business basic data and the target business data.

[0005] According to another aspect of the present disclosure, a data processing device is provided, including: a data processing device, including: a parsing module, used to parse target business data of a business, and determine multiple abnormal identification results of the business, wherein the business target data represents the expected execution requirements of the business; a template determination module, used to respond to a confirmation result for the abnormal identification result, and determine an abnormal warning template corresponding to the target abnormal identification result based on the target abnormal identification result indicated by the confirmation result, wherein the target abnormal identification result includes at least one of the multiple abnormal identification results, and the abnormal warning template includes a to-be-filled field and a fixed field; an early warning module, used to determine the field content used to fill in the to-be-filled field based on the business basic data and target business data of the business, and obtain early warning data, wherein the business basic data includes resource data for processing the business; and an abnormality resolution module, used to obtain a business abnormality resolution strategy based on the early warning data, the business basic data and the target business data.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: 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 a method as disclosed in the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, and when the computer program is executed by a processor, the method of the present disclosure is implemented.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 An exemplary system architecture to which the data processing method and device according to an embodiment of the present disclosure can be applied is schematically shown;

[0012] Figure 2 A flowchart schematically shows a data processing method according to an embodiment of the present disclosure;

[0013] Figure 3 A flowchart for determining multiple abnormality identification results according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 4 A flowchart for determining a rule recognition result according to an embodiment of the present disclosure is schematically shown;

[0015] Figure 5 A framework diagram of a business management system according to another embodiment of the present disclosure is schematically shown;

[0016] Fig. 6A The schematic diagram schematically shows an optimization diagram of generating a large model according to another embodiment of the present disclosure;

[0017] Figure 6B The optimized schematic diagram of the abnormality recognition large model according to another embodiment of the present disclosure is schematically shown;

[0018] Figure 7 A block diagram schematically shows a data processing device according to an embodiment of the present disclosure; and

[0019] Figure 8 A block diagram of an electronic device suitable for implementing a data processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0020] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] In the software delivery business scenario, business risk management has always been one of the key points of business management. In most current software development businesses, although each business manager has his or her own management method, there is a lack of unified management at the organizational level. In addition, risk warning and monitoring are often ignored or lacking.

[0022] In order to solve this technical problem, the present disclosure provides a data processing method, including: parsing target business data of a business to determine multiple exception identification results, wherein the business target data represents the expected execution requirements of the business; in response to confirmation results for multiple exception identification results, based on the target exception identification result indicated by the confirmation result, determining an exception warning template corresponding to the target exception identification result, wherein the exception warning template includes fields to be filled in and fixed fields, and the target exception node includes at least one of multiple warning data; based on business basic data and target business data, determining field content for filling in the fields to be filled in to obtain warning data, wherein the business basic data includes resource data for processing the business; and based on the warning data, the business basic data and the target business data, obtaining a business exception resolution strategy.

[0023] By using the above data processing method disclosed in the present invention, it is possible to identify multiple possible abnormal identification results in advance by parsing the target business data, and determine the warning data based on the basic business data and the target business data. And based on the warning data, the basic business data and the target business data, multiple business abnormality resolution strategies are obtained. In this way, automated and intelligent abnormal problem monitoring and early warning are realized. Then, it helps business processing personnel find the best solution, and then eliminate abnormal problems such as risks in the bud.

[0024] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0025] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0026] Figure 1 An exemplary system architecture to which the data processing method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown.

[0027] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the data processing method and apparatus can be applied may include a terminal device, but the terminal device may implement the data processing method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0028] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0029] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0030] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0031] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for the content browsed by the user using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to the user request) to the terminal device.

[0032] It should be noted that the data processing method provided in the embodiment of the present disclosure can generally be executed by the terminal device 101, 102, or 103. Accordingly, the data processing apparatus provided in the embodiment of the present disclosure can also be set in the terminal device 101, 102, or 103.

[0033] Alternatively, the data processing method provided in the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the data processing device provided in the embodiment of the present disclosure may generally be arranged in the server 105. The data processing method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the data processing device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0034] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0035] It should be noted that the sequence numbers of the operations in the following method are only used as representations of the operations for the purpose of description, and should not be regarded as representing the execution order of the operations. Unless explicitly stated, the method does not need to be executed completely in the order shown.

[0036] Figure 2 The flowchart of the data processing method according to the embodiment of the present disclosure is schematically shown.

[0037] like Figure 2 As shown, the method includes operations S210 to S240.

