Data processing methods, apparatus, computer equipment and storage media

By performing point analysis and data processing on the feedback data and operation paths of the banking business system, and using the data processing model to automatically respond to or transfer feedback issues, the problem of low flexibility in problem collection and processing in traditional systems has been solved, achieving efficient and unified management and flexible feedback.

CN116843443BActive Publication Date: 2026-11-17INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202310875669.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-07-17
Publication Date
2026-11-17
Estimated Expiration
2043-07-17

AI Technical Summary

Technical Problem

The problem feedback module in traditional banking systems results in low flexibility in problem collection and processing, and makes it impossible to efficiently and uniformly manage user feedback problems from multiple business systems.

Method used

By acquiring problem feedback data and operation paths from various business systems, we perform pause analysis, use data processing models to determine problem categories, and automatically reply when a response text exists; otherwise, we provide feedback based on the problem flow path. This integrates a feedback collection pre-processing module, a data processing module, an output module, and a problem flow feedback module, thereby improving the efficiency and flexibility of problem collection and processing.

Benefits of technology

It has enabled efficient and unified management of issues in banking business systems, improved the flexibility of issue collection and processing, and enhanced the efficiency and flexibility of issue feedback.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116843443B_ABST
    Figure CN116843443B_ABST
Patent Text Reader

Abstract

This application relates to a data processing method, apparatus, computer equipment, storage medium, and computer program product, and pertains to the field of artificial intelligence technology. The method includes: acquiring problem feedback data and operation paths from various business systems; performing pause analysis on the operation paths to obtain pause data; and processing the problem feedback data and pause data according to a data processing model to determine the corresponding problem category; the data processing model is the data processing model corresponding to the current business system; when a problem reply text corresponding to the problem category exists, outputting the problem reply text to the feedback interface; when no problem reply text corresponding to the problem category exists, feeding back the problem feedback data and pause data according to the problem flow path. This method improves the flexibility of problem feedback.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a data processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] As banking operations expand, different services require different operating systems, resulting in a large number of such systems within a bank. After each system goes live, user feedback needs to be collected so that maintenance personnel can address these issues and perform necessary repairs.

[0003] In traditional technology, user feedback is collected through a separate issue feedback module deployed within each business system. Then, the system administrators in each business system respond to the collected issues, thus completing the processing of user feedback from each business system.

[0004] However, currently, issues are collected through the issue feedback modules of each business system, and the system administrators of each business system answer the issues reported by users, resulting in low flexibility in issue collection and processing. Summary of the Invention

[0005] Therefore, it is necessary to provide a data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0006] Firstly, this application provides a data processing method. The method includes:

[0007] Obtain problem feedback data and operation paths from various business systems;

[0008] The operation path is analyzed for pauses to obtain pause data. The problem feedback data and the pause data are then processed according to a data processing model to determine the problem category to which the problem feedback data and the pause data belong. The data processing model is the data processing model corresponding to the current business system.

[0009] When a response text for the question category exists, the response text will be output to the feedback interface.

[0010] If there is no corresponding response text for the question category, the question feedback data and the pause data will be fed back according to the question flow path.

[0011] In one embodiment, before performing pause analysis on the operation path to obtain pause data, and processing the problem feedback data and the pause data according to a data processing model to determine the corresponding problem category of the problem feedback data and the pause data, the method further includes:

[0012] The sample pause data and the sample problem feedback data from each business system are respectively input into the data processing model to obtain a first processing result corresponding to the pause data and a second processing result corresponding to the problem feedback data; the pause data includes a first sample label and the problem feedback data includes a second sample label.

[0013] The first processing result is compared with the first sample label to determine the first loss of the data processing model, and the second processing result is compared with the second sample label to determine the second loss of the data processing model.

[0014] When the first loss and the second loss meet the preset conditions, the training of the data processing model is stopped, and the trained data processing model is obtained.

[0015] In one embodiment, the step of performing pause analysis on the operation path to obtain pause data includes:

[0016] The operation path is broken down according to the business functions contained in each business system to obtain the sub-operation path corresponding to each business function;

[0017] Record the repeated paths in each of the sub-operation paths to obtain the pause point data.

[0018] In one embodiment, after splitting the operation path for the business functions included in each business system to obtain sub-operation paths corresponding to each business function, the method further includes:

[0019] The sub-operation paths are analyzed for the business functions contained in each business system to obtain the usage frequency of each business function;

[0020] The multiple business functions whose usage frequency is greater than a preset threshold are identified as high-frequency functions, and the problem feedback data and the pause data corresponding to the high-frequency functions are marked and displayed.

[0021] In one embodiment, when there is no corresponding question reply text for the question category, feeding back the question feedback data and the pause data according to the question flow path includes:

[0022] If there is no corresponding response text for the question category, determine the question flow path corresponding to the question category based on the question feedback data and the question category corresponding to the operation path;

[0023] The problem feedback data and the pause point data are fed back according to the problem flow path.

[0024] In one embodiment, after feeding back the problem feedback data and the pause point data according to the problem flow path, the method further includes:

[0025] Receive response information for the feedback data of the problem and the pause data, and output and display the response information in the feedback interface.

[0026] In one embodiment, when there is no corresponding question response text for the question category, after feeding back the question feedback data and the pause data according to the question flow path, the method further includes:

[0027] If no response text corresponding to the problem category of the problem feedback data and the pause data is received, the problem category will be updated to an unclosed loop problem.

[0028] The non-closed-loop rate of each business system is calculated based on the number of non-closed-loop problem categories in each business system and the number of problem categories in each business system.

