Abnormal data processing method and device, program product and storage medium

Abstract

The embodiment of the invention discloses an abnormal data processing method and device, a program product and a storage medium, and is suitable for the financial science and technology field, and the method comprises the steps: obtaining error submission information sent by a first user; displaying the error submission information to the second user, receiving an auditing result of the error submission information sent by the second user, and storing the error submission information into a pre-established solution database based on the auditing result; receiving query error information sent by a third user, and querying a target solution corresponding to the query error information in the solution database; and displaying the target solution to a third user, so that the third user solves the query error information based on the target solution. According to the method provided by the invention, the working efficiency of business personnel is improved, and the customer satisfaction and credibility can also be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of financial technology, and in particular to an abnormal data processing method, device, program product and storage medium. Background Technology

[0002] In the financial sector, such as banks and securities firms, business personnel (non-technical staff) may frequently encounter various information system errors during daily business promotion and customer service. Resolving these errors may require adjusting specific business parameters, and because business personnel lack technical background, they cannot directly understand the meaning of the errors, let alone quickly determine a solution.

[0003] Currently, the majority of error handling involves business personnel submitting error information to developers via email, phone, or a ticketing system. Developers then need to reproduce the problem, check logs, locate the issue, and provide suggested solutions. Business personnel then attempt to implement these solutions until the error is resolved. However, this process often takes hours or even days from reporting an issue to receiving feedback, severely impacting business continuity. Furthermore, the existence of technical jargon between business personnel and developers makes information transmission prone to errors, affecting the efficiency of all parties involved and reducing the efficiency of error information processing. Summary of the Invention

[0004] This invention provides an abnormal data processing method, device, program product, and storage medium, which can improve the work efficiency of staff from all parties and improve the processing efficiency of error information.

[0005] In a first aspect, embodiments of the present invention provide an abnormal data processing method, comprising:

[0006] Obtain error submission information sent by the first user; wherein, the error submission information includes error information and solutions to the error information; the error solutions include problem symptoms, error causes, business operation steps, guidance scripts, and parameter configuration items;

[0007] The error submission information is displayed to the second user, and the review result of the error submission information sent by the second user is received. Based on the review result, the error submission information is stored in the pre-established solution database.

[0008] Receive query error information sent by a third user, and query the solution database for the target solution corresponding to the query error information;

[0009] The target solution is presented to the third user so that the third user can resolve the query error information based on the target solution.

[0010] Secondly, embodiments of the present invention provide an abnormal data processing apparatus, the apparatus comprising:

[0011] The information acquisition module is used to acquire error submission information sent by the first user; wherein, the error submission information includes error information and solutions to the error information; the error solutions include problem symptoms, error causes, business operation steps, guidance scripts, and parameter configuration items;

[0012] The data storage module is used to display the error submission information to the second user, receive the review result of the error submission information sent by the second user, and store the error submission information in a pre-established solution database based on the review result;

[0013] The information query module is used to receive query error information sent by a third user and query the solution database for the target solution corresponding to the query error information;

[0014] The information processing module is used to display the target solution to the third user, so that the third user can resolve the query error information based on the target solution.

[0015] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the abnormal data processing method as described in any of the embodiments of the present invention.

[0016] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the abnormal data processing method as described in any of the embodiments of the present invention.

[0017] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the abnormal data processing method as described in any of the embodiments of the present invention.

[0018] In this embodiment of the invention, error submission information sent by a first user is obtained. This error submission information includes error details and a solution to the error. The solution includes the problem phenomenon, the cause of the error, business operation steps, guidance scripts, and parameter configuration items. The error submission information is displayed to a second user, and the review result of the error submission information sent by the second user is received. Based on the review result, the error submission information is stored in a pre-established solution database. A query error message sent by a third user is received, and a target solution corresponding to the query error message is queried in the solution database. The target solution is displayed to the third user, enabling the third user to resolve the query error message based on the target solution. This method, through error submission information including solutions to the error details, ensures that solutions can be released simultaneously with new problems, solving the problem of information lag. Business personnel can quickly and independently obtain error reporting guidance through the solution database, significantly reducing the time spent creating event tickets and facilitating cross-team workflows, thus accelerating the business promotion process. This improves the work efficiency of business personnel while also enhancing customer satisfaction and trust. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a first flowchart of an abnormal data processing method provided in an embodiment of the present invention;