[0038] In operation S210, target business data of the business is parsed to determine a plurality of abnormality identification results of the business.

[0039] In operation S220 , in response to a confirmation result for the abnormal identification result, an abnormal warning template corresponding to the target abnormal identification result is determined based on the target abnormal identification result indicated by the confirmation result.

[0040] In operation S230, based on the basic business data and target business data of the business, the field content to be filled in the to-be-filled field is determined to obtain early warning data.

[0041] In operation S240, a business anomaly resolution strategy is obtained based on the warning data, the basic business data, and the target business data.

[0042] The business may include software development business, but is not limited thereto, and may also include construction business, etc. As long as it involves target business data and has risk issues, it can be regarded as the business involved in the present disclosure.

[0043] Business target data represents the expected execution requirements of the business. For example, it can refer to the agreed content that needs to be followed or the expected standards that need to be achieved in order to complete the business, such as business contract information.

[0044] The target business data can be analyzed, and multiple abnormal identification results can be obtained by issuing abnormal warnings for various requirements involved in the target business data. The abnormal identification results can include possible risk issues.

[0045] For example, the abnormal identification results may include at least one of the following: abnormal identification results such as cost risk, schedule risk, business risk, customer complaint risk, and project management risk.

[0046] Multiple abnormal identification results can be displayed to the business manager on the display interface. The business manager can use a mouse or a manual touch screen to click or input commands on the multiple abnormal identification results on the display interface to determine whether to continue analyzing the abnormal identification results.

[0047] In response to a confirmation result for the abnormal identification result, an abnormal warning template corresponding to the target abnormal identification result may be determined from a plurality of abnormal warning templates based on the target abnormal identification result indicated by the confirmation result.

[0048] The abnormal warning template may include a field to be filled in and a fixed field, and the target abnormal identification result includes at least one of the multiple abnormal identification results. The fixed field includes a fixed content for indicating the alarm. The field to be filled in includes an adjustable content for indicating the alarm.

[0049] Taking the target anomaly identification result including the risk of resource value exceeding the expected value as an example, the fixed field may include one or more of "resource overspending value", "abnormal level", etc. The to-be-filled field may include a specific value or level value.

[0050] The basic business data may include resource data used to process the business. For example, the basic business data may include business resource data such as data on resources consumed to process the business and personnel data of relevant business processing personnel used to process the business, but is not limited thereto. The basic business data also includes business attribute data such as business type data, business prospect data, industry knowledge data, etc.

[0051] Based on the basic business data and target business data, information can be extracted from the fields to be filled in, and the extracted information can be calculated to obtain the field content corresponding to the fields to be filled in. Based on the field content and fixed fields, early warning data can be obtained.

[0052] The early warning data can be displayed on the display interface. A correction box or a confirmation control can also be set on the display interface so that the business management personnel can correct the early warning data in the correction box, or confirm the early warning data by clicking the confirmation control.

[0053] Based on the warning data, basic business data and target business data, the abnormal identification results indicated in the warning data can be safely controlled or the business processing method can be adjusted to obtain a business abnormality resolution strategy.

[0054] The business anomaly resolution strategy may refer to a solution to eliminate the target anomaly identification result. Taking the target anomaly identification result as a resource exceeding the expected value as an example, multiple business anomaly resolution strategies may include: reducing manpower expenditure, increasing outsourcing to reduce own expenditure, increasing budget or obtaining supplementary agreements, etc.

[0055] One business exception resolution strategy may be set in the relevant instance, but compared with setting only one business exception resolution strategy, setting multiple business exception resolution strategies can improve the intelligence and effectiveness of risk resolution.

[0056] By utilizing the business processing method provided by the embodiment of the present disclosure, it is possible to automatically generate multiple abnormal identification results by parsing the target business data. By confirming the result, the target abnormal identification result is determined from the multiple abnormal identification results, thereby improving flexibility. In addition, the early warning data is determined through the basic business data and the target business data, and the business abnormality resolution strategy is obtained based on the early warning data, thereby improving intelligence. In addition, the comprehensive processing capabilities of business abnormality early warning and business abnormality resolution are improved.

[0057] The above embodiment provides an overall introduction to the data processing method. Figure 3 A specific explanation is provided on how to determine multiple anomaly identification results.

[0058] Figure 3 A flowchart for determining multiple abnormality identification results according to an embodiment of the present disclosure is schematically shown.