[0029] An alarm is issued for any business system whose non-closed-loop rate exceeds a preset threshold.

[0030] In one embodiment, after feeding back the problem feedback data and the pause point data according to the problem flow path, the method further includes:

[0031] According to a preset strategy, the problem feedback data and pause data of each business system are statistically processed to obtain the statistical results of each business system for the problem feedback data or the pause data.

[0032] The statistical results of each business system will be output and displayed; the statistical results are used to reflect the problem handling status of the business systems.

[0033] Secondly, this application also provides a data processing apparatus. The apparatus includes:

[0034] The feedback collection module is used to obtain problem feedback data and operation paths from various business systems;

[0035] The data processing module is used to perform pause analysis on the operation path to obtain pause data, and to process the problem feedback data and the pause data according to the data processing model to determine the problem category to which the problem feedback data and the pause data belong; the data processing model is the data processing model corresponding to the current business system;

[0036] The output module is used to output the question reply text to the feedback interface when there is a question reply text corresponding to the question category;

[0037] The problem flow feedback module is used to feed back the problem feedback data and the pause data according to the problem flow path when there is no corresponding problem reply text for the problem category.

[0038] In one embodiment, the device further includes:

[0039] The sample training module is used to input the sample pause data and the sample problem feedback data from each business system into the data processing model to obtain a first processing result corresponding to the pause data and a second processing result corresponding to the problem feedback data; the pause data includes a first sample label and the problem feedback data includes a second sample label.

[0040] The loss comparison module is used to compare the first processing result with the first sample label to determine the first loss of the data processing model, and to compare the second processing result with the second sample label to determine the second loss of the data processing model.

[0041] The discrimination module is used to stop training the data processing model when the first loss and the second loss meet preset conditions, so as to obtain the trained data processing model.

[0042] In one embodiment, the data processing module is specifically used for:

[0043] The operation path is broken down according to the business functions contained in each business system to obtain the sub-operation path corresponding to each business function;

[0044] Record the repeated paths in each of the sub-operation paths to obtain the pause point data.

[0045] In one embodiment, the device further includes:

[0046] The frequency analysis module is used to analyze the sub-operation paths for the business functions contained in each business system to obtain the usage frequency corresponding to each business function;

[0047] The high-frequency function determination module is used to determine multiple business functions whose usage frequency is greater than a preset threshold as high-frequency functions, and to mark and display the problem feedback data and the pause data corresponding to the high-frequency functions.

[0048] In one embodiment, the problem flow feedback module is specifically used for:

[0049] If there is no corresponding response text for the question category, determine the question flow path corresponding to the question category based on the question feedback data and the question category corresponding to the operation path; and feed back the question feedback data and the pause data according to the question flow path.

[0050] In one embodiment, the device further includes:

[0051] The output display module is used to receive response information for the feedback data of the problem and the pause data, and to output and display the response information in the feedback interface.

[0052] In one embodiment, the device further includes:

[0053] The update module is used to update the problem category to an unclosed loop problem if no problem feedback data and the pause data corresponding to the problem category are received.

[0054] The non-closed-loop rate calculation module is used to calculate the non-closed-loop rate of each business system based on the number of non-closed-loop problem categories in each business system and the number of problem categories in each business system.

[0055] The alarm module is used to issue alarms for business systems whose non-closed-loop rate is greater than a preset threshold.

[0056] In one embodiment, the device further includes:

[0057] The statistics module is used to perform statistical processing on the problem feedback data and pause data of each business system according to a preset strategy, and to obtain the statistical results of each business system on the problem feedback data or the pause data.

[0058] The output display module is used to output and display the statistical results of each business system; the statistical results are used to reflect the problem handling status of the business system.

[0059] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0060] Obtain problem feedback data and operation paths from various business systems;

[0061] The operation path is analyzed for pauses to obtain pause data. The problem feedback data and the pause data are then processed according to a data processing model to determine the problem category to which the problem feedback data and the pause data belong. The data processing model is the data processing model corresponding to the current business system.

[0062] When a response text for the question category exists, the response text will be output to the feedback interface.

[0063] If there is no corresponding response text for the question category, the question feedback data and the pause data will be fed back according to the question flow path.

[0064] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0065] Obtain problem feedback data and operation paths from various business systems;

[0066] The operation path is analyzed for pauses to obtain pause data. The problem feedback data and the pause data are then processed according to a data processing model to determine the problem category to which the problem feedback data and the pause data belong. The data processing model is the data processing model corresponding to the current business system.

[0067] When a response text for the question category exists, the response text will be output to the feedback interface.

[0068] If there is no corresponding response text for the question category, the question feedback data and the pause data will be fed back according to the question flow path.

[0069] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0070] Obtain problem feedback data and operation paths from various business systems;

[0071] The operation path is analyzed for pauses to obtain pause data. The problem feedback data and the pause data are then processed according to a data processing model to determine the problem category to which the problem feedback data and the pause data belong. The data processing model is the data processing model corresponding to the current business system.

[0072] When a response text for the question category exists, the response text will be output to the feedback interface.

[0073] If there is no corresponding response text for the question category, the question feedback data and the pause data will be fed back according to the question flow path.

[0074] The aforementioned data processing methods, devices, computer equipment, storage media, and computer program products analyze and process user operation paths to obtain user pause data. This pause data reflects the user's usage of the business system. Data processing models are used to process the pause data or user feedback data to obtain the problem categories of the feedback data or pause data. Automatic responses are provided when corresponding problem reply texts exist; otherwise, the problem category is fed back based on the problem flow path. This allows for the collection of problems from various business systems using multiple feedback formats, improving the efficiency of problem collection and response. Furthermore, providing feedback to problems from various business systems based on the problem flow path enhances the flexibility of problem feedback. Attached Figure Description

[0075] Figure 1 This is a diagram illustrating the application environment of a data processing method in one embodiment.