[0021] Figure 2 This is a second flowchart of an abnormal data processing method provided in an embodiment of the present invention;

[0022] Figure 3 A third flowchart of an abnormal data processing method provided in an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of the structure of an abnormal data processing device provided in an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0026] Figure 1 This is a first flowchart of an abnormal data processing method provided by an embodiment of the present invention. The method of this embodiment can improve the work efficiency of staff from all parties and improve the processing efficiency of error information. The information collected in the method of this embodiment is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse. This method can be executed by an abnormal data processing device provided by an embodiment of the present invention, which can be implemented in software and / or hardware. The following embodiments will illustrate this using the integration of this device into an electronic device as an example. The electronic device can be a server or computer device equipped with a banking system, etc. (Refer to...) Figure 1 The method may specifically include the following steps:

[0027] Step 101: Obtain the error submission information sent by the first user.

[0028] The first user is the developer responsible for developing the business system. Error submission information includes error messages and solutions; the solutions include the problem description, the cause of the error, the business operation steps, guidance messages, and parameter configuration items. Specifically, during the development of the business system, the first user can understand the error messages that may occur during subsequent system use based on the system's logical functions—that is, the error codes of business errors that business personnel may trigger. The first user can generate error submission information based on these codes. Alternatively, if the business side has already triggered an error that cannot be resolved independently, the business personnel will send it to the first user. The first user can determine the error message based on the predicted error code or the received error code from the business side, and then determine the corresponding solution.

[0029] For example, the error code for a failed transfer due to inconsistent payee information is 0017. The error submission information uploaded by the first user is: Error message: 0017; Problem description: The page displays "Payee information is inconsistent, transfer failed"; Error reason: The system verification found that the entered name does not match the core returned account name; Business operation steps: Verify the information entered by the customer; Guide them to delete the old record and add it again in "Payee Management"; Re-initiate the transfer; Guiding words: "Please confirm again whether the payee name is completely consistent with the bank's reservation, pay attention to spaces or uncommon characters"; Parameter configuration items: None (this error does not require backend parameter adjustment).

[0030] In one optional implementation, an error information storage request sent by a first user is received, and it is determined whether the error information storage request includes a solution to the error information; if the error information storage request does not include a solution, a target solution template is determined based on the error type of the error information and predefined solution templates for each type; the target solution template is displayed to the first user so that the first user can generate a solution based on the target solution template; and an error submission message sent by the first user, including the error information and the solution to the error information, is received.

[0031] Step 102: Display the error submission information to the second user, receive the review result of the error submission information sent by the second user, and store the error submission information in the pre-established solution database based on the review result.

[0032] The second user is the reviewer of the error submissions uploaded by the first user; this could be a system designer, for example. The solution database is pre-built and stores the solutions corresponding to each error code.

[0033] Specifically, since the first user is a professional developer, the error submission information they upload might not be suitable for business users, meaning they might not understand it. Therefore, to ensure the technical correctness and user-friendliness of the solution, the first user needs to display the error submission information to a second user after uploading it. The second user can review the error submission information, checking for errors, overly technical descriptions, or insufficient business-friendliness. If the error submission information is correct and well-described, the review result is "approved." If the error submission information is incorrect or poorly described, the review result is "failed." After confirming the review result, the second user returns it to the server. If the review result is "approved," the server can store the error submission information in the solution database. If the review result is "failed," the review result is sent to the first user so that the first user can modify the error submission information accordingly.

[0034] In one optional implementation, if the review result is approved, the error submission information is stored in the solution database; if the review result is rejected, the review result is analyzed for modifiability based on a pre-trained language model to obtain a modifiability analysis result; wherein, the modifiability analysis result includes modifiability or non-modifiability; if the modification analysis result is modifiability, the error submission information is modified, and the modified error submission information is stored in the solution database.

