Operation and maintenance data processing method, system, equipment and computer program product

Abstract

The invention provides an operation and maintenance data processing method, system and device and a computer program product, and relates to the technical field of operation and maintenance. The method comprises the steps that a large model obtains an operation and maintenance work order; carrying out key information extraction on the operation and maintenance work order by the large model to obtain work order key information; wherein the work order key information comprises at least one of a complaint type, a related service and a user appeal; the large model calls a service diagnosis system to perform abnormality diagnosis according to the work order key information and obtains returned abnormality diagnosis suggestions; the large model matches a receipt scheme template corresponding to the related business from the scene knowledge base according to the related business; and the large model generates a receipt scheme for the operation and maintenance work order based on the work order key information, the abnormality diagnosis opinions and the receipt scheme template. According to the embodiment of the invention, end-to-end automation of operation and maintenance work order processing can be realized, and the processing efficiency and accuracy are greatly improved.

Description

Technical Field

[0001] This disclosure relates to the field of operation and maintenance technology, and in particular to an operation and maintenance data processing method, system, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] This section is intended to provide background or context for the embodiments of this disclosure as set forth in the claims. The description herein is not intended to be a prior art simply because it is included in this section.

[0003] Traditional operation and maintenance work order processing mainly relies on manual labor, which has three major problems: First, system fragmentation requires staff to frequently switch between multiple independent systems, which is cumbersome and inefficient. Second, data silos prevent the exchange of critical data such as billing and business information, resulting in difficulties in querying, insufficient basis for responses, and poor accuracy and timeliness in processing. Third, there are high risks of breach of contract and compliance, as manual operation is prone to errors, response delays, and leakage of user information, which seriously affect service quality and corporate reputation.

[0004] Therefore, there is an urgent need for a method that can efficiently and accurately process maintenance work orders. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method, system, electronic device, computer-readable storage medium, and computer program product for processing operation and maintenance data, which can improve the processing efficiency and accuracy of operation and maintenance work orders.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] This disclosure provides an operation and maintenance data processing method, including: a large model acquiring operation and maintenance work orders; the large model extracting key information from the operation and maintenance work orders to obtain key information of the work orders; wherein, the key information of the work orders includes at least one of complaint type, involved business, and user request; the large model calling a business diagnosis system to perform anomaly diagnosis based on the key information of the work orders and obtaining returned anomaly diagnosis opinions; the large model matching the corresponding return order scheme template for the involved business from a scenario knowledge base based on the involved business; and the large model generating a return order scheme for the operation and maintenance work orders based on the key information of the work orders, the anomaly diagnosis opinions, and the return order scheme template.

[0008] In some embodiments, the method further includes: the business diagnostic system determining user identification information corresponding to the maintenance work order based on the key information; the business diagnostic system retrieving business data corresponding to the user identification from multiple business systems; the business diagnostic system performing anomaly diagnosis based on the business data corresponding to the user identification to obtain anomaly diagnosis data; and generating anomaly diagnosis opinions based on the anomaly diagnosis data.

[0009] In some embodiments, the key information of the work order further includes the operation and maintenance type; wherein, the method further includes: the large model obtaining classification rules from the large model knowledge management module; the large model processing the key information of the operation and maintenance work order based on the classification rules to determine the operation and maintenance type of the operation and maintenance work order.

[0010] In some embodiments, the large model generates a response for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinion, and the response plan template. This includes: the large model calling the large model knowledge management module to perform knowledge retrieval based on the key information of the work order to obtain knowledge associated with the maintenance work order; and the large model generating a response for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinion, the response plan template, and the knowledge associated with the maintenance work order.

[0011] In some embodiments, the large model invokes the large model knowledge management module to perform knowledge retrieval based on the key information of the work order to obtain knowledge associated with the maintenance work order, including: the large model determining knowledge retrieval rules according to the business involved; the large model processing the key information of the work order based on the knowledge retrieval rules to determine a knowledge retrieval scheme, the knowledge retrieval scheme including at least one of knowledge graph retrieval, expert corpus retrieval, and knowledge retrieval enhancement; and the large model knowledge management module performing knowledge retrieval based on the knowledge retrieval scheme to determine the knowledge associated with the maintenance work order.

[0012] In some embodiments, the large-scale model knowledge management module stores at least one of a business knowledge graph, expert corpus, and a knowledge retrieval enhancement scheme; wherein, the large-scale model knowledge management module performs knowledge retrieval based on the knowledge retrieval scheme to determine the knowledge associated with the maintenance work order, including: if it is determined to retrieve through the knowledge graph, then retrieving the knowledge associated with the maintenance work order from the business knowledge graph according to the key information of the work order; if it is determined to retrieve through the expert corpus, then retrieving the knowledge associated with the maintenance work order from the expert corpus of the large-scale model knowledge management module; if it is determined to retrieve through the knowledge retrieval enhancement scheme, then retrieving the knowledge associated with the maintenance work order from the database or from the network using the knowledge retrieval enhancement scheme.

[0013] In some embodiments, the method further includes: sending the maintenance work order and the return plan for the maintenance work order to an expert object so that the expert object can evaluate the return plan; receiving the evaluation of the return plan from the expert object; and updating and optimizing the large model knowledge management module based on the maintenance work order, the return plan, and the evaluation.

[0014] This disclosure provides an operation and maintenance data processing system, including: a large model for acquiring operation and maintenance work orders; extracting key information from the operation and maintenance work orders to obtain key information of the work orders; wherein the key information of the work orders includes at least one of complaint type, involved business, and user request; calling a business diagnosis system to perform anomaly diagnosis based on the key information of the work orders, and obtaining returned anomaly diagnosis opinions; matching the corresponding return order scheme template from a scenario knowledge base based on the involved business; and generating a return order scheme for the operation and maintenance work orders based on the key information of the work orders, the anomaly diagnosis opinions, and the return order scheme template.

[0015] This disclosure provides an electronic device comprising: a memory and a processor; the memory for storing computer program instructions; and the processor for calling the computer program instructions stored in the memory to implement the operation and maintenance data processing method described above.

[0016] This disclosure provides a computer-readable storage medium storing computer program instructions to implement the operation and maintenance data processing method as described in any of the preceding embodiments.

[0017] This disclosure provides a computer program product or computer program that includes computer program instructions stored in a computer-readable storage medium. The computer program instructions are read from the computer-readable storage medium, and the processor executes the computer program instructions to implement the aforementioned operation and maintenance data processing method.