[0059] like Figure 3As shown, the target business data 310 can be input into the anomaly identification large model M310 to obtain a model identification result 320 for processing the business. The target business data 310 and the decision tree M320 are matched to obtain a rule identification result 330 for processing the business. Based on the model identification result 320 and the rule identification result 330, multiple anomaly identification results 340 are obtained.

[0060] The target business data may be input into the anomaly identification model to obtain a model identification result. However, this is not limited to this. The target business data may also be input into a deep learning model to obtain a model identification result. The model identification result may include multiple anomaly identification results.

[0061] Compared with the method of inputting into a deep learning model, inputting into a large anomaly recognition model can fully utilize the long text processing capabilities of the large model and improve the accuracy of the model's anomaly recognition results.

[0062] Figure 4 The flowchart for determining the rule recognition result according to an embodiment of the present disclosure is schematically shown.

[0063] like Figure 4 As shown, the decision tree M410 may include multiple branches, each branch includes multiple nodes M411 and decision nodes M412. The node information of each node may include but is not limited to: threshold, matching rules, etc. Each decision node may include a business exception information. Multiple nodes and decision nodes are connected to each other through edges M413 for indicating the matching path of the next level.

[0064] Matching the target business data with the decision tree to obtain a rule identification result for processing the business may include: determining key content 420 from the target business data 410 based on the contract type. And determining a decision tree that matches the contract type from multiple decision trees. Matching the key content 420 with the node information in the decision tree step by step until a decision node of the decision tree is obtained. Based on the business abnormality information indicated by the decision node, as at least one abnormality identification result, a rule identification result 430 is obtained.

[0065] Taking software development business as an example, the key contents in the target business data may include project payment amount, completion deadline, business development function requirements, breach of contract clauses, etc. The decision tree corresponding to software development may include nodes: payment amount threshold, completion deadline threshold, number of development function requirements, number of breach of contract clauses threshold, etc. Decision nodes may include: cost risk points, schedule risk points, business risk points, customer complaint risk points, project management risk points, etc.

[0066] Obtaining multiple abnormality identification results based on the model identification result and the rule identification result may include: obtaining the multiple abnormality identification results by intersecting or unioning the model identification result and the rule identification result.

[0067] By using the various analytical methods provided by the present disclosure and taking advantage of the respective advantages of various different means, the automation and intelligence of determining abnormal identification results can be improved. Obtaining multiple abnormal identification results by finding the intersection can improve the accuracy and effectiveness of early warning. Obtaining multiple abnormal identification results by finding the union can increase the scope of early warning and avoid the problem of risk omission.

[0068] According to an embodiment of the present disclosure, when executing Figure 2 After the operation S210 shown, and before the operation S220 is performed, the data processing method may further include: displaying a plurality of abnormal identification results on a display interface, and receiving a confirmation result for the abnormal identification result.

[0069] This improves the effectiveness of the target anomaly identification results while combining manual specified operations to increase the flexibility of determination.

[0070] The following will explain how to determine the abnormal warning template based on the target abnormality recognition result.

[0071] According to the embodiments of the present disclosure, Figure 2 The operation S220 shown, based on the target abnormality recognition result indicated by the confirmation result, determining the abnormality warning template corresponding to the target abnormality recognition result, may include: based on the risk type of the target abnormality recognition result and the template mapping relationship, determining the abnormality warning template corresponding to the target abnormality recognition result from multiple abnormality warning templates. The template mapping relationship represents the corresponding relationship between the abnormality warning template and the abnormality type.

[0072] The abnormal warning template may include fixed fields and fields to be filled in. The use of fixed fields and fields to be filled in can improve the flexibility of generating warning data while reducing the difficulty of generating warning data through the abnormal warning template.

[0073] Multiple abnormal warning templates may be set, each of which matches the abnormal type of at least one target abnormal identification result, thereby increasing the application scope of the data processing method disclosed herein.

[0074] The following will explain how to generate warning data using an abnormal warning template.

[0075] According to the embodiments of the present disclosure, Figure 2The operation S230 shown, based on the business basic data and target business data of the business, determines the field content used to fill in the to-be-filled field, and obtains the early warning data, which may include: based on the fixed field, determining the target content from the business basic data and the target business data. Based on the target content and the predetermined threshold, obtain the early warning data. The predetermined threshold is determined from the specification data related to the business.

[0076] Based on the fixed fields, the focus of abnormal attention can be determined. Thus, the content related to the fixed fields, such as the target content, is determined from the basic business data and the target business data. The target content is the content required to determine the field to be filled.