[0035] Step 103: Receive the query error information sent by the third user, and query the solution database for the target solution corresponding to the query error information.

[0036] The third user is a non-technical person, such as a business employee in a bank responsible for daily business promotion and customer service. The error query is used by the third user to find solutions to system error codes triggered during their work. The error query information includes the error code being queried. Specifically, when a business employee encounters a system error, they can directly use the self-service query interface to send a query for the error information to the server. After receiving the query, the server, based on the error code, searches its solution database for the corresponding target solution.

[0037] In one optional implementation, contextual analysis is performed on the query error information to obtain contextual information of the query error information; wherein, the contextual information includes error content, page address and user operation; the contextual information is converted into dense vectors according to a pre-determined word embedding model; the similarity between the dense vectors and the solution vectors corresponding to the solutions in the solution database is calculated respectively; wherein, the solution database is a vector database; the solution corresponding to the solution vector with the highest similarity is determined as the target solution.

[0038] Step 104: Present the target solution to the third user so that the third user can resolve the query error information based on the target solution.

[0039] Specifically, after determining the target solution, it can be presented to a third user. The third user can then resolve the error message by following the operational steps and guidance provided in the target solution. For example, the operational steps of the target solution might be: switch the network to cellular mobile network and log out and log back in.

[0040] The technical solution of this embodiment involves obtaining error submission information sent by a first user. This error submission information includes error details and solutions. The solutions include the problem description, cause, operational steps, guidance, and parameter configuration items. The error submission information is then displayed to a second user, and the review results are received. Based on the review results, the error submission information is stored in a pre-established solution database. A query error message is received from a third user, and a target solution corresponding to the query error message is searched in the solution database. The target solution is then displayed to the third user, enabling them to resolve the query error message. This technical solution, by including solutions in the error submission information, ensures that solutions can be released simultaneously with new problems, solving the problem of information lag. Business personnel can quickly and independently obtain error reporting guidance through the solution database, significantly reducing the time spent creating event tickets and facilitating cross-team workflows, thus accelerating business promotion. This improves the work efficiency of business personnel while also enhancing customer satisfaction and trust.

[0041] Figure 2 A second flowchart of an abnormal data processing method provided in an embodiment of the present invention. The specific method may be as follows: Figure 2 As shown, the method may include the following steps:

[0042] Step 201: Receive the error message storage request sent by the first user and determine whether the error message storage request includes a solution for the error message.

[0043] In this solution, the error message storage request is an instruction sent by the first user to the server, instructing the server to store the error information. To provide an efficient and self-service channel for error code retrieval and solution acquisition, and to reduce unnecessary cross-role communication and event-based workflows, the error submission information must include a solution to the error. Therefore, upon receiving an error message storage request, the server can determine whether the content to be stored in the request includes a solution to the error.

[0044] Step 202: If the error message storage request does not include a solution, then determine the target solution template based on the error type of the error message and the predefined solution templates for each type.

[0045] The error solution includes the problem description, error cause, business operation steps, guidance script, and parameter configuration items. Specifically, the target solution template corresponds to the error message, facilitating the first user to generate a solution template. Different error types correspond to different types of solution templates. For example, for network timeout errors, the problem description in the solution template is a screenshot of the error interface. For business field validation errors, the problem description in the solution template is a text description of the error details. If the error message storage request does not include a solution, to facilitate the first user's accurate and quick solution upload, the server can determine the error type of the error message based on the error message storage request and select the target solution template corresponding to the error type from all types of solution templates. If the error message storage request includes a corresponding solution, the server directly retrieves the error submission information sent by the first user, which includes the error message and the solution for the error message.

[0046] Step 203: Show the target solution template to the first user so that the first user can generate a solution based on the target solution template.

[0047] After determining the target solution template, the server displays it to the first user through a visual interface. The first user can view the target solution template, fill in the required information, and obtain a complete solution.

[0048] Step 204: Receive the error submission information sent by the first user, which includes the error information and the solution to the error.

[0049] Step 205: Based on the audit results, store the erroneous submission information in the pre-established solution database.