[0076] Figure 2 This is a flowchart illustrating a data processing method in one embodiment;

[0077] Figure 3 This is a flowchart illustrating a data processing model training method in one embodiment;

[0078] Figure 4 This is a flowchart illustrating a method for analyzing operation paths and determining pause data in one embodiment.

[0079] Figure 5 This is a flowchart illustrating a method for determining high-frequency functions in one embodiment;

[0080] Figure 6 This is a flowchart illustrating a method for determining a problem flow path in one embodiment;

[0081] Figure 7 This is a flowchart illustrating a method for determining the problem flow path in one embodiment;

[0082] Figure 8 This is a schematic diagram illustrating an example of a problem flow path in one embodiment;

[0083] Figure 9 This is a flowchart illustrating a method for generating alarms for various business systems in one embodiment;

[0084] Figure 10 This is a flowchart illustrating a method for performing statistics on various business systems in one embodiment;

[0085] Figure 11 This is a structural block diagram of a data processing device in one embodiment;

[0086] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0087] 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.

[0088] In one embodiment, a data processing method is provided, which can be applied to, for example... Figure 1 The unified problem management system shown includes: a feedback collection module, a data processing module, an output module, a problem flow feedback module, a statistical analysis module, and a model training module. Specifically, the feedback collection module includes a problem feedback data collection unit and an operation path collection unit; the data processing module includes a frequency analysis module and a high-frequency function determination module; the problem flow feedback module includes an output display module; the statistical analysis module includes a statistics module, an output display module, an update module, a non-closed-loop rate calculation module, and an alarm module; and the model training module includes a sample training module, a loss comparison module, and a discrimination module.

[0089] This embodiment illustrates the integration of a unified management system for this problem into a terminal. It is understood that this system can also be integrated into a server, or into a system that includes both a terminal and a server, and the data processing methods within the system are implemented through the interaction between the terminal and the server. In this embodiment, as... Figure 2 As shown, the method includes the following steps:

[0090] Step 202: Obtain problem feedback data and operation paths from each business system.

[0091] Each business system includes a feedback collection front-end module, which includes a problem feedback data collection unit and an operation path collection unit.

[0092] The problem feedback data collection unit is used to collect user problem feedback data and then send the problem feedback data back to the terminal.

[0093] The operation path collection unit is used to collect the user's operation path, which includes the number of times the user clicks on the function menus of various business systems, the page dwell time, and the system performance index data at a given time.

[0094] In this embodiment, each business system has a deployed problem feedback data collection unit and an operation path collection unit. Users can input problem data to be reported in the problem feedback data collection unit. This problem data may include system name, problem category, problem description, urgency level, system screenshot (which can be an uploaded local file, a one-click screenshot, or a copied and pasted image), problem submitter information, expected response date, etc. The feedback collection front-end module deployed in each business system has a unified interface style. The terminal returns the problem data input by the user in the current business system as problem feedback data, and the terminal obtains the problem feedback data from each business system.

[0095] When users utilize the functions of various business systems, the operation path collection unit automatically captures user clicks on each function menu and records the duration of user dwell time on each function page, thus collecting the terminal's operation paths for each business system in real time. Specifically, for each business function's corresponding function menu, the terminal captures user clicks on the function menu in real time, incrementing the cumulative number of function menu clicks by 1, and forming an operation path based on the order in which the user clicks on each function menu.

[0096] Step 204: Perform pause analysis on the operation path to obtain pause data, and process the problem feedback data and pause data according to the data processing model to determine the corresponding problem category of the problem feedback data and pause data.

[0097] The data processing model is a natural language processing model.

[0098] Each business system has an independent data processing model, which is the data processing model corresponding to the current business system.

[0099] In this embodiment, the terminal performs pause analysis on each operation path in each business system according to the function menu of each business system to obtain pause data in each business system, wherein this pause data is text data. The terminal inputs the pause data and the question feedback data into a data processing model to determine the question category to which the question feedback data and the pause data belong. The data processing model can be a natural language processing model such as FastText, TextCNN, ULMFit, BERT, etc. This application uses the FastText model as an example for illustration. The terminal inputs the word sequences of the text data type question feedback data and the pause data into the FastText model respectively. The FastText model outputs the probability that the sequence belongs to different question categories.

[0100] Specifically, when the terminal receives problem feedback data, it inputs the data into the data processing model in real time. The model calculates the probability that the feedback data belongs to different categories and identifies the category with the highest probability. When the terminal receives operation paths from various business systems, it performs pause analysis on these paths in real time to obtain pause data. This pause data is then input into the data processing model, which calculates the probability that the pause data belongs to different categories and identifies the category with the highest probability. Specifically, for pause data corresponding to the current operation path, the terminal registers menu functions on pages exceeding a preset dwell time in the database as pause data, based on the user's dwell time on each function page in each business system. The terminal also analyzes the continuity of user operations on each function menu in each business system, registering function menus on operation paths that do not meet continuity criteria in the database as pause data.

[0101] Step 206: When there is a corresponding question reply text for the question category, output the question reply text to the feedback interface.