[0018] The operation and maintenance data processing method, system, electronic device, computer-readable storage medium, and computer program product provided in this disclosure automatically complete the entire process from work order information extraction and business diagnosis to solution generation through a large model. This effectively solves the problems of system fragmentation and data silos in traditional manual processing, and significantly improves the processing efficiency, accuracy, and standardization of operation and maintenance work orders, providing a complete technical foundation for intelligent operation and maintenance.

[0019] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this disclosure. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0021] Figure 1 A schematic diagram of a scenario that can be applied to the operation and maintenance data processing method or system in the embodiments of this disclosure is shown.

[0022] Figure 2 This is a flowchart illustrating an operation and maintenance data processing method according to an exemplary embodiment.

[0023] Figure 3 This is a flowchart illustrating an abnormality diagnosis opinion generation method according to an exemplary embodiment.

[0024] Figure 4 This is a flowchart illustrating a method for generating a receipt according to an exemplary embodiment.

[0025] Figure 5 This is a flowchart illustrating an association knowledge acquisition method according to an exemplary embodiment.

[0026] Figure 6 This is a schematic diagram illustrating the structure of an operation and maintenance work order processing system according to an exemplary embodiment.

[0027] Figure 7 This is a flowchart illustrating a maintenance work order processing method according to an exemplary embodiment.

[0028] Figure 8 This is a block diagram illustrating an operation and maintenance data processing system according to an exemplary embodiment.

[0029] Figure 9 A schematic diagram of the structure of an electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0030] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0031] Those skilled in the art will recognize that embodiments of this disclosure can be a system, apparatus, method, or computer program product. Therefore, this disclosure can be implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0032] The features, structures, or characteristics described in this disclosure can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more specific details omitted, or other methods, components, systems, steps, etc., can be employed. In other instances, well-known methods, systems, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0033] In this disclosure, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0034] The accompanying drawings are merely illustrative of this disclosure, and the same reference numerals in the drawings denote the same or similar parts, thus omitting repeated descriptions of them. Some block diagrams shown in the drawings do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0035] The flowchart shown in the accompanying drawings is merely illustrative and does not necessarily include all content and steps, nor does it require execution in the described order. For example, some steps may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0036] In the description of this disclosure, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences; the terms "contains," "includes," and "has" are used to indicate an open-ended meaning of inclusion and refer to the existence of additional elements / components / etc. besides those listed.

[0037] To better understand the above-mentioned objectives, features and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0038] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in this disclosed technical solution all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security and network security.

[0039] In traditional operation and maintenance systems, operation and maintenance work orders dispatched by customer service currently rely mainly on manual processing, which harbors many problems that urgently need to be solved.

[0040] 1. System Fragmentation: In the work order classification stage, staff need to manually filter work order types in a dedicated classification system based on complex and ever-changing business rules. Each type has a different processing flow and responsible department, making it easy to misclassify work orders and slowing down the processing time. When querying business interfaces, since user issues often involve multiple business modules, staff have to frequently switch between logging into various independent systems. In the response generation stage, staff need to extract relevant information from different systems and then manually integrate it into a standardized response. This process is prone to information omissions or formatting errors, further reducing processing efficiency.

[0041] 2. Data Silos: The existence of data silos severely restricts the accuracy and timeliness of work order processing. For example, the billing diagnostic system stores crucial data such as detailed user consumption records, package pricing standards, and reasons for billing anomalies. This data is essential for resolving user work orders regarding billing disputes and package usage questions. However, because it lacks data interoperability with the work order system, when customer service receives a relevant work order, they cannot directly retrieve the data from the billing diagnostic system. They must rely on manual searching through the billing system one by one. This not only increases the workload but may also lead to responses lacking factual basis due to untimely or incorrect searches, failing to accurately answer user questions. The entire process is time-consuming, prone to human error, and negatively impacts user experience.

[0042] 3. Breach of Contract and Compliance Risks: Manual processing of work orders is prone to errors due to factors such as staff proficiency, sense of responsibility, and workload. Furthermore, manual processing makes it difficult to strictly control response times and processing cycles, especially during peak periods with a surge in work orders, easily leading to delays. In addition, when processing work orders involving user privacy and sensitive information, failure to comply with compliance requirements during manual operations may result in information leaks, violations of data security laws and regulations, and severe legal consequences and reputational damage to the company, ultimately significantly impacting customer satisfaction and market competitiveness.

[0043] To address the aforementioned issues, this application proposes the following technical solutions to improve the accuracy and efficiency of operation and maintenance methods.

[0044] The exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0045] Figure 1 A schematic diagram of a scenario that can be applied to the operation and maintenance data processing method or system in the embodiments of this disclosure is shown.

[0046] Please refer to Figure 1 The diagram illustrates an implementation environment provided by an exemplary embodiment of this disclosure.

[0047] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0048] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, desktop computers, wearable devices, virtual reality devices, smart home devices, etc.

[0049] Server 105 can be a server that provides various services, such as a backend management server that supports the devices operated by users using terminal devices 101, 102, and 103. The backend management server can analyze and process received requests and other data, and feed the processing results back to the terminal devices.

[0050] A server can be a standalone physical server, a server cluster or a distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. This disclosure does not impose any restrictions on this.

[0051] Server 105 can, for example, obtain maintenance work orders through a large model; server 105 can, for example, extract key information from the maintenance work orders through the large model to obtain key information of the work orders; wherein, the key information of the work orders includes at least one of the following: complaint type, business involved, and user request; server 105 can, for example, call the business diagnosis system to perform anomaly diagnosis based on the key information of the work orders through the large model, and obtain the returned anomaly diagnosis opinion; server 105 can, for example, match the corresponding return order solution template for the business involved from the scenario knowledge base based on the business involved through the large model; server 105 can, for example, generate a return order solution for the maintenance work orders based on the key information of the work orders, the anomaly diagnosis opinion, and the return order solution template through the large model.

[0052] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Server 105 can be a single physical server or a combination of multiple servers. Depending on actual needs, it can have any number of terminal devices, networks, and servers.

[0053] Figure 2 This is a flowchart illustrating an operation and maintenance data processing method according to an exemplary embodiment. The method provided in this disclosure can be executed by any electronic device with computing power, for example, the method can be executed by the above-described... Figure 1The execution can be performed by a server or terminal device in the embodiments, or it can be performed by both a server and a terminal device. In the following embodiments, the server is used as the execution subject for illustration, but this disclosure is not limited to this.