[0050] The solution database is pre-built and stores the solutions corresponding to each error code. Since the first user is a professional developer, the error submission information uploaded by the first user may not be suitable for business users, meaning they might not understand it. Therefore, to ensure the technical correctness of the solution and its user-friendliness, the first user needs to display the error submission information to a second user after uploading it. The second user can review the error submission information and store it in the pre-built solution database based on the review results.

[0051] Optionally, in this solution, storing erroneous submission information into a pre-established solution database based on the review results includes the following steps A1-A3:

[0052] Step A1: If the audit result is approved, the error submission information will be stored in the solution database.

[0053] Step A2: If the review result is "review failed", then perform a modifiable analysis on the review result based on the pre-trained language model to obtain the modifiable analysis result.

[0054] The modifiable analysis results include those that can be modified and those that cannot. The language model is pre-trained based on a large amount of historical review results and corresponding historical erroneous submission information. It is used to modify erroneous submissions that fail review. In this solution, the language model can be an intelligent question-answering model. Specifically, if the review result is "failed," it indicates that the erroneous submission information submitted by the first user contains technical errors or inappropriate descriptions. The server can input the erroneous submission information and the review result into the language model. The language model first performs feature transformation and feature concatenation on the review result and erroneous submission information to obtain input features. The input features are analyzed to determine the data items that fail review, and whether these data items can be modified is then entered into the system.

[0055] For example, if the data item that fails the review is an operational step, and the description of the failure is "the language is too technical and business personnel may not understand it," it can be determined that the data item that fails the review does not involve technical underlying logic, and the language model determines that the modifiable analysis result is modifiable. If the data item that fails the review is a parameter configuration item, and the description of the failure is "the parameter configuration is incorrect," it can be determined that the data item that fails the review involves technical underlying logic, and the language model determines that the modifiable analysis result is not modifiable.

[0056] Step A3: If the analysis result is modifiable, modify the error submission information and store the modified error submission information in the solution database.

[0057] Specifically, if the analysis result is deemed modifiable, it means the error submission information can be directly modified through the language model. The language model can then be used to modify the error submission information, and the modified information is stored in the solution database. For example, if the data item that failed the review is an operation step, and the description of the failure is "the language is too technical and business personnel may not understand it," the language model determines that the analysis result is modifiable. Furthermore, the language model modifies the description of the operation step in a more easily understandable way and stores the modified error submission information in the solution database.

[0058] If the analysis result is deemed unmodifiable, the review result is sent to the first user, allowing them to correct the erroneous submission. By using a language model to pre-determine whether something can be modified or not, purely descriptive defects can be intercepted before manual review, reducing the number of times a second user needs to submit a revised version and shortening the review cycle. By automatically rewriting steps and wording, the solution can be made more business-friendly, eliminating the need for developers to rework it, significantly reducing communication and modification costs, and improving the work experience for all parties involved.

[0059] Step 206: Receive the query error information sent by the third user, perform context analysis on the query error information, and obtain the context information of the query error information.

[0060] The context information includes the error content, page address, and user actions. Specifically, the solution database in this solution is a vector database. Therefore, to facilitate finding the corresponding target solution in the solution database, the query error information needs to be processed to obtain a dense vector for easier searching. After receiving the query error information, context analysis can be performed to extract key fields such as the error number and error message, thus obtaining the context information of the query error information.

[0061] Step 207: Convert the context information into dense vectors according to the pre-determined word embedding model; determine the target solution based on the dense vectors and the solution database.

[0062] The solution database is a vector database. A dense vector is a fixed-length, numerically continuous, and dimensionless sequence of real numbers. Each bit in a dense vector is non-zero and carries a semantic weight. Dense vectors can cluster synonymous or similar descriptions in close proximity, allowing the server to perform rapid comparisons. The word embedding model (the same model used to build the solution database) is pre-trained and used to transform contextual information into vectors. Specifically, after obtaining the contextual information, it is input into the word embedding model, which converts each word into a corresponding index. The word embedding model uses the contextual information to generate context-sensitive weights for each word. A pooling layer is then used to average or extract the first and second word vectors to obtain the dense vector of the entire text. Optionally, in this solution, the target solution is determined based on the dense vector and the solution database, including: calculating the similarity between the dense vector and the solution vectors in the solution database; and determining the solution corresponding to the solution vector with the highest similarity as the target solution.