[0102] In this embodiment, the terminal retrieves the corresponding problem response text from the database based on the problem category of the pause data or problem feedback data. If a problem response text for the corresponding problem category exists in the database, it is output to the feedback interface as the problem response text for the corresponding problem category of the current pause data or problem feedback data. Optionally, if the problem corresponding to the problem category is pause data identified by the operation path collection unit, the terminal feeds back the problem response text corresponding to the pause data to the feedback interface of the business system maintenance personnel to assist the maintenance personnel in making decisions regarding the maintenance of the business system; if the problem corresponding to the problem category is problem feedback data collected by the problem feedback data collection unit, the terminal feeds back the problem response text corresponding to the problem category to the user's problem feedback data collection unit to assist the user in resolving the reported problem.

[0103] Step 208: When there is no corresponding question reply text for the question category, the question feedback data and pause data are fed back according to the question flow path.

[0104] In this embodiment, the terminal retrieves the corresponding question reply text from the database based on the question category to which the question feedback data and pause data belong. If no corresponding question reply text exists in the database, the terminal determines the question flow path corresponding to the question feedback data and pause data according to the preset question flow path, and then sends the question feedback data and pause data back to the user terminal of the corresponding person according to the question flow path corresponding to the question feedback data and pause data.

[0105] In the above data processing method, by analyzing and processing the user's operation path, user pause data is obtained. User pause data can reflect the user's usage of the business system. According to the data processing model, the pause data or user problem feedback data is processed to obtain the problem categories of problem feedback data or pause data. When a corresponding problem reply text exists, an automatic reply is given. When no corresponding problem reply text exists, the problem category is fed back according to the problem flow path. Problems from various business systems can be collected according to multiple feedback forms, improving the efficiency of problem collection and response. At the same time, feeding back problems from various business systems according to the problem flow path can improve the flexibility of problem feedback.

[0106] In one embodiment, such as Figure 3 As shown, before step 204 performs pause analysis on the operation path to obtain pause data, and processes the problem feedback data and pause data according to the data processing model to determine the corresponding problem category, the method further includes:

[0107] Step 302: Input the sample pause data and the sample problem feedback data from each business system into the data processing model to obtain the first processing result corresponding to the pause data and the second processing result corresponding to the problem feedback data.

[0108] The sample pause data includes the first sample label, and the sample problem feedback data includes the second sample label.

[0109] In this embodiment, the terminal uses the sample pause data labeled with the first sample label and the sample question feedback data labeled with the second sample label as training samples for the data processing model, and inputs the sample pause data and the sample question feedback data into the data processing model respectively to obtain the processing result of the data processing model on the sample pause data, i.e., the first processing result, and the processing result of the data processing model on the sample question feedback data, i.e., the second processing result.

[0110] In an optional embodiment, the training samples for the data processing model may further include accumulated problem feedback data and pause data after the data processing model has been running continuously. Specifically, within a preset time period, the terminal retrieves pause data and problem feedback data from the problem details table in the database. This pause data and problem feedback data represent the business system corresponding to the data processing model, and the status of this pause data and problem feedback data is "confirmed and passed." If the status condition of "confirmed and passed" is met, the terminal uses this pause data and problem feedback data as training samples for the data processing model and performs periodic training on the data processing model corresponding to the current business system. When the accuracy of the data processing model in each business system reaches a preset threshold, the terminal deploys the data processing model online as a usable data processing model for the current business system. For example, within a preset time period, the terminal randomly selects 70% of the pause data and problem feedback data that meet the state conditions from the problem details table in the database as training samples, and uses the corresponding problem categories as labels to train the data processing model of the current business system. The terminal also uses 30% of the pause data and problem feedback data that meet the state conditions and their corresponding problem categories as the test dataset. The terminal then uses the trained data processing model based on the training samples to test the data processing model based on the test dataset. When the accuracy of the data processing model reaches 95%, it is deployed online as a usable data processing model for the current business system.

[0111] Step 304: Compare the first processing result with the first sample label to determine the first loss of the data processing model; compare the second processing result with the second sample label to determine the second loss of the data processing model.

[0112] In this embodiment, the terminal compares the first processing result with the first sample label to determine the first loss of the data processing model for processing the pause data, and compares the second processing result with the second sample label to determine the second loss of the data processing model for processing the problem feedback data.

[0113] Step 306: When the first loss and the second loss meet the preset conditions, stop training the data processing model and obtain the trained data processing model.

[0114] In this embodiment, the terminal has preset conditions for training data processing models in each business system. When training the data processing model corresponding to each business system, if the first loss and the second loss of the data processing model meet the preset conditions, the terminal stops training the data processing model and determines that the current data processing model is the trained data processing model.

[0115] In this embodiment, by training the data processing model corresponding to each business system, and using the trained data processing model to classify and identify the problem categories of problem feedback data and pause data, the accuracy of identifying the problem categories of problem feedback data and pause data can be improved.

[0116] In one embodiment, such as Figure 4 As shown, step 204 performs pause analysis on the operation path to obtain pause data, including:

[0117] Step 402: Decompose the operation path according to the business functions contained in each business system to obtain the sub-operation path corresponding to each business function.

[0118] In this embodiment, the terminal pre-stores a function menu path rule table, as shown in Table 1 below. This function menu path rule table is used to determine the various business functions included in the operation path. Different business systems have different business functions. The operation path represents the user's click path on the function menu within each business function. The terminal records the user's operation path according to the identifier corresponding to each function menu. For each business function included in each business system, the terminal splits the function menus corresponding to different functions in the operation path to obtain sub-operation paths corresponding to each business function. For example, as shown in Table 1 below, Table 1 lists the function menus corresponding to different business functions in the business system:

[0119] Table 1

[0120] Business System Business Functions Start Menu On-the-spot menu 1 On-the-spot menu 2 End Menu A Business Registration A1 A2 A Document Inquiry B1 B2 B3 A Business review C1 C2 C3 C4

[0121] For example, if a user's operation path is B1, B2, B3, A1, A1, A2, C1, C2, C2, C3, C4, A1, A2, A1, A2, where B1, B2, and B3 are sub-operation paths for the same business function, then the operation path is split to obtain the sub-operation paths corresponding to each business function, namely B1, B2, B3; A1; A1, A2; C1, C2, C2, C3, C4; A1, A2; A1, A2.