[0054] Reference Figure 2 The operation and maintenance data processing method provided in this embodiment may include the following steps.

[0055] Step S202: Obtain maintenance work orders from the large model.

[0056] In the IT or communications field, an operations and maintenance work order typically refers to a formatted electronic or paper document used to record, track, manage, and resolve a specific operations and maintenance task or problem.

[0057] In some embodiments, after receiving an operation and maintenance work order, the intelligent processing flow for the complaint work order can be initiated within the complaint work order processing system. After the intelligent processing flow for the complaint work order is triggered, the complaint work order processing system can synchronize the complaint content, such as user feedback "the data plan has not been exceeded but the billing is abnormal", and front-line dispatch opinions (preliminary judgment from the front line "it may be a temporary bug in the billing system", etc.), to the large model, providing raw input for subsequent intelligent processing.

[0058] Step S204: The large model extracts key information from the maintenance work order to obtain key information of the work order; among which, the key information of the work order includes at least one of the complaint type, the business involved, and the user's request.

[0059] In some embodiments, the key information in a work order may also include the maintenance type.

[0060] In some embodiments, the large model can also obtain classification rules from the large model knowledge management module; the large model can also process key information of operation and maintenance work orders based on classification rules to determine the operation and maintenance type of the operation and maintenance work order.

[0061] The large model knowledge management module can be a module specifically designed to acquire, organize, store, update, and provide the various specialized and structured knowledge required by the large model when processing operation and maintenance work orders.

[0062] In some embodiments, the large model knowledge management module may store knowledge graphs related to knowledge in the field. For example, in the field of communication, when processing operation and maintenance work orders, knowledge graphs related to the field of communication can be pre-stored in the large model knowledge management module.

[0063] In some embodiments, the large model knowledge management module may also pre-store some corpus, such as expert response templates, response generation rules, response generation restrictions, etc., and this application does not impose any restrictions on this.

[0064] In some embodiments, the large model knowledge management module can also perform knowledge-enhanced search to retrieve specific knowledge from the network.

[0065] Knowledge augmentation refers to methods that improve the accuracy, professionalism, and factual reliability of content generated by a large model by retrieving relevant information from external knowledge sources and providing it as supplementary context.

[0066] In some embodiments, the large model knowledge management module described above can be independent of the large model.

[0067] In some embodiments, the "Complaint Ticket Key Information Extraction & Intelligent Classification" module of the large model can process the basic information of the received ticket: first, it uses natural language processing technology to identify and extract key information such as "complaint type (e.g., fee dispute)," "related business (e.g., data plan)," and "user's core demand (e.g., refund of abnormal charges)"; then, based on the classification rules in the large model's knowledge management module (associated with the business scenario knowledge base), it automatically determines the ticket category (e.g., classifies it as a "billing complaint ticket"), laying the foundation for accurate processing in the future.

[0068] In step S206, the large model calls the business diagnostic system to perform anomaly diagnosis based on the key information of the work order and obtains the returned anomaly diagnosis opinion.

[0069] In some embodiments, a business diagnostic system can refer to a dedicated software system that uses automated scripts, rule engines, or data analysis models to detect and analyze the operating status, data consistency, and business logic of a specific business system (such as billing, network, or order) in order to quickly locate the root cause of anomalies and generate diagnostic conclusions.

[0070] In some embodiments, the business diagnostic system can perform root cause analysis. The system can automatically analyze the problem symptoms and trace them back to the most fundamental business or technical cause.

[0071] For example, suppose a user complains, "Why did my phone bill suddenly surge?" Upon receiving this work order, the business diagnostic system will automatically execute a diagnostic script: It will query the user's call, data usage, and SMS details for the most recent billing cycle; compare this to historical usage for the same period and find an abnormally high level of "international roaming data traffic"; check the user's plan and find that they have not activated an international roaming plan, thus being charged at the standard rate, leading to the surge in charges. The diagnostic output will be: "Root cause analysis: The user incurred high international roaming charges due to data traffic usage abroad and has not activated a discounted data plan."

[0072] In some embodiments, the business diagnostic system can also perform compliance and consistency checks to examine whether business data, user status, or system configuration conform to predefined business rules and policies.

[0073] For example, suppose a user applies for a "package downgrade," but discovers an error in the billing amount the following month. The business diagnostic system will automatically check: confirm whether the user's downgrade application was successfully processed; check if there is any overlap or gap in the effective dates of the old and new packages; and verify whether the monthly fee calculation correctly applies the new package's pricing standard. The diagnostic output will be: "Consistency check failed: After the user downgraded their package, the system still deducted the monthly fee based on the old package, resulting in an overcharge of 15 yuan."

[0074] In some embodiments, the large model can push the key information of the classified work orders (including classification results, extracted core requests, etc.) to the "one-click diagnosis (billing) system" to initiate an information query request. Based on the received work order information, the business diagnosis system retrieves its own stored data, such as billing diagnosis data (e.g., user package tariff standards, historical billing records, system operation logs), and provides diagnostic opinions (e.g., "No abnormalities were found in the system billing logic; the real-time deduction interface needs to be investigated") and diagnostic steps (e.g., "Step 1: Check the user package code; Step 2: Verify the deduction trigger conditions"), providing factual basis for solution generation.

[0075] Step S208: The large model matches the corresponding receipt solution template from the scenario knowledge base based on the business involved.

[0076] In some embodiments, before generating a processing solution, the large model can retrieve high-quality response solution knowledge corresponding to the business from the "Intelligent Processing Scenario Knowledge Base for Complaint Work Orders". This knowledge consists of historically accumulated and verified work order processing templates (such as "Standard Response Framework for Fee Dispute Work Orders" and "Troubleshooting Steps for Fault Work Orders"), which are used to guide solution generation and ensure that the solution fits the actual business scenario and complies with processing specifications.

[0077] Step S210: The large model generates a return plan for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinions, and the return plan template.

[0078] In some embodiments, the large model can integrate the key information of the aforementioned work orders, anomaly diagnosis opinions, response plan templates, and relevant scenario knowledge. The "large model generates complaint handling solutions" module of the large model automatically generates a handling solution for the current work order. For example, for a work order involving a fee dispute, the output includes a complete response containing "words to reassure the user (e.g., 'Hello, we have verified the fee anomaly you reported'), root cause analysis (e.g., 'caused by a temporary billing bug in the system'), and a solution (e.g., 'The bug has been fixed and the overcharged amount has been refunded, expected to arrive within 24 hours')," which is then simultaneously pushed to the complaint work order processing system.