[0063] After obtaining the dense vector, a hierarchical navigable small-world search algorithm can be used to calculate the similarity between the dense vector and each solution vector, and the solution corresponding to the solution vector with the highest similarity is determined as the target solution. Alternatively, after obtaining the dense vector, the server can perform normalized inner products on the dense vector and each solution vector one by one to obtain the similarity between the dense vector and each solution vector.

[0064] Step 208: Present the target solution to the third user so that the third user can resolve the query error information based on the target solution.

[0065] The technical solution of this embodiment receives an error information storage request sent by a first user and determines whether the error information storage request includes a solution to the error information. If the error information storage request does not include a solution, a target solution template is determined based on the error type of the error information and predefined solution templates for each type. The target solution template is displayed to the first user so that the first user can generate a solution based on the target solution template. The system also receives error submission information sent by the first user, including the error information and a solution to the error information. Based on the review results, the error submission information is stored in a pre-established solution database. Furthermore, the system receives query error information sent by a third user, performs context analysis on the query error information to obtain the context information of the query error information, converts the context information into a dense vector according to a pre-determined word embedding model, and determines a target solution based on the dense vector and the solution database. The target solution is displayed to the third user so that the third user can solve the query error information based on the target solution. This technical solution, by forcibly binding error information and its solution, ensures that any new error code is accompanied by an operable solution when it is generated, ensuring that a solution can be released simultaneously with the occurrence of a new problem, thus solving the problem of information lag. Contextual analysis accurately identifies the dense vector corresponding to query errors. Retrieving these dense vectors from a vector database improves retrieval efficiency and accuracy. Business personnel can quickly and independently obtain error handling guidance from the solution database, significantly reducing the time spent creating incident tickets and facilitating cross-team workflows, thus accelerating business rollout. This not only improves business personnel efficiency but also enhances customer satisfaction and trust.

[0066] Figure 3 This is a third flowchart of an abnormal data processing method provided in an embodiment of the present invention. The specific method can be as follows: Figure 3 As shown, the method may include the following steps:

[0067] Step 301: Obtain the error submission information sent by the first user.

[0068] The error submission information includes the error message and the solution to the error message; the error solution includes the problem phenomenon, the cause of the error, the business operation steps, the guidance script and the parameter configuration items.

[0069] Step 302: Display the error submission information to the second user, receive the review result of the error submission information sent by the second user, and store the error submission information in the pre-established solution database based on the review result.

[0070] Step 303: Receive the query error information sent by the third user, and query the target solution corresponding to the query error information in the solution database.

[0071] Step 304: Present the target solution to the third user so that the third user can resolve the query error information based on the target solution.

[0072] Step 305: Display the solution evaluation interface to the third user and obtain the evaluation information of the target solution through the solution evaluation interface.

[0073] The evaluation information refers to the feedback obtained by a third user after using the target solution, assessing its performance. This evaluation information may include a rating result and a rating description. The rating result can be a specific score, and the rating description is a detailed description of the usage. In one optional implementation, after the third user queries the error information, the server can display a solution evaluation interface. The third user can fill in the rating result and rating description on this interface, and the server can obtain the evaluation information of the target solution through this interface.

[0074] Step 306: Perform feedback analysis on the evaluation information to obtain the feedback type corresponding to the evaluation information.

[0075] The feedback type is categorized as positive feedback, explicit negative feedback, or implicit negative feedback. Positive feedback indicates that the third user is relatively satisfied with the target solution, and the target solution resolves the corresponding system error. Explicit negative feedback indicates that the third user is clearly dissatisfied with the target solution, and the target solution cannot resolve the corresponding system error. Implicit negative feedback indicates that the target solution can resolve the corresponding system error, but the solution method or process is not comprehensive or user-friendly. Specifically, after receiving the evaluation information, the server can analyze the rating results and rating descriptions to determine the feedback type corresponding to the evaluation information.