[0122] Step 404: Record the repeated paths in each sub-operation path to obtain the pause point data.

[0123] In this embodiment, the terminal records the duplicate paths in each sub-operation path of each complete operation path and treats the duplicate paths as pause data. For example, in the sub-operation paths B1, B2, B3; A1; A1, A2; C1, C2, C2, C3, C4; A1, A2; A1, A2, if there is a duplicate path for function menu C2 in the sub-operation path C1, C2, C2, C3, C4, it indicates that there may be a problem with function menu C2 in business system A, and the terminal records function menu C2 in business system A as pause data.

[0124] In an optional embodiment, the operation path collection unit can record the user's dwell time data on each page. When the dwell time data of a certain function page exceeds a preset threshold, the terminal records the function page as a pause point.

[0125] In this embodiment, by collecting and analyzing the user's operation path in each business system in real time, the pause data of each business system is determined. The terminal can collect user problems in using each business system in a timely manner, so as to process the pause data of each business system and provide feedback on the problems, thereby improving the flexibility of problem feedback.

[0126] In one embodiment, such as Figure 5 As shown, after step 402 decomposes the operation path for the business functions contained in each business system to obtain the sub-operation path corresponding to each business function, the method further includes:

[0127] Step 502: Analyze the sub-operation paths of the business functions contained in each business system to obtain the usage frequency of each business function.

[0128] In this embodiment, the terminal obtains the usage frequency of each business function based on the operation path corresponding to each business function in each sub-operation path of each business system.

[0129] Step 504: Identify multiple business functions whose usage frequency exceeds a preset threshold as high-frequency functions, and mark and display the problem feedback data and pause data corresponding to the high-frequency functions.

[0130] In this embodiment, the terminal includes a preset high-frequency function threshold. After collecting the operation paths of each business system, the terminal counts the usage frequency of the business function corresponding to each operation path in real time. The business function whose usage frequency is greater than the preset high-frequency function threshold is identified as a high-frequency function. After the pause data of the operation path containing the high-frequency function is fed back, the terminal marks and displays the operation path containing the high-frequency function in the display interface of the user terminal of the corresponding person.

[0131] In an optional embodiment, the terminal determines a preset number of high-frequency functions and their rankings based on the usage frequency of each service function. For example, for the top N high-frequency functions (where N is a preset number of high-frequency functions), the terminal sorts them according to the usage frequency of the N high-frequency functions. After the pause data of the operation data corresponding to the top N high-frequency functions is fed back, the terminal displays a mark indicating that the operation path belongs to the top N high-frequency functions on the display interface of the user terminal of the corresponding person.

[0132] In this embodiment, by identifying high-frequency functions in each business system and marking the corresponding operation paths, the relevant personnel can be prompted to prioritize handling the pause data in the high-frequency functions, thereby enhancing the pertinence of problem feedback and improving the flexibility of problem feedback.

[0133] In one embodiment, such as Figure 6 As shown, in step 208, when there is no corresponding question reply text for the question category, the question feedback data and pause data are fed back according to the question flow path, including:

[0134] Step 602: When there is no corresponding question reply text for the question category, determine the question flow path corresponding to the question category based on the question feedback data and the question category corresponding to the operation path.

[0135] Different problem categories in different business systems correspond to different problem flow paths.

[0136] In this embodiment, the terminal includes a preset problem routing path, which is the routing path corresponding to the problem category. If there is no problem reply text corresponding to the problem category, such as... Figure 7 As shown, the terminal determines the problem flow path corresponding to the problem category based on the problem feedback data output by the data processing model and the problem category of the operation path, according to the preset problem flow path initialization method.

[0137] In an optional embodiment, the terminal pre-configures rules and processes such as timeliness, monitoring, problem flow path, and response role, as shown in Table 2 below.

[0138] Table 2

[0139] Serial Number System user group categories Problem Categories Rule Type Rule Description Parameter value 1 ALL Consultation Questions aging Question response time 2 2 ALL System malfunction aging Question response time 1 3 ALL Demand issues aging Question response time 3 4 ALL ALL monitor Non-closed loop rate 50% 5 ALL ALL monitor First-order closed-loop rate 30% 6 ALL Consultation Questions Problem Flow Path Issue Submission 1 7 ALL Consultation Questions Problem Flow Path frontline staff reply 2 8 ALL Consultation Questions Problem Flow Path Problem confirmed 3 9 ALL System malfunction Problem Flow Path Issue Submission 1 10 ALL System malfunction Problem Flow Path frontline staff reply 2 11 ALL System malfunction Problem Flow Path Problem confirmed 3 12 ALL Demand issues Problem Flow Path Issue Submission 1 13 ALL Demand issues Problem Flow Path frontline staff reply 2 14 ALL Demand issues Problem Flow Path Product Manager Role Analysis 3 15 ALL Demand issues Problem Flow Path Determine version plan 4 16 ALL Demand issues Problem Flow Path Problem confirmed 5 17 For customers Consultation Questions Problem Flow Path Issue Submission 1 18 For customers Consultation Questions Problem Flow Path frontline staff reply 2 19 For customers Consultation Questions Problem Flow Path Review by the auditing staff 3 20 For customers Consultation Questions Problem Flow Path Problem confirmed 4 21 ALL Consultation Questions Response post role frontline staff reply Support Manager 22 ALL System malfunction Response post role frontline staff reply Development Manager 23 ALL Demand issues Response post role frontline staff reply Product Manager 24 ……