[0079] This embodiment proposes an end-to-end automated processing system and method for operation and maintenance work orders based on a large model. This system breaks through the limitations of traditional manual processing modes. By deeply integrating multiple key technologies, it constructs an efficient and accurate end-to-end automated processing system. Through the deep integration of work order classification, dynamic prompt word configuration, diagnostic interface calls, and large model generation technologies, it achieves end-to-end automation from work order identification to response generation. This not only significantly reduces labor costs and the risk of errors caused by manual operation, but also significantly improves the response efficiency and processing accuracy of work orders.

[0080] The technical solution provided in this embodiment achieves full automation of the operation and maintenance work order process from input, analysis, diagnosis to response generation by deeply integrating key information extraction, intelligent classification, automatic troubleshooting by the business diagnosis system, and matching with the scenario knowledge base through a large model. This significantly improves processing efficiency and accuracy, greatly reduces labor costs and operational risks, and continuously optimizes system capabilities through a closed-loop knowledge update mechanism, providing efficient, reliable, and evolvable intelligent operation and maintenance solutions for industries such as telecommunications.

[0081] Figure 3 This is a flowchart illustrating an abnormality diagnosis opinion generation method according to an exemplary embodiment.

[0082] refer to Figure 3 The above-mentioned method for generating abnormal diagnostic opinions may include the following steps.

[0083] In step S302, the business diagnostic system determines the user identification information corresponding to the maintenance work order based on the key information.

[0084] User identification information refers to key data that can uniquely identify a user.

[0085] In telecommunications operators' systems, the most common user identification information is the mobile phone number. In addition, it can also be: a user account ID, a unique identifier assigned by the operator's internal system; a customer number, a unique number in a CRM (Customer Relationship Management) system; and a broadband account, for fixed-line services.

[0086] User identification information is not a vague user name or address, but an index key that can be precisely matched to a unique user record in the database.

[0087] User identification information serves as a technological bridge to break down data silos. It enables data previously scattered across different business systems to be linked together around a unique user identity, forming a complete user view and directly resolving the "data silo" problem. There's no need for manual searching across multiple systems using vague information like names; the system automatically aggregates cross-system data through precise user identification, providing a comprehensive data foundation for accurate diagnostics.

[0088] In step S304, the business diagnostic system retrieves the business data corresponding to the user identifier from multiple business systems.

[0089] Step S306: The business diagnosis system performs anomaly diagnosis based on the business data corresponding to the user identifier and obtains anomaly diagnosis data.

[0090] After acquiring integrated user business data, the business diagnostic system performs automated analysis using its built-in rule engine and data model. For example, the system can match and cross-validate multi-dimensional data such as user packages, consumption records, and business status with preset business rules (such as pricing standards, status logic, and usage thresholds) in real time. Once it detects deviations from the normal pattern, such as abnormal billing amounts, contradictory service statuses, or sudden changes in usage, it triggers the abnormal rules, accurately locates the root cause, and generates structured abnormal diagnostic data and opinions.

[0091] Step S308: Generate abnormal diagnosis opinions based on abnormal diagnosis data.

[0092] Based on anomaly diagnostic data, the system uses natural language processing (NLP) technology to integrate the rules triggering the anomaly, related business data, and the identified root cause into a structured diagnostic conclusion. This conclusion not only includes a clear qualitative description (e.g., "billing amount discrepancy") but also clarifies specific quantitative evidence (e.g., "monthly package fee is 50 yuan, actual charge is 65 yuan"), and ultimately points to actionable investigation directions or conclusions (e.g., "the root cause is suspected to be unexplained additional charges; it is recommended to check value-added service subscription records"). This provides accurate and professional decision-making basis for subsequent solution generation.

[0093] This technical solution automatically links and integrates user data from multiple isolated business systems using precise user identification information. It then utilizes a rule engine and data model for real-time comparison and root cause analysis, ultimately transforming the diagnostic results into structured diagnostic opinions containing clear conclusions, quantitative evidence, and operational suggestions. This effectively breaks down data silos and achieves full automation from data aggregation to intelligent diagnosis, providing solid and reliable decision support for generating accurate operation and maintenance solutions.

[0094] Figure 4 This is a flowchart illustrating a method for generating a receipt according to an exemplary embodiment.

[0095] refer to Figure 4 The large model generates return receipts for maintenance work orders based on key work order information, anomaly diagnosis opinions, and return receipt templates.

[0096] Step S402: Obtain maintenance work orders for the large model.

[0097] Step S404: The large model extracts key information from the maintenance work order to obtain the key information of the work order; among which, the key information of the work order includes at least one of the complaint type, the business involved, and the user's request.

[0098] In step S406, the large model calls the business diagnostic system to perform anomaly diagnosis based on the key information of the work order and obtains the returned anomaly diagnosis opinion.

[0099] Step S408: The large model matches the corresponding receipt solution template from the scenario knowledge base based on the business involved.

[0100] This step standardizes the receipt processing scheme. The specific process is as follows: The large model first identifies the "related business" (such as "5G data traffic deduction") in the key information of the work order. Then, using this as an index, it automatically retrieves and calls the optimal receipt template pre-set for that business scenario from the scenario knowledge base. This ensures the structural standardization and business fit of the generated scheme, providing a high-quality foundation for subsequent filling in of specific diagnostic information and user-defined expressions.

[0101] The core value of this step lies in elevating response generation from "drafting from scratch" to "precise optimization." By intelligently matching business templates from a scenario knowledge base, it directly addresses the core pain points of inconsistent response formats and non-standard solutions encountered in manual processing. This not only ensures the professionalism and compliance of the response content but also significantly improves solution generation efficiency, laying a solid foundation for subsequently embedding personalized diagnostic results.

[0102] In step S410, the big model calls the big model knowledge management module to retrieve knowledge based on the key information of the work order, and obtains the knowledge associated with the operation and maintenance work order.

[0103] The big data model uses the extracted key information from work orders (such as complaint type and user requests) as a retrieval request, actively invoking the "big data model knowledge management module." This module then searches and returns in-depth knowledge (such as technical principles, historical cases, and policy provisions) highly relevant to the current work order from its managed knowledge graph, expert corpus, and other resources. This provides solid information support and decision-making basis for subsequently generating accurate and professional work order solutions.