[0076] In one optional implementation, feedback information with a score less than or equal to a preset score can be defined as explicit negative feedback. For feedback information with a score greater than the preset score and whose description includes pre-defined fine-grained keywords, the feedback type can be defined as implicit negative feedback. For feedback information with a score greater than the preset score but whose description does not include pre-defined fine-grained keywords, the feedback type can be defined as positive feedback. The pre-defined fine-grained keywords are pre-defined based on specific business needs and the performance of the business system, and are used to determine whether the target solution has defects. For example, if the feedback information is: a score of 3 (preset score is 2); and the evaluation description contains the keywords "step skipping" and "missing diagram," then the feedback type of the feedback information is determined to be implicit negative feedback.

[0077] Step 307: Update the solution database based on feedback type and evaluation information.

[0078] Specifically, different feedback types correspond to different methods of updating the solution database. In this solution, optionally, updating the solution database based on feedback type and evaluation information includes the following steps B1-B2:

[0079] Step B1: If the feedback type is explicit negative feedback, then display the evaluation information to the first user and obtain the updated solution sent by the first user based on the evaluation information; update the solution database based on the updated solution.

[0080] Specifically, if the feedback type is explicit negative feedback, it means that the target solution cannot resolve the corresponding system error and is therefore an invalid solution. Thus, if the feedback type is explicit negative feedback, the server can display the evaluation information to the first user. After receiving the evaluation information, the first user determines a new solution based on it, obtains an updated solution, and updates the solution database accordingly.

[0081] Step B2: If the feedback type is implicit negative feedback, store the keywords of the evaluation information into the pre-defined clustering library; update the solution database based on the clustering library.

[0082] The clustering library stores keywords triggered by evaluation information corresponding to each implicit negative feedback. If the feedback type is implicit negative feedback, it means the target solution can resolve the corresponding system error, but the third-party user who rated it believes the solution method or process is not comprehensive or user-friendly enough. Since evaluation information has a certain degree of subjectivity, to avoid the server affecting the accuracy of the overall evaluation based on individual evaluations, the keywords of the evaluation information can be stored in the clustering library first. If the frequency of a certain keyword in a certain evaluation message in the clustering library exceeds a preset number, it indicates that the evaluation information does indeed have a problem, and the evaluation information and the corresponding target solution are sent to the first user. After receiving the evaluation information, the first user determines a new solution based on the evaluation information, obtains an updated solution, and updates the solution database based on the updated solution.

[0083] Of course, if the feedback type is positive, the solution database will not be updated. By sending the target solution corresponding to explicit negative feedback directly to developers, invalid solutions can be quickly corrected, preventing business personnel from continuing to use erroneous information. By clustering the target solutions of implicit negative feedback before triggering modifications, subjective evaluations can be avoided from interfering with overall judgment, thus improving the credibility of the feedback.

[0084] The technical solution of this embodiment involves acquiring error submission information sent by a first user. This error submission information includes error details and solutions; the solutions include the problem phenomenon, the cause of the error, business operation steps, guidance scripts, and parameter configuration items. The error submission information is displayed to a second user, and the review result of the error submission information sent by the second user is received. Based on the review result, the error submission information is stored in a pre-established solution database. A query error message sent by a third user is received, and a target solution corresponding to the query error message is queried in the solution database. The target solution is displayed to the third user, enabling the third user to resolve the query error message based on the target solution. A solution evaluation interface is displayed to the third user, and the evaluation information of the target solution is obtained through the solution evaluation interface. Feedback analysis is performed on the evaluation information to obtain the feedback type corresponding to the evaluation information; the feedback type is positive feedback, explicit negative feedback, or implicit negative feedback. The solution database is updated based on the feedback type and evaluation information. This technical solution, through feedback from the third user, drives continuous optimization of solutions, ensuring the effectiveness and usability of the solution database. Simultaneously, it enables business personnel to solve customer problems more professionally and quickly, improving customer satisfaction and trust.