[0077] For example, the target anomaly identification result is a resource anomaly, and the fixed field is "resource overspending value". Then the contract resource value can be determined from the target business data. Based on the basic business data, the project resource value used to process the business is determined. The difference between the contract resource value and the project resource value is used as the target content. Based on the target content, the resource overspending value is determined. The target content can be used as early warning data. However, it is not limited to this. It can also include: based on the target content and a predetermined threshold determined from the business-related specification data, a risk level is obtained. Based on the risk level and the target content, early warning data is obtained.

[0078] For example, the predetermined threshold is a resource overspending numerical threshold, such as **, and it has been determined that the resource overspending numerical value exceeds **, then the target abnormality identification result identified in the early warning data is a resource risk, and the risk level is level one.

[0079] Taking the target abnormality identification result including schedule risk as an example, the fixed field may include "overdue time", and the target content is determined from the basic business data and the contract content. For example, if the completion deadline requirement includes AAA and the expected time to complete the business is BBB, then the target content is BBB-AAA. The predetermined threshold may include an overdue threshold. Based on the overdue threshold and the target content, the abnormality level is determined. Based on the fixed field, the target content and the abnormality level, early warning data on schedule risk is obtained.

[0080] The warning data is determined based on the target content and predetermined thresholds, thereby improving the richness and diversity of the warning data, thereby increasing the presentation of more effective information to business managers and improving the effectiveness of subsequent business anomaly resolution strategies.

[0081] The following describes how to generate multiple business exception resolution strategies.

[0082] According to the embodiments of the present disclosure, Figure 2The operation S240 shown obtains multiple business exception resolution strategies based on the early warning data, basic business data and target business data, including: inputting the early warning data, basic business data and target business data into the solution generation model to obtain at least one business exception resolution strategy and identification data used to characterize the importance of each of the at least one business exception resolution strategies.

[0083] The early warning data, basic business data and target business data can be input into the solution generation model to obtain multiple solution information. However, it is not limited to this. Multiple identification data corresponding to multiple business exception solution strategies can also be obtained. The multiple identification data are used to characterize the importance of each of the multiple business exception solution strategies.

[0084] In another example, only the early warning data may be input into a large solution generation model to obtain multiple solution resolution strategies.

[0085] Compared with only using early warning data as a reference for generating business anomaly resolution strategies, using multiple reference factors provided by the embodiments of the present disclosure to generate multiple business anomaly resolution strategies can fully utilize the high processing capabilities of the large model and improve the relevant knowledge that can be learned by the large model, thereby improving the effectiveness of multiple business anomaly resolution strategies.

[0086] According to the embodiments of the present disclosure, Figure 2 The operation S240 shown, obtaining a business exception resolution strategy based on the warning data, the basic business data and the target business data, may also include: sorting the multiple business exception resolution strategies based on multiple identification data, and displaying the sorted multiple business exception resolution strategies.

[0087] On the display interface, multiple business exception resolution strategies are displayed according to the sorting, which can fully reflect the importance of each of the multiple business exception resolution strategies, thereby effectively improving the reminder level of important information. In addition, when there are too many business exception resolution strategies, multiple business exception resolution strategies can be screened through identification data to remove non-important information and highlight important business exception resolution strategies.

[0088] According to an embodiment of the present disclosure, when executing Figure 2 After the operation S240 shown, the data processing method may further include: acquiring business execution data of the business, and determining a solution result of the target abnormality identification result based on the business execution data and the warning data.

[0089] The current business execution data in the data processing system can be collected in real time. The business execution data may include business resource data and business attribute data of completed businesses.

[0090] The resolution result of the target anomaly identification result can be determined based on the business execution data and the warning data. The resolution result can include the result that the business anomaly has been resolved or the result that the business anomaly has not been resolved.

[0091] By providing abnormal warnings for business before executing the business, we can obtain target abnormal identification results, warning data and business abnormality resolution strategies. Then, by real-time tracking of progress and determining the resolution results, we can quickly respond to unresolved target abnormal identification results, which is conducive to real-time reminders and reduces the business losses ultimately caused by business abnormalities.

[0092] Figure 5 A framework diagram of a business management system according to another embodiment of the present disclosure is schematically shown.