[0104] In step S412, the large model generates a response for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinions, the response plan template, and the knowledge associated with the maintenance work order.

[0105] This technical solution achieves precision and automation in operation and maintenance work order responses through multi-source information fusion and intelligent generation technology. The system uses standardized response templates as its structural foundation, incorporates root cause conclusions from anomaly diagnosis, and enhances the in-depth information provided by the associated knowledge base. Ultimately, it synthesizes personalized response forms that are standardized, accurate, and professional, significantly improving response quality and processing efficiency, and completely changing the traditional work mode that relies on manual drafting.

[0106] Figure 5 This is a flowchart illustrating an association knowledge acquisition method according to an exemplary embodiment.

[0107] refer to Figure 5 The large model uses the key information of the work order to call the knowledge management module of the large model to retrieve knowledge associated with the operation and maintenance work order, which may include the following steps.

[0108] Step S502: The large model determines the knowledge retrieval rules based on the business involved.

[0109] Retrieval rules refer to a set of strategic instructions dynamically generated or selected by the large model based on key information such as the business involved in the current maintenance work order. These rules are used to determine which knowledge sources, with what priority, and using which retrieval methods to obtain the most relevant information for the work order.

[0110] Step S504: The large model processes the key information of the work order based on knowledge retrieval rules to determine the knowledge retrieval scheme. The knowledge retrieval scheme includes at least one of knowledge graph retrieval, expert corpus retrieval, and knowledge retrieval enhancement.

[0111] The retrieval plan is a specific plan at the execution level. It clarifies "what to do" and "what to use" and is the executable result output by the retrieval rules.

[0112] Knowledge graph retrieval is a method for querying and reasoning within a structured, networked knowledge system. A knowledge graph consists of "entities" (such as users, service packages, and base stations) and "relationships" (such as "belongs to," "depends on," and "cause"), forming a vast network of relationships.

[0113] Expert corpus retrieval is a method of finding relevant historical records and solutions in an unstructured text database by searching for semantic similarity. This database is like a "working notebook" storing all the past experiences and success stories of experts.

[0114] For example.

[0115] A work order scenario could be a user complaint such as "My 5G network speed is very slow, and videos buffer."

[0116] Retrieval process: The large model will search the expert corpus for historical work orders with semantic similarity to "slow 5G network speed" and "video buffering".

[0117] Search results: One historical high-quality response plan was returned, which included: "1. Suggesting the user check the signal strength of their location; 2. Guiding the user to restart their phone or turn airplane mode on and off; 3. Providing an SMS code for one-click network configuration refresh; 4. Standard reassurance script."

[0118] The core value of expert corpus retrieval can be: solving the "how to do it" problem and providing verified, directly referable or reusable solutions and script templates.

[0119] Knowledge retrieval enhancement can be a retrieval method that breaks through the boundaries of the local knowledge base and obtains the latest and most specific information in real time from external data sources (such as databases, APIs, and the Internet). When the question exceeds the scope of existing knowledge, it serves as "external assistance" for the system.

[0120] In some embodiments, the large model knowledge management module may store at least one of the following: a business knowledge graph, an expert corpus, and a knowledge retrieval enhancement scheme.

[0121] The large-scale model knowledge management module performs knowledge retrieval based on a knowledge retrieval scheme. The knowledge associated with the maintenance work order can include: if the retrieval is determined to be through a knowledge graph, then the knowledge associated with the maintenance work order is retrieved from the business knowledge graph based on the key information of the work order; if the retrieval is determined to be through an expert corpus, then the knowledge associated with the maintenance work order is retrieved from the expert corpus of the large-scale model knowledge management module; if the retrieval is determined to be through a knowledge retrieval enhancement scheme, then the knowledge associated with the maintenance work order is retrieved from the database or online using the knowledge retrieval enhancement scheme.

[0122] This technical solution achieves precise knowledge support for operation and maintenance work orders through an intelligent knowledge retrieval mechanism: the system can dynamically formulate retrieval strategies based on the work order business type, flexibly use knowledge graphs for deep relationship reasoning, match historical solutions with the help of expert corpora, and enhance the acquisition of real-time external information through knowledge retrieval, thereby constructing a complete and accurate knowledge system, providing a solid information foundation for generating high-quality return receipt solutions, and significantly improving the professionalism and reliability of operation and maintenance processing.

[0123] In some embodiments, maintenance work orders and corresponding return plans for maintenance work orders can be sent to expert objects so that expert objects can evaluate the return plans; then the evaluation of the return plans by expert objects can be received; finally, the large model knowledge management module can be updated and optimized based on maintenance work orders, return plans, and evaluations.

[0124] In some embodiments, after the complaint ticket processing system receives the solutions generated by the large model, experts can evaluate and provide feedback on the solutions based on actual business experience and user service standards (such as marking "the solution is feasible" or "apology text needs to be added"), and send the evaluation results back to the large model for model iteration and optimization.

[0125] In addition, response solutions deemed "high-quality" by experts (such as solutions with clear logic, high efficiency, and good user satisfaction) will be stored in the scenario knowledge base. These solutions will serve as new knowledge, supplementing and updating the knowledge base content, allowing subsequent work order processing to reuse richer high-quality experiences, forming a closed loop of "knowledge accumulation - solution generation - evaluation and optimization - knowledge update".

[0126] This solution introduces an expert evaluation and feedback mechanism, constructing a complete closed loop from solution generation to model optimization: the system sends the automatically generated operation and maintenance work order response solution to the expert end for manual evaluation, and updates the large model knowledge management module based on the evaluation results, thereby realizing the continuous accumulation of knowledge and the self-optimization of the system, ensuring that the operation and maintenance processing capability is continuously iterated and enhanced in actual combat.

[0127] Figure 6 This is a schematic diagram illustrating the structure of an operation and maintenance work order processing system according to an exemplary embodiment.

[0128] like Figure 6 The aforementioned operation and maintenance work order processing system can include three parts: business-side application, large model application layer, and infrastructure management.

[0129] Large Model Infrastructure Management Layer: As the underlying support of the system, it includes intelligent computing power management and invocation and general computing power management and invocation. The former dynamically allocates high-performance intelligent computing resources for scenarios with special requirements for intelligent computing power, such as large model training and inference, to ensure the efficient operation of the model; the latter is responsible for the overall scheduling of general computing power such as routine data processing and system services, so that the basic computing power of the system is allocated on demand, providing a stable "power" for the operation of upper-layer functions.