[0085] Figure 4 This is a schematic diagram of an abnormal data processing device provided in an embodiment of the present invention. This device is suitable for executing the abnormal data processing method provided in an embodiment of the present invention. Figure 4 As shown, the device may specifically include:

[0086] The information acquisition module 401 is used to acquire error submission information sent by the first user; wherein, the error submission information includes error information and solutions to the error information; the error solutions include problem symptoms, error causes, business operation steps, guidance scripts, and parameter configuration items;

[0087] The data storage module 402 is used to display the error submission information to the second user, receive the review result of the error submission information sent by the second user, and store the error submission information in a pre-established solution database based on the review result;

[0088] The information query module 403 is used to receive query error information sent by a third user and query the solution database for the target solution corresponding to the query error information;

[0089] The information processing module 404 is used to display the target solution to the third user, so that the third user can resolve the query error information based on the target solution.

[0090] Optionally, the information acquisition module 401 is specifically used to: receive an error information storage request sent by the first user, and determine whether the error information storage request includes a solution to the error information;

[0091] If the error message storage request does not include the solution, then the target solution template is determined based on the error type of the error message and the predefined solution templates for each type.

[0092] The target solution template is displayed to the first user so that the first user can generate the solution based on the target solution template;

[0093] Receive the error submission information sent by the first user, which includes the error information and a solution to the error information.

[0094] Optionally, the data storage module 402 is specifically used to: if the audit result is that the audit is passed, store the error submission information in the solution database;

[0095] If the review result is "review failed", then the review result is analyzed for modifiability based on the pre-trained language model to obtain a modifiability analysis result; wherein, the modifiability analysis result includes modifiability or non-modifiability;

[0096] If the analysis result indicates that the error submission information is modifiable, then the error submission information is modified and stored in the solution database.

[0097] Optionally, the information query module 403 is specifically used to: perform context analysis on the query error information to obtain the context information of the query error information; wherein, the context information includes error content, page address and user operation;

[0098] The context information is converted into a dense vector based on a pre-determined word embedding model;

[0099] The target solution is determined based on the dense vectors and the solution database.

[0100] Optionally, the information query module 403 is further configured to: calculate the similarity between the dense vector and the solution vector corresponding to the solution in the solution database; wherein the solution database is a vector database;

[0101] The solution corresponding to the solution vector with the highest similarity is determined as the target solution.

[0102] Optionally, the information processing module 404 is specifically used to: display the solution evaluation interface to the third user, and obtain the evaluation information of the target solution through the solution evaluation interface;

[0103] The evaluation information is subjected to feedback analysis to obtain the feedback type corresponding to the evaluation information; wherein, the feedback type is positive feedback, explicit negative feedback, or implicit negative feedback;

[0104] The solution database is updated based on the feedback type and the evaluation information.

[0105] Optionally, the information processing module 404 is further configured to: if the feedback type is explicit negative feedback, display the evaluation information to the first user and obtain the updated solution sent by the first user based on the evaluation information;

[0106] Update the solution database based on the aforementioned update solution;

[0107] If the feedback type is implicit negative feedback, then the keywords of the evaluation information are stored in a pre-defined clustering library;

[0108] The solution database is updated based on the clustering library.

[0109] The abnormal data processing apparatus provided in this embodiment of the invention can execute the abnormal data processing method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution. Content not described in detail in this embodiment can be referred to the description in any method embodiment of the invention.

[0110] This invention also provides a computer program product.

[0111] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer program products, which may include one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be an application-specific or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, with reference to... Figure 5 , Figure 5 The electronic device 12 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application. Figure 5 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0113] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0114] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0115] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0116] A program / utility 40 having a set (at least one) of program modules 46 may be stored, for example, in memory 28. Such program modules 46 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 46 typically perform the functions and / or methods described in the embodiments of this application.

[0117] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 12, and / or with any device that enables electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although... Figure 5 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0118] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing an abnormal data processing method provided in this embodiment of the invention: obtaining error submission information sent by a first user; wherein, the error submission information includes error information and a solution to the error information; the error solution includes the problem phenomenon, error cause, business operation steps, guidance script, and parameter configuration items; displaying the error submission information to a second user, receiving the review result of the error submission information sent by the second user, and storing the error submission information in a pre-established solution database based on the review result; receiving query error information sent by a third user, and querying the solution database for a target solution corresponding to the query error information; displaying the target solution to the third user so that the third user can resolve the query error information based on the target solution.