[0093] like Figure 5 As shown, a business anomaly monitoring module 510 can be set in the business management system 500. The business anomaly monitoring module 510 is used to execute the data processing method. When the contract information about the business is identified in the business management system 500, the target business data is parsed to obtain multiple anomaly identification results. And displayed in the preview window 520 of the business management system 500. In response to the confirmation result of the business management personnel, the target anomaly identification result is determined from the multiple anomaly identification results. And the anomaly warning template corresponding to the target anomaly identification result is determined from the multiple anomaly warning templates stored in the database 530 of the business management system 500. From the basic business data and target business data stored in the database 530, the target content is determined, filled into the field to be filled, and the warning data is obtained, and the large model is generated by using the solution to process the basic business data and target business data of the warning data to obtain the business anomaly solution strategy. The business anomaly solution strategy is marked in the business processing module 540, which is convenient for the business management personnel to view at any time. As the business progresses, the business processing status is continuously updated in the business processing module 540 in the business management system 500, thereby improving the ability to report the target anomaly identification result after determining the early warning data and the business anomaly resolution strategy. When the target anomaly identification result is successfully reported, the business manager can determine the target business anomaly resolution strategy from multiple business anomaly resolution strategies. The system automatically associates the business with the target anomaly identification result and assigns it to the person who needs to resolve the target anomaly identification result. When the business corresponding to the target anomaly identification result identified in the system is executed, the resolution result is obtained. For example, the target anomaly identification result is automatically set as the risk has been resolved and is pending confirmation.

[0094] The system can automatically give a judgment result on whether the target abnormal identification result monitoring can be closed according to the task resolution situation, and send the result to the business administrator. The business administrator decides whether to trust the judgment result of the system. If no judgment result is given within a predetermined period of time, such as 7 days, the judgment result of the system is trusted to be accurate by default. If it is possible, it will be closed directly. If it is not possible, a new task will be created or associated, and the abnormal monitoring status will automatically change to in progress.

[0095] According to an embodiment of the present disclosure, when executing Figure 2 After the operation S240 shown, the data processing method may further include: obtaining a timeliness evaluation result for the business based on the processing time and warning data of the target abnormality identification result.

[0096] The timeliness evaluation result can be used as at least one measurement indicator of the effect of business exception processing. The data processing evaluation result can be obtained based on the timeliness evaluation result and the completion evaluation result, such as the weighted sum of the timeliness evaluation result and the completion evaluation result.

[0097] The processing time can be determined based on the solution result. For example, the solution result representation can mark the discovery time and completion time corresponding to the target abnormality identification result. Based on the discovery time and completion time, the processing time is obtained.

[0098] For each target anomaly identification result, the timeliness evaluation result is obtained based on the processing time of the solution result and the anomaly level of the warning data. For example, according to the preset rules, the anomaly level of the warning data is matched with the preset weight to obtain a weight value that matches the anomaly level. The processing time is multiplied by the weight value to obtain the timeliness evaluation result.

[0099] In the case where the target anomaly identification results include multiple ones, the timeliness evaluation result of each target anomaly identification result can be used as a timeliness evaluation sub-result. Based on the multiple timeliness evaluation sub-results and the number of target anomaly identification results, the timeliness evaluation result is obtained.

[0100] Based on multiple timeliness evaluation sub-results and the number of target anomaly recognition results, a timeliness evaluation result is obtained, which can be seen in formula (1).

[0101] ;Formula (1)

[0102] Among them, P represents the timeliness evaluation result, Indicates the processing time of the i-th target anomaly recognition result, represents the abnormality level of the i-th target abnormality recognition result, and I represents the total number of target abnormality recognition results.

[0103] Using the timeliness assessment results as a metric, in addition to measuring the speed of handling abnormal risks, it is also possible to quantify the improvement of business processing capabilities into the comprehensiveness and accuracy of indicators through scientific measurement standards.

[0104] According to an embodiment of the present disclosure, when executing Figure 2 After the operation S240 shown, the data processing method may further include: when it is determined that the business exception solution strategy and the business execution data do not match, optimizing the solution generation model for generating the business exception solution strategy based on the business execution data, the business exception solution strategy and the decision preference identifier. The decision preference identifier includes identification data for characterizing whether the business exception solution strategy and the business exception solution strategy are each adopted.

[0105] The business execution data may represent the current business processing status data. It may be the actual business execution data obtained after adjusting the business basic data based on the business. The business exception resolution strategy may be used to indicate the expected business execution data. The actual business execution data and the business exception resolution strategy representing the expected business execution data may be matched to determine whether the business management personnel adopt the business exception resolution strategy in the actual business processing process. If it is adopted, the adopted identification data can be identified. If it is not adopted, the unadopted identification data can be identified.