[0140] Among them, numbers 1-3 are timeliness rules, representing the timeliness rules for answering questions of each question category. For example, for a consultation question with a parameter value of 2, the timeliness rule is that the consultation question must be answered within 2 days. Numbers 4 and 5 are monitoring rules, which monitor the non-closure rate and first-loop closure rate of feedback data and pause data for questions in each business system. For example, when the non-closure rate of a certain business system is lower than 50%, the terminal will issue an alarm for that business system; when the first-loop closure rate of a certain business system is lower than 30%, the terminal will issue an alarm for that system. Numbers 6-8 represent the default process steps for consultation questions. The system user group category is "ALL", which means that the current rule is effective when no separate rules are set for a certain category of system. For the rules of question flow path, the parameter value is the flow order of the current question flow path in the process. Numbers 9-11 are the default question flow paths for system abnormal questions. Figure 8 As shown, numbers 12-16 represent the default issue flow path for requirement-related issues. Numbers 17-20 represent issues submitted by customers within the system's user group category "Customer-Oriented," and the terminal has a separate issue flow path for this category. Numbers 21-23 define the rules for the response role. For example, for all business system inquiries, the frontline response personnel are support managers; for system anomaly issues, the frontline response personnel are development managers; and for requirement-related issues, the frontline response personnel are product managers.

[0141] Step 604: Feed back the problem feedback data and the pause point data according to the problem flow path.

[0142] In this embodiment, the terminal feeds back the current problem feedback data and pause data to the user terminal of the person corresponding to the problem flow path according to the problem category to which the problem feedback data and pause data belong.

[0143] In this embodiment, when there is no corresponding problem response text for a problem category, the problem feedback data and operation path are fed back through the problem flow path. This allows the problem feedback data and pause data from different business systems to be fed back to the user terminals of the corresponding personnel in a targeted manner, which can improve the flexibility of problem feedback.

[0144] In one embodiment, after step 604 feeds back the problem feedback data and the pause point data according to the problem flow path, the method further includes:

[0145] It receives response information for problem feedback data and pause data, and outputs and displays the response information in the feedback interface.

[0146] In this embodiment, after the user terminal of the corresponding person returns the reply information, the terminal receives the reply information for the problem feedback data and the pause data. If the problem corresponding to the problem category is the pause data identified by the data processing module, the terminal records the reply data as the problem reply text in the problem details table of the database, and outputs and displays it. If the problem corresponding to the problem category is the problem feedback data collected by the problem feedback data collection unit, the terminal outputs and displays the reply information corresponding to the problem category in the user's problem feedback data collection unit to assist the user in resolving the feedback problem.

[0147] In this embodiment, by feeding back and displaying the response information of the corresponding personnel to the problem feedback data and pause data, the flexibility of the response information to the problem feedback data and pause data can be improved.

[0148] In one embodiment, such as Figure 9 As shown, in step 208, when there is no corresponding question reply text for the question category, after feeding back the question feedback data and pause data according to the question flow path, the method further includes:

[0149] Step 902: If no problem feedback data and pause data are received, the corresponding problem reply text for the problem category will be updated to "unclosed loop problem".

[0150] In this embodiment, if the personnel corresponding to the problem flow path of the problem feedback data and pause data do not provide a response to the problem feedback data and pause data, that is, the terminal does not receive the problem reply text corresponding to the problem feedback data and pause data, then the terminal updates the problem category to an unclosed loop problem. If the personnel corresponding to the problem flow path of the problem feedback data and pause data have provided a response to the problem feedback data and pause data, that is, the terminal has received the problem reply text corresponding to the problem feedback data and pause data, then the terminal updates the problem category to a closed loop problem.

[0151] Step 904: Calculate the non-closed loop rate of each business system based on the number of non-closed loop problem categories and the number of problem categories in each business system.

[0152] In this embodiment of the application, the terminal compares the number of problem categories with the total number of problem categories in each business system, and uses the ratio obtained from the comparison as the non-closed-loop rate of each business system.

[0153] Step 906: Issue an alarm for business systems whose non-closed-loop rate exceeds a preset threshold.

[0154] In this embodiment, the terminal includes preset alarm thresholds for each business system, and monitors the non-closed-loop rate in each business system. If the non-closed-loop rate of a certain business system is greater than the preset alarm threshold, the terminal will issue an alarm for that business system.

[0155] In this embodiment, by monitoring the non-closed-loop rate of each business system and issuing alarms for business systems with a non-closed-loop rate greater than a preset alarm threshold, the statistical analysis of each business system can be improved, assisting relevant personnel in making optimization decisions for each business system.

[0156] In one embodiment, such as Figure 10 As shown, after step 604 feeds back the problem feedback data and pause data according to the problem flow path, the method further includes:

[0157] Step 1002: Perform statistical processing on the problem feedback data and pause data of each business system according to the preset strategy to obtain the statistical results of each business system on the problem feedback data or pause data.

[0158] In this embodiment of the application, the terminal can perform statistical processing on the problem feedback data of each business system according to a preset strategy (statistical indicators). For example, the terminal can rank the business systems with the fastest response information feedback rate (top N business systems) or the business systems with the highest one-time resolution rate (top N business systems).

[0159] Step 1004: Output and display the statistical results of each business system.

[0160] The statistical results are used to reflect the problem handling status of the business system.