[0130] Large model application layer (i.e.) Figure 6 (Large-scale model scenario implementation): This module connects the underlying computing power with business applications and consists of knowledge management and large-scale model core capability modules.

[0131] Knowledge Management Module: Constructs a knowledge operation system, including: 1. Knowledge Graph: Organizes a knowledge network related to business rules, problem classifications, and solution relationships in complaint ticket processing. For example, it links "network failure tickets" with knowledge nodes such as "troubleshooting steps" and "common causes" to form a structured knowledge foundation. 2. Corpus Generation: Based on the knowledge graph and actual ticket scenarios, it automatically generates corpora such as dialogues and process descriptions needed to train the large-scale model, enriching the model's learning materials. 3. Enhanced Knowledge Retrieval: Optimizes knowledge query capabilities. When the large-scale model needs to call knowledge to process tickets, it quickly and accurately locates and returns relevant information from the knowledge graph to assist in decision-making.

[0132] The core capabilities of the large model focus on key technologies in natural language processing, including natural language processing and natural language generation.

[0133] Natural Language Processing: Understanding user requests and problem descriptions in work order texts, recognizing semantics, and extracting key information, such as extracting core content like "abnormal billing" and "data plan" from "abnormal billing, extra charges were deducted even though data usage was not exceeded"; Natural Language Generation: Based on the understood content and with the support of the knowledge management module, natural language text such as response messages and solutions are generated. For example, for the above-mentioned abnormal billing work order, a response is generated including but not limited to "Your data plan has not exceeded the limit. The abnormal billing was caused by a temporary billing bug in the system. It has been fixed and the overcharged amount has been refunded".

[0134] Business-side application layer: Includes existing business systems and a large-scale intelligent model for handling complaint work orders (i.e., the complaint work order processing system in the diagram), realizing the transformation of work order processing from "manual decentralized operation" to "intelligent closed-loop processing".

[0135] Existing business systems: The complaint work order processing system (which carries historical work order data and manual processing records) and the one-click diagnostic system (which stores diagnostic tools and results for network, billing, etc.) are connected to the actual operation system. As the business input source, they send the original work orders and diagnostic data to the intelligent processing model.

[0136] The intelligent complaint order processing model is the core of business processing, relying on system scheduling and connecting three key functions: - Automated work order classification: Based on the natural language processing capabilities of large models, it automatically identifies the problem type of work orders (such as network failure, fee dispute, service inquiry, etc.), replacing manual classification and improving sorting efficiency; - Complaint ticket knowledge management: On the one hand, it receives structured knowledge from the knowledge management module, and on the other hand, it feeds back new experiences (such as new fault solutions) accumulated in the handling of tickets to the knowledge graph, continuously updating the knowledge system; - Work order response solution generation: Integrating natural language generation capabilities and knowledge retrieval results, it automatically generates a complete processing solution for categorized work orders, including problem analysis, solutions, and scripted responses, which can be directly used to reply to users or guide maintenance personnel in their operations.

[0137] Figure 7 This is a flowchart illustrating a maintenance work order processing method according to an exemplary embodiment.

[0138] refer to Figure 6 and Figure 7 The above-mentioned maintenance work order processing method may include the following technical details.

[0139] The complaint work order intelligent processing system based on a large model proposed in this application revolves around "work order input - intelligent processing - solution output - knowledge closure," consisting of 7 core steps. Each step relies on the collaborative operation of system modules. For details, please refer to the appendix. Figure 7 .

[0140] Step 1: Initiate the intelligent processing flow and collect basic work order information.

[0141] Users can initiate the intelligent processing flow for complaint tickets through their actions. Once triggered, the complaint ticket processing system synchronizes the complaint content with the larger model, such as the user's feedback that "the data allowance was not exceeded but the billing was abnormal," along with the frontline dispatcher's comments (preliminary judgment from the frontline staff that "it may be a temporary bug in the billing system," etc.), providing raw input for subsequent intelligent processing.

[0142] Step 2: Extract key information from the large model and classify it intelligently.

[0143] The "Complaint Ticket Key Information Extraction & Intelligent Classification" module of the large model processes the basic information of the received tickets: first, it uses natural language processing technology to identify and extract key information such as "complaint type (e.g., fee dispute)," "related business (e.g., data plan)," and "user's core demand (e.g., refund of abnormal charges)." Then, based on the classification rules in the knowledge management module (associated with the business scenario knowledge base), it automatically determines the ticket category (e.g., classifies it as a "billing complaint ticket"), laying the foundation for accurate processing in the future.

[0144] Step 3: Query auxiliary information from the one-click diagnostic system.

[0145] The large model pushes the key information of the categorized work orders (including categorization results and extracted core requests) to the "One-Click Diagnosis (Billing) System" to initiate an information query request. Based on the received work order information, the system retrieves its stored billing and diagnostic data (such as user package tariff standards, historical billing records, and system operation logs) and provides diagnostic opinions (such as "No abnormalities were found in the system billing logic; the real-time deduction interface needs to be investigated") and diagnostic steps (such as "Step 1: Check the user package code; Step 2: Verify the deduction trigger conditions"), providing factual basis for solution generation.

[0146] Step 4: Use the scenario knowledge base to assist in solution generation.

[0147] Before generating a processing solution, the large model retrieves high-quality response solution knowledge from the "Intelligent Processing Scenario Knowledge Base for Complaint Work Orders." This knowledge consists of historically accumulated and validated work order processing templates (such as the "Standard Response Framework for Fee Dispute Work Orders" and "Troubleshooting Steps for Fault Work Orders"), which guide the generation of solutions and ensure that the solutions fit the actual business scenario and comply with processing standards.

[0148] Step 5: Generate a complaint handling plan using a large model.

[0149] By integrating the key information extracted in step 2, the diagnostic data obtained in step 3, and the scenario knowledge invoked in step 4, the "Large Model Generates Complaint Handling Solution" module of the large model automatically generates a handling solution for the current work order. For example, for a work order involving a fee dispute, the output includes a complete response containing "words to reassure the user (e.g., 'Hello, we have verified the fee anomaly you reported'), root cause analysis (e.g., 'Caused by a temporary billing bug in the system'), and a solution (e.g., 'The bug has been fixed and the overcharged amount has been refunded, expected to arrive within 24 hours')," which is then simultaneously pushed to the complaint work order processing system.