[0106] Determining whether each business exception resolution strategy matches the business execution data may include: determining the similarity between the business exception resolution strategy and the business execution data according to the semantic information or semantic features of the business exception resolution strategy and the business execution data. When the similarity is greater than a similarity threshold, it is determined that the business exception resolution strategy matches the business execution data. When the similarity is less than or equal to the similarity threshold, it is determined that the business exception resolution strategy does not match the business execution data.

[0107] When it is determined that the business exception resolution strategy and the business execution data do not match, the business execution data can be determined to be the execution operation corresponding to the target exception identification result. However, the multiple business exception resolution strategies given by the solution generation model do not meet the actual needs and are not adopted.

[0108] The business exception resolution strategy and identification data for each of the multiple business exception resolution strategies to identify whether they are adopted may be used to obtain a decision preference identification.

[0109] Using early warning data, basic business data and target business data as input data for training samples, decision preference identification and business exception resolution strategy, as well as decision preference identification and business execution data, as label pairs, the solution generation model is optimized and trained to obtain the optimized solution generation model. There is no limitation on loss function and parameter adjustment method, as long as it can be a reinforcement training method that can be combined with decision preference identification.

[0110] By adding decision preference identifiers to labels, reinforcement learning can be used to enable the large model to learn relevant knowledge about output results that meet actual needs during the training process, thereby improving the ability of the solution to generate business anomaly resolution strategies for the large model.

[0111] Fig. 6A The optimized schematic diagram of generating a large model according to another embodiment of the present disclosure is schematically shown.

[0112] like Fig. 6A As shown, the early warning data 610, the basic business data 620 and the target business data 630 are input into the solution generation model M610 to obtain the business exception solution strategy 640. Determine whether the business exception solution strategy and the business execution data match. In the case where it is determined that there is a match between the business exception solution strategy and the business execution data, stop the operation. In the case where it is determined that there is no match between the business exception solution strategy and the business execution data, the solution generation model M610 for generating the business exception solution strategy is optimized based on the business execution data 660, the business exception solution strategy 640 and the decision preference identifier 650.

[0113] Figure 6B The optimized schematic diagram of the abnormality recognition large model according to another embodiment of the present disclosure is schematically shown.

[0114] like Figure 6B As shown, the target business data 630 is input into the abnormality identification large model M620 to obtain a model identification result 670. Determine whether the model identification result matches the target abnormality identification result. In the case where it is determined that the model identification result matches the target abnormality identification result, stop the operation. In the case where it is determined that the model identification result does not match the target abnormality identification result, the abnormality identification large model M620 used to generate the model identification result is optimized based on the target business data 630 and the identification preference identifier 680.

[0115] The recognition preference identifier may include identification data for characterizing whether the model recognition result output by the anomaly recognition large model is adopted. It can be understood that the target anomaly recognition result is the adopted identification data.

[0116] By using recognition preference identifiers as part of the training sample data, reinforcement learning can be used to enable the large model to learn relevant knowledge about the output results that meet actual needs during the training process, thereby improving the business anomaly recognition capability of the anomaly recognition large model.

[0117] Figure 7 The block diagram schematically shows a data processing device according to an embodiment of the present disclosure.

[0118] like Figure 7 As shown, the data processing device 700 includes: a parsing module 710 , a template determination module 720 , an early warning module 730 and an abnormality resolution module 740 .

[0119] The parsing module 710 is used to parse the target business data of the business and determine multiple abnormality identification results of the business. The business target data represents the expected execution requirements of the business.

[0120] The template determination module 720 is used to determine the abnormal warning template corresponding to the target abnormal identification result based on the target abnormal identification result indicated by the confirmation result in response to the confirmation result for the abnormal identification result. The target abnormal identification result includes at least one of the multiple abnormal identification results, and the abnormal warning template includes a field to be filled in and a fixed field.

[0121] The early warning module 730 is used to determine the field content to be filled in the to-be-filled field based on the business basic data and target business data of the business, and obtain early warning data. The business basic data includes resource data for processing the business.

[0122] The exception resolution module 740 is used to obtain a business exception resolution strategy based on the warning data, the basic business data and the target business data.

[0123] According to an embodiment of the present disclosure, the parsing module includes: a model parsing submodule, a rule parsing submodule and a parsing submodule.

[0124] The model parsing submodule is used to input the target business data into the anomaly recognition model to obtain the model recognition result.