[0161] In this embodiment of the application, the terminal can output and display the statistical results of each business system, which is used to make a horizontal comparison of the feedback data on problem feedback data and pause data of each business system.

[0162] In this embodiment, by analyzing the feedback data on problems and pauses from each business system, statistical processing is performed on each business system according to a preset strategy. This enables a horizontal comparison of the business systems and visualizes the statistical results of each business system, assisting relevant personnel in making optimization decisions for each business system.

[0163] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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.

[0164] Based on the same inventive concept, this application also provides a data processing apparatus for implementing the data processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more data processing apparatus embodiments provided below can be found in the limitations of the data processing method described above, and will not be repeated here.

[0165] In one embodiment, such as Figure 11 As shown, a data processing device 1100 is provided, including: a feedback collection pre-module 1101, a data processing module 1102, an output module 1103, and a problem flow feedback module 1104, wherein:

[0166] The feedback collection front-end module 1101 is used to obtain problem feedback data and operation paths from various business systems;

[0167] The data processing module 1102 is used to perform pause analysis on the operation path, obtain pause data, and process the problem feedback data and pause data according to the data processing model to determine the problem category to which the problem feedback data and pause data belong; the data processing model is the data processing model corresponding to the current business system;

[0168] The output module 1103 is used to output the problem reply text to the feedback interface when there is a problem reply text corresponding to the problem category;

[0169] The problem flow feedback module 1104 is used to feed back problem feedback data and pause data according to the problem flow path when there is no problem reply text corresponding to the problem category.

[0170] In one embodiment, the device further includes:

[0171] The sample training module is used to input the sample pause data and the sample problem feedback data from each business system into the data processing model to obtain the first processing result corresponding to the pause data and the second processing result corresponding to the problem feedback data; the pause data includes the first sample label and the problem feedback data includes the second sample label.

[0172] The loss comparison module is used to compare the first processing result with the first sample label to determine the first loss of the data processing model, and to compare the second processing result with the second sample label to determine the second loss of the data processing model.

[0173] The discrimination module is used to stop training the data processing model when the first loss and the second loss meet preset conditions, and to obtain the trained data processing model.

[0174] In one embodiment, the data processing module is specifically used for:

[0175] The operation path is broken down according to the business functions contained in each business system to obtain the sub-operation path corresponding to each business function;

[0176] Record the repeated paths in each sub-operation path to obtain the pause point data.

[0177] In one embodiment, the device further includes:

[0178] The frequency analysis module is used to analyze the sub-operation paths of the business functions contained in each business system to obtain the usage frequency of each business function.

[0179] The high-frequency function determination module is used to identify multiple business functions whose usage frequency exceeds a preset threshold as high-frequency functions, and to mark and display the problem feedback data and pause data corresponding to the high-frequency functions.

[0180] In one embodiment, the problem flow feedback module is specifically used for:

[0181] When there is no corresponding response text for a problem category, the problem flow path corresponding to the problem category is determined based on the problem feedback data and the problem category corresponding to the operation path;

[0182] Feedback data on problems and pause points are fed back based on the problem flow path.

[0183] In one embodiment, the device further includes:

[0184] The output display module is used to receive response information for the question feedback data and pause data, and to output and display the response information in the feedback interface.

[0185] In one embodiment, the device further includes:

[0186] The update module is used to update the problem category to "unclosed loop problem" if no problem feedback data and pause data are received.

[0187] The non-closed loop rate calculation module is used to calculate the non-closed loop rate of each business system based on the number of non-closed loop problem categories and the number of problem categories in each business system.

[0188] The alarm module is used to issue alarms for business systems whose non-closed-loop rate exceeds a preset threshold.

[0189] In one embodiment, the device further includes:

[0190] The statistics module is used to perform statistical processing on the problem feedback data and pause data of each business system according to the preset strategy, and to obtain the statistical results of each business system on the problem feedback data or pause data.

[0191] The output display module is used to output and display the statistical results of each business system; the statistical results are used to reflect the problem handling status of the business system.

[0192] Each module in the aforementioned data processing 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, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0193] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 12 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. 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 stored in the non-volatile storage media. The database stores problem detail table data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a data processing method.

[0194] Those skilled in the art will understand that Figure 12The 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.

[0195] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0196] Obtain problem feedback data and operation paths from various business systems;

[0197] The operation path is analyzed for pauses to obtain pause data. The problem feedback data and pause data are then processed according to the data processing model to determine the corresponding problem categories. The data processing model is the data processing model corresponding to the current business system.

[0198] When there is a corresponding response text for a problem category, the response text will be output to the feedback interface;

[0199] When there is no corresponding reply text for the problem category, the problem feedback data and pause data will be fed back according to the problem flow path.

[0200] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0201] The sample pause data and the sample problem feedback data from each business system are respectively input into the data processing model to obtain the first processing result corresponding to the pause data and the second processing result corresponding to the problem feedback data; the pause data includes the first sample label and the problem feedback data includes the second sample label.

[0202] The first processing result is compared with the first sample label to determine the first loss of the data processing model; the second processing result is compared with the second sample label to determine the second loss of the data processing model.

[0203] When the first loss and the second loss meet the preset conditions, the training of the data processing model is stopped, and the trained data processing model is obtained.

[0204] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0205] The operation path is broken down according to the business functions contained in each business system to obtain the sub-operation path corresponding to each business function;

[0206] Record the repeated paths in each sub-operation path to obtain the pause point data.