[0150] Step 6: Experts evaluate and provide feedback on the proposed solution.

[0151] After receiving the solutions generated by the large model, the complaint ticket processing system forwards them to the expert end. Based on practical business experience and user service standards, the experts evaluate and provide feedback on the solutions (such as marking "solution feasible" or "apology text needs to be added"), and then send the evaluation results back to the large model for iterative optimization.

[0152] Step 7: Store high-quality solutions in the scenario knowledge base.

[0153] Work order solutions deemed "high-quality" by experts (e.g., solutions with clear logic, high efficiency, and good user satisfaction) will be stored in the scenario knowledge base. These solutions will serve as new knowledge, supplementing and updating the knowledge base, allowing subsequent work order processing to reuse richer high-quality experiences, forming a closed loop of "knowledge accumulation - solution generation - evaluation and optimization - knowledge update".

[0154] This embodiment achieves end-to-end automated processing from work order identification to response generation by constructing a fully automated system that integrates work order input, key information extraction and classification, diagnostic information query, solution generation, and knowledge closure. After work order input, the system automatically extracts and intelligently classifies key information, eliminating the need for manual work order type filtering and switching between different systems for information entry. This automated process significantly improves the continuity and efficiency of work order processing.

[0155] Simultaneously, the existing business systems (complaint ticket processing system, one-click diagnostic system, etc.) are deeply integrated with the large model application layer, breaking down the barriers between systems. The large model application layer can acquire data from different business systems in real time, such as obtaining billing diagnostic data from the one-click diagnostic system, providing comprehensive data support for ticket processing. This enables efficient data flow and sharing between different systems, solving the problems of low processing efficiency and insufficient accuracy caused by data silos in existing technologies.

[0156] Furthermore, in the solution generation stage, the large-scale model integrates key work order information, diagnostic data, and knowledge from the scenario knowledge base to dynamically generate a complete solution that includes problem analysis, solutions, and response scripts. Unlike traditional methods that generate responses using fixed templates or simple rules, the large-scale model makes dynamic decisions based on rich data and knowledge. The generated solutions are more closely aligned with the actual work order scenario, better meeting diverse user needs and demonstrating higher intelligence and flexibility.

[0157] Finally, through expert evaluation and feedback on the generated solutions, high-quality solutions are stored in the scenario knowledge base, achieving a closed loop of "knowledge accumulation - solution generation - evaluation and optimization - knowledge update". This continuous optimization mechanism allows the system to continuously learn and accumulate new knowledge and experience. Over time, the accuracy and efficiency of work order processing will continuously improve. Most existing technologies lack such an effective knowledge update and optimization mechanism, making it difficult to adapt to constantly changing business scenarios and user needs.

[0158] This embodiment discloses an end-to-end automated processing system and method for operation and maintenance work orders based on a large network model. Addressing the system fragmentation, data silos, and compliance risks inherent in traditional manual work order processing, it achieves end-to-end automation through a three-layer architecture: the infrastructure layer provides computing power, the application layer handles knowledge management and natural language processing, and the business side completes work order classification and solution generation. This method follows an "input-processing-output-knowledge closed loop" process, overcoming the limitations of manual methods in seven steps, improving efficiency and accuracy, reducing costs and risks, and providing an intelligent solution for operation and maintenance work order processing.

[0159] In summary, the technical solutions provided by the above embodiments have at least the following beneficial effects.

[0160] 1. The large-scale model is a self-developed model trained using proprietary network data. This solution deeply integrates the entire chain of work order classification, interface calls, and response generation through the large-scale network model to build an end-to-end automated processing system, fundamentally replacing manual operation, greatly improving processing efficiency and accuracy, and breaking through the limitations of the traditional model.

[0161] 2. Through deep integration between the large-scale model application layer and business-side systems, real-time data flow and cross-system collaboration are achieved. This ensures comprehensive information while eliminating redundant manual system switching operations, achieving the dual goals of efficient processing and accurate responses. Furthermore, by solidifying compliance protocols and processing logic within the system, the risk of default is reduced to near zero, achieving both process simplification and risk control optimization while maintaining processing quality.

[0162] 3. This solution deeply integrates it into the entire work order processing process, enabling end-to-end empowerment from information extraction and classification decision-making to solution generation. For the first time in an operation and maintenance scenario, it has built a three-in-one automated architecture of "business system - knowledge system - big model capability", providing a new paradigm for the intelligent upgrade of the industry.

[0163] It should be particularly noted that the steps in each embodiment of the above-described operation and maintenance data processing method can be overlapped, substituted, added, or deleted. Therefore, these reasonable permutations and combinations of operation and maintenance data processing methods should also fall within the protection scope of this disclosure, and the protection scope of this disclosure should not be limited to the described embodiments.

[0164] Based on the same inventive concept, this disclosure also provides an operation and maintenance data processing system, as described in the following embodiments. Since the principle by which this system embodiment solves the problem is similar to that of the above method embodiment, the implementation of this system embodiment can refer to the implementation of the above method embodiment, and repeated details will not be repeated.

[0165] Figure 8 This is a block diagram illustrating an operation and maintenance data processing system according to an exemplary embodiment. (Refer to...) Figure 8 The operation and maintenance data processing system 800 provided in this embodiment may include: a large model network 801, a business diagnosis system 802, and a large model knowledge management module 803.

[0166] The large model network can be used to obtain operation and maintenance work orders; key information is extracted from the operation and maintenance work orders to obtain key information of the work orders; the key information of the work orders includes at least one of the following: complaint type, involved business, and user request; based on the key information of the work orders, the business diagnosis system is invoked to perform anomaly diagnosis and obtain the returned anomaly diagnosis opinion; based on the involved business, the corresponding return order solution template is matched from the scenario knowledge base; based on the key information of the work orders, the anomaly diagnosis opinion, and the return order solution template, a return order solution for the operation and maintenance work orders is generated.

[0167] In some embodiments, the business diagnostic system may be used to determine the user identification information corresponding to the maintenance work order based on the key information; retrieve the business data corresponding to the user identification from multiple business systems; perform anomaly diagnosis based on the business data corresponding to the user identification to obtain anomaly diagnosis data; and generate the anomaly diagnosis opinion based on the anomaly diagnosis data.

[0168] In some embodiments, the key information of the work order further includes the operation and maintenance type; wherein the large model can also be used to obtain classification rules from the large model knowledge management module; the key information of the operation and maintenance work order is processed based on the classification rules to determine the operation and maintenance type of the operation and maintenance work order.