[0125] The rule parsing submodule is used to match the target business data with the decision tree to obtain the rule recognition result.

[0126] The parsing submodule is used to obtain multiple abnormality recognition results based on the model recognition results and the rule recognition results.

[0127] According to an embodiment of the present disclosure, the early warning module includes: an extraction submodule and an early warning submodule.

[0128] The extraction submodule is used to determine the target content from the business basic data and the target business data based on the fixed fields. The target content is used to determine the fields to be filled.

[0129] The early warning submodule is used to obtain early warning data based on the target content and the predetermined threshold value. The predetermined threshold value is determined from the normative data related to the business.

[0130] According to an embodiment of the present disclosure, the exception resolution module includes: an input submodule and a sorting submodule.

[0131] The input submodule is used to input the warning data, basic business data and target business data into the solution generation model to obtain multiple business exception resolution strategies and identification data used to characterize the importance of each of the multiple business exception resolution strategies.

[0132] The sorting submodule is used to sort multiple business exception resolution strategies based on multiple identification data and display the sorted multiple business exception resolution strategies.

[0133] According to an embodiment of the present disclosure, the data processing device further includes: an acquisition module, a result determination module, and an evaluation module.

[0134] The acquisition module is used to obtain the business execution data of the business.

[0135] The result determination module is used to determine the solution result of the target abnormality identification result based on the business execution data and the warning data.

[0136] The evaluation module is used to obtain a timeliness evaluation result for the business based on the processing time and warning data of the target anomaly identification result, wherein the processing time is determined based on the solution result.

[0137] According to an embodiment of the present disclosure, the data processing device further includes: an optimization module.

[0138] The optimization module is used to optimize the solution generation model for generating the business exception resolution strategy based on the business execution data, the business exception resolution strategy and the decision preference identifier when it is determined that there is a mismatch between the business exception resolution strategy and the business execution data, wherein the decision preference identifier includes identification data for characterizing whether the business execution data and the business exception resolution strategy are respectively adopted.

[0139] According to an embodiment of the present disclosure, the template determination module includes: a template determination submodule.

[0140] The template determination submodule is used to determine the abnormal warning template corresponding to the abnormal type from multiple abnormal warning templates based on the abnormal type and template mapping relationship of the target abnormality recognition result, wherein the template mapping relationship represents the corresponding relationship between the abnormal warning template and the abnormal type.

[0141] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0142] According to an embodiment of the present disclosure, an electronic device 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 a method as in the embodiment of the present disclosure.

[0143] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute a method as described in an embodiment of the present disclosure.

[0144] According to an embodiment of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, the method according to the embodiment of the present disclosure is implemented.

[0145] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0146] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0147] A number of components in the device 800 are connected to an input / output (I / O) interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0148] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0149] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0151] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0152] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0153] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0154] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0155] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0156] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A data processing method, comprising: Parsing business target data of a business to determine a plurality of abnormality identification results of the business, wherein the business target data represents expected execution requirements of the business; In response to a confirmation result for the abnormal identification result, based on a target abnormal identification result indicated by the confirmation result, determining an abnormal warning template corresponding to the target abnormal identification result, wherein the target abnormal identification result includes at least one of the plurality of abnormal identification results, and the abnormal warning template includes a to-be-filled field and a fixed field; Based on the business basic data and the business target data of the business, determining the field content for filling in the to-be-filled field to obtain early warning data, wherein the business basic data includes resource data for processing the business; and Based on the warning data, the basic business data and the business target data, a business anomaly resolution strategy is obtained.

2. The method according to claim 1, wherein: The business target data of the business is parsed to determine multiple abnormality identification results of the business, including: Inputting the business target data into the anomaly recognition large model to obtain a model recognition result; Matching the business target data with the decision tree to obtain a rule recognition result; and Based on the model recognition result and the rule recognition result, a plurality of abnormality recognition results are obtained.

3. The method according to claim 1 or 2, wherein: The determining, based on the business basic data and the business target data of the business, the field content to be filled in the to-be-filled field to obtain the early warning data includes: Based on the fixed fields, determining target content from the business basic data and the business target data, wherein the target content is used to determine the fields to be filled in; and The early warning data is obtained based on the target content and a predetermined threshold, wherein the predetermined threshold is determined from specification data related to the business.