[0119] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements an abnormal data processing method as provided in all embodiments of this invention: obtaining error submission information sent by a first user; wherein the error submission information includes error information and a solution to the error information; the error solution includes a problem phenomenon, an error cause, business operation steps, guidance scripts, and parameter configuration items; displaying the error submission information to a second user, receiving an audit result of the error submission information sent by the second user, and storing the error submission information in a pre-established solution database based on the audit result; receiving a query error information sent by a third user, and querying the solution database for a target solution corresponding to the query error information; displaying the target solution to the third user, so that the third user can resolve the query error information based on the target solution. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electronic device, apparatus, or device that is electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used or combined with an electronic device, apparatus, or device by instructions to execute it.

[0120] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in conjunction with an electronic device, apparatus, or device that executes instructions.

[0121] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0122] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0123] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. An abnormal data processing method, characterized in that, The method includes: Obtain error submission information sent by the first user; wherein, the error submission information includes error information and solutions to the error information; the error solutions include problem symptoms, error causes, business operation steps, guidance scripts, and parameter configuration items; The error submission information is displayed to the second user, and the review result of the error submission information sent by the second user is received. Based on the review result, the error submission information is stored in the pre-established solution database. Receive query error information sent by a third user, and query the solution database for the target solution corresponding to the query error information; The target solution is presented to the third user so that the third user can resolve the query error information based on the target solution.

2. The method according to claim 1, characterized in that, Retrieve the error submission information sent by the first user, including: Receive the error information storage request sent by the first user, and determine whether the error information storage request includes a solution to the error information; If the error message storage request does not include the solution, then the target solution template is determined based on the error type of the error message and the predefined solution templates for each type. The target solution template is displayed to the first user so that the first user can generate the solution based on the target solution template; Receive the error submission information sent by the first user, which includes the error information and a solution to the error information.

3. The method according to claim 1, characterized in that, Based on the audit results, the error submission information is stored in a pre-established solution database, including: If the review result is "approved", the error submission information will be stored in the solution database. If the review result is "review failed", then the review result is analyzed for modifiability based on the pre-trained language model to obtain a modifiability analysis result; wherein, the modifiability analysis result includes modifiability or non-modifiability; If the analysis result indicates that the error submission information is modifiable, then the error submission information is modified and stored in the solution database.

4. The method according to claim 1, characterized in that, Querying the solution database for the target solution corresponding to the query error information includes: Context analysis is performed on the query error information to obtain the context information of the query error information; wherein, the context information includes the error content, page address, and user operation; The context information is converted into a dense vector based on a pre-determined word embedding model; The target solution is determined based on the dense vectors and the solution database.

5. The method according to claim 4, characterized in that, Determining the target solution based on the dense vectors and the solution database includes: Calculate the similarity between the dense vector and the corresponding solution vector in the solution database; wherein, the solution database is a vector database. The solution corresponding to the solution vector with the highest similarity is determined as the target solution.

6. The method according to claim 1, characterized in that, The method further includes: The solution evaluation interface is displayed to the third user, and the evaluation information of the target solution is obtained through the solution evaluation interface; The evaluation information is subjected to feedback analysis to obtain the feedback type corresponding to the evaluation information; wherein, the feedback type is positive feedback, explicit negative feedback, or implicit negative feedback; The solution database is updated based on the feedback type and the evaluation information.

7. The method according to claim 6, characterized in that, Updating the solution database based on the feedback type and the evaluation information includes: If the feedback type is explicit negative feedback, then the evaluation information is displayed to the first user, and the updated solution sent by the first user based on the evaluation information is obtained; Update the solution database based on the aforementioned update solution; If the feedback type is implicit negative feedback, then the keywords of the evaluation information are stored in a pre-defined clustering library; The solution database is updated based on the clustering library.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements an abnormal data processing method according to any one of claims 1-7.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the abnormal data processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the abnormal data processing method as described in any one of claims 1 to 7.

Images