[0207] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0208] Analyze the sub-operation paths for the business functions contained in each business system to obtain the usage frequency of each business function;

[0209] Multiple business functions whose usage frequency exceeds a preset threshold are identified as high-frequency functions, and the corresponding problem feedback data and pause data are marked and displayed.

[0210] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0211] When there is no corresponding response text for a problem category, the problem flow path corresponding to the problem category is determined based on the problem feedback data and the problem category corresponding to the operation path;

[0212] Feedback data on problems and pause points are fed back based on the problem flow path.

[0213] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0214] It receives response information for problem feedback data and pause data, and outputs and displays the response information in the feedback interface.

[0215] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0216] If no response text is received for the corresponding issue category of the issue feedback data and pause data, the issue category will be updated to an unclosed loop issue.

[0217] Calculate the non-closed loop rate of each business system based on the number of non-closed loop problem categories and the number of problem categories in each business system.

[0218] Alarms will be issued for business systems whose non-closed-loop rate exceeds a preset threshold.

[0219] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0220] Based on the preset strategy, the problem feedback data and pause data of each business system are statistically processed to obtain the statistical results of each business system on the problem feedback data or pause data.

[0221] The statistical results of each business system are output and displayed; the statistical results are used to reflect the problem handling status of the business systems.

[0222] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0223] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0224] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0225] 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 above methods. Any references to memory, 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, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0226] 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.

[0227] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. 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 application should be determined by the appended claims.

Claims

1. A data processing method, characterized by, The method includes: Obtain problem feedback data and operation paths from various business systems; The operation path is analyzed for pauses to obtain pause data. The problem feedback data and the pause data are then processed according to a data processing model to determine the problem category to which the problem feedback data and the pause data belong. The data processing model is the data processing model corresponding to the current business system. Specifically, performing pause analysis on the operation path to obtain pause data includes: splitting the operation path according to the business functions contained in each business system to obtain sub-operation paths corresponding to each business function; and recording the duplicate paths in each sub-operation path to obtain pause data. When a response text for the question category exists, the response text will be output to the feedback interface. If there is no corresponding response text for the question category, the question feedback data and the pause data will be fed back according to the question flow path.

2. The method of claim 1, wherein, Before performing pause analysis on the operation path to obtain pause data, and processing the problem feedback data and the pause data according to the data processing model to determine the corresponding problem category of the problem feedback data and the pause data, the method further includes: The sample pause data and the sample problem feedback data from each business system are respectively input into the data processing model to obtain a first processing result corresponding to the pause data and a second processing result corresponding to the problem feedback data; the pause data includes a first sample label and the problem feedback data includes a second sample label. The first processing result is compared with the first sample label to determine the first loss of the data processing model, and the second processing result is compared with the second sample label to determine the second loss of the data processing model. When the first loss and the second loss meet the preset conditions, the training of the data processing model is stopped, and the trained data processing model is obtained.

3. The method of claim 1, wherein, After splitting the operation path according to the business functions contained in each business system to obtain the sub-operation path corresponding to each business function, the method further includes: The sub-operation paths are analyzed for the business functions contained in each business system to obtain the usage frequency of each business function; The multiple business functions whose usage frequency is greater than a preset threshold are identified as high-frequency functions, and the problem feedback data and the pause data corresponding to the high-frequency functions are marked and displayed.

4. The method of claim 1, wherein, When there is no corresponding response text for the question category, the step of feeding back the question feedback data and the pause data according to the question flow path includes: If there is no corresponding response text for the question category, determine the question flow path corresponding to the question category based on the question feedback data and the question category corresponding to the operation path; The problem feedback data and the pause point data are fed back according to the problem flow path.

5. The method according to claim 4, characterized in that, After feeding back the problem feedback data and the pause point data according to the problem flow path, the method further includes: Receive response information for the feedback data of the problem and the pause data, and output and display the response information in the feedback interface.

6. The method according to claim 1 or 4, characterized in that, When there is no corresponding question reply text for the question category, after feeding back the question feedback data and the pause data according to the question flow path, the method further includes: If no response text corresponding to the problem category of the problem feedback data and the pause data is received, the problem category will be updated to an unclosed loop problem. The non-closed-loop rate of each business system is calculated based on the number of non-closed-loop problem categories in each business system and the number of problem categories in each business system. An alarm is issued for any business system whose non-closed-loop rate exceeds a preset threshold.

7. The method according to claim 4, characterized in that, After feeding back the problem feedback data and the pause point data according to the problem flow path, the method further includes: According to a preset strategy, the problem feedback data and pause data of each business system are statistically processed to obtain the statistical results of each business system for the problem feedback data or the pause data. The statistical results of each business system will be output and displayed; the statistical results are used to reflect the problem handling status of the business systems.

8. A data processing apparatus, characterized in that, The device includes: The feedback collection module is used to obtain problem feedback data and operation paths from various business systems; The data processing module is used to perform pause analysis on the operation path to obtain pause data, and to process the problem feedback data and the pause data according to the data processing model to determine the problem category to which the problem feedback data and the pause data belong; the data processing model is the data processing model corresponding to the current business system; Specifically, the data processing module is used to: break down the operation path according to the business functions contained in each business system to obtain sub-operation paths corresponding to each business function; record the duplicate paths in each sub-operation path to obtain pause data; The output module is used to output the question reply text to the feedback interface when there is a question reply text corresponding to the question category; The problem flow feedback module is used to feed back the problem feedback data and the pause data according to the problem flow path when there is no corresponding problem reply text for the problem category.

9. 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 to 7.

10. 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 to 7.

11. 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 to 7.

Citation Information

Patent Citations

  • Client application information feedback method and device, client and equipment

    CN113094507A

  • Problem management system

    CN115238043A