4. The method according to any one of claims 1 to 3, wherein: The business anomaly resolution strategy is obtained based on the warning data, the business basic data and the business target data. The business anomaly resolution strategy includes: Inputting the warning data, the basic business data and the business target data into a solution generation model to obtain a plurality of business exception solution strategies and attention identification data for characterizing the importance of each of the plurality of business exception solution strategies; and Based on the multiple identification data, the multiple business exception resolution strategies are sorted, and the sorted multiple business exception resolution strategies are displayed.

5. The method according to any one of claims 1 to 4, further comprising: Acquiring business execution data of the business; Determining a solution to the target abnormality identification result based on the business execution data and the early warning data; as well as Based on the processing time of the target anomaly identification result and the warning data, a timeliness evaluation result for the business is obtained, wherein the processing time is determined based on the solution result.

6. The method according to claim 5, further comprising: When it is determined that there is a mismatch between the business exception resolution strategy and the business execution data, a large model for generating a solution for generating the business exception resolution strategy is optimized based on the business execution data, the business exception resolution strategy and a decision preference identifier, wherein the decision preference identifier includes identification data for characterizing whether the business execution data and the business exception resolution strategy are respectively adopted.

7. The method according to any one of claims 1 to 6, wherein: The determining of an abnormality warning template corresponding to the target abnormality recognition result indicated by the confirmation result includes: Based on the abnormality type and template mapping relationship of the target abnormality recognition result, an abnormality warning template corresponding to the abnormality type is determined from multiple abnormality warning templates, wherein the template mapping relationship represents the corresponding relationship between the abnormality warning template and the abnormality type.

8. A data processing device, comprising: A parsing module, used to parse target business data of a business and determine a plurality of abnormal identification results of the business, wherein the business target data represents the expected execution requirements of the business; A template determination module, configured to determine, in response to a confirmation result for the abnormal identification result, an abnormal warning template corresponding to the target abnormal identification result based on a target abnormal identification result indicated by the confirmation result, wherein the target abnormal identification result includes at least one of the plurality of abnormal identification results, and the abnormal warning template includes a field to be filled in and a fixed field; an early warning module, configured to determine, based on basic business data of the business and the target business data, field content to be filled in the to-be-filled field, and obtain early warning data, wherein the basic business data includes resource data for processing the business; and The exception resolution module is used to obtain a business exception resolution strategy based on the warning data, the basic business data and the target business data.

9. The device according to claim 8, wherein: The parsing module comprises: The model analysis submodule is used to input the target business data into the anomaly recognition large model to obtain the model recognition result; A rule parsing submodule, used to match the target business data with the decision tree to obtain a rule recognition result; and The parsing submodule is used to obtain a plurality of abnormality identification results based on the model identification results and the rule identification results.

10. The device according to claim 8 or 9, wherein: The early warning module comprises: an extraction submodule, configured to determine target content from the basic business data and the target business data based on the fixed fields, wherein the target content is used to determine the fields to be filled in; and The early warning submodule is used to obtain the early warning data based on the target content and a predetermined threshold, wherein the predetermined threshold is determined from specification data related to the business.

11. The device according to any one of claims 8 to 10, wherein: The exception resolution module includes: An input submodule, used for inputting the warning data, the basic business data and the target business data into the solution generation model, to obtain a plurality of the business exception solution strategies and identification data for characterizing the importance of each of the plurality of the business exception solution strategies; and The sorting submodule is used to sort the multiple business exception resolution strategies based on the multiple identification data, and display the sorted multiple business exception resolution strategies.

12. The device according to any one of claims 8 to 11, further comprising: An acquisition module, used to acquire the business execution data of the business; A result determination module, used to determine a solution result of the target abnormality identification result based on the business execution data and the warning data; as well as An evaluation module is used to obtain a timeliness evaluation result for the business based on the processing time of the target abnormality identification result and the warning data, wherein the processing time is determined based on the solution result.

13. The apparatus according to claim 12, further comprising: An optimization module is used to optimize a solution generation model for generating the business exception resolution strategy based on the business execution data, the business exception resolution strategy and a decision preference identifier when it is determined that there is a mismatch between the business exception resolution strategy and the business execution data, wherein the decision preference identifier includes identification data for characterizing whether the business execution data and the business exception resolution strategy are respectively adopted.

14. The device according to any one of claims 8 to 13, wherein: The template determination module comprises: The template determination submodule is used to determine an abnormal warning template corresponding to the abnormal type from multiple abnormal warning templates based on the abnormal type of the target abnormality identification result and the template mapping relationship, wherein the template mapping relationship represents the corresponding relationship between the abnormal warning template and the abnormal type.

15. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

17. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images