[0169] In some embodiments, generating a receipt for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinion, and the receipt template may include: the large model calling the large model knowledge management module to perform knowledge retrieval based on the key information of the work order to obtain knowledge associated with the maintenance work order; and the large model generating a receipt for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinion, the receipt template, and the knowledge associated with the maintenance work order.

[0170] In some embodiments, the large model calls the large model knowledge management module to perform knowledge retrieval based on the key information of the work order to obtain knowledge associated with the maintenance work order. This may include: the large model determining knowledge retrieval rules based on the business involved; the large model processing the key information of the work order based on the knowledge retrieval rules to determine a knowledge retrieval scheme, wherein the knowledge retrieval scheme includes at least one of knowledge graph retrieval, expert corpus retrieval, and knowledge retrieval enhancement.

[0171] In some embodiments, the large model knowledge management module can be used to perform knowledge retrieval based on the knowledge retrieval scheme and determine the knowledge associated with the maintenance work order.

[0172] In some embodiments, the large-scale model knowledge management module stores at least one of a business knowledge graph, expert corpus, and a knowledge retrieval enhancement scheme; wherein, the large-scale model knowledge management module performs knowledge retrieval based on the knowledge retrieval scheme, and determining the knowledge associated with the maintenance work order may include: if it is determined to retrieve through a knowledge graph, then retrieving knowledge associated with the maintenance work order from the business knowledge graph according to the key information of the work order; if it is determined to retrieve through expert corpus, then retrieving knowledge associated with the maintenance work order from the expert corpus of the large-scale model knowledge management module; if it is determined to retrieve through a knowledge retrieval enhancement scheme, then retrieving knowledge associated with the maintenance work order from a database or through a network using the knowledge retrieval enhancement scheme.

[0173] In some embodiments, the large model network can also send the maintenance work order and the response plan for the maintenance work order to an expert object so that the expert object can evaluate the response plan; receive the evaluation of the response plan from the expert object; and update and optimize the large model knowledge management module based on the maintenance work order, the response plan, and the evaluation.

[0174] It should be noted that the large model network 801, business diagnosis system 802 and large model knowledge management module 803 mentioned above correspond to S202 to S206 in the method embodiment. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above method embodiment.

[0175] Since the functions of system 800 have been described in detail in their corresponding method embodiments, they will not be repeated here.

[0176] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a portion of a module or program segment containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer program instructions.

[0177] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0178] Figure 9 A schematic diagram of an electronic device suitable for implementing embodiments of the present disclosure is shown. It should be noted that... Figure 9 The electronic device 900 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0179] like Figure 9 As shown, the electronic device 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage section 908 into a random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device 900. The CPU 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0180] The following components are connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 910 as needed so that computer programs read from it can be installed into storage section 908 as needed.

[0181] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing computer program instructions for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 909, and / or installed from removable medium 911. When the computer program is executed by central processing unit (CPU) 901, it performs the functions defined above in the system of this disclosure.

[0182] It should be noted that the computer-readable storage medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, 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 device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable computer program instructions. 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 can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Computer program instructions contained on a computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0183] In another aspect, this disclosure also provides a computer-readable storage medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the device, enable the device to perform the following functions: a large model acquires maintenance work orders; the large model extracts key information from the maintenance work orders to obtain key information of the work orders; wherein the key information of the work orders includes at least one of complaint type, involved business, and user request; the large model, based on the key information of the work orders, calls a business diagnostic system to perform anomaly diagnosis and obtains the returned anomaly diagnosis opinion; the large model, based on the involved business, matches the corresponding return order solution template from the scenario knowledge base; the large model generates a return order solution for the maintenance work orders based on the key information of the work orders, the anomaly diagnosis opinion, and the return order solution template.

[0184] According to one aspect of this disclosure, a computer program product or computer program is provided, comprising computer program instructions stored in a computer-readable storage medium. The computer program instructions are read from the computer-readable storage medium, and a processor executes the computer program instructions to implement the methods provided in various optional implementations of the above embodiments.

[0185] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions of the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive) and includes several computer program instructions to cause an electronic device (such as a server or terminal device) to execute the method according to the embodiments of this disclosure.

[0186] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0187] It should be understood that this disclosure is not limited to the detailed structures, drawing arrangements or implementations shown herein; rather, this disclosure is intended to cover various modifications and equivalent arrangements contained within the spirit and scope of the appended claims.

Claims

1. A method for processing operation and maintenance data, characterized in that, include: Large-scale model for obtaining maintenance work orders; The large model extracts key information from the maintenance work order to obtain key information of the work order; wherein, the key information of the work order includes at least one of the following: complaint type, business involved, and user request; The large model calls the business diagnostic system to perform anomaly diagnosis based on the key information of the work order, and obtains the returned anomaly diagnosis opinion. The large model matches the corresponding return order template from the scenario knowledge base based on the business involved. The large model generates a response plan for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinions, and the response plan template.

2. The method according to claim 1, characterized in that, The method further includes: The business diagnostic system determines the user identification information corresponding to the maintenance work order based on the key information of the work order. The business diagnostic system retrieves the business data corresponding to the user identifier from multiple business systems; The business diagnostic system performs anomaly diagnosis based on the business data corresponding to the user identifier and obtains anomaly diagnostic data. The abnormal diagnostic opinion is generated based on the abnormal diagnostic data.

3. The method according to claim 1, characterized in that, The key information in the work order also includes the maintenance type; the method further includes: The large model obtains classification rules from the large model knowledge management module; The large model processes the key information of the operation and maintenance work order based on the classification rules to determine the operation and maintenance type of the operation and maintenance work order.

4. The method according to claim 1, characterized in that, The large model generates a response for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinions, and the response plan template, including: The large model calls the large model knowledge management module to perform knowledge retrieval based on the key information of the work order, and obtains the knowledge associated with the maintenance work order; The large model generates a response plan for the maintenance work order based on the key information of the work order, the anomaly diagnosis opinions, the response plan template, and the knowledge associated with the maintenance work order.

5. The method according to claim 4, characterized in that, The large model, based on the key information of the work order, calls the large model knowledge management module to perform knowledge retrieval and obtain knowledge associated with the maintenance work order, including: The large model determines knowledge retrieval rules based on the relevant business; The large model processes the key information of the work order based on the knowledge retrieval rules to determine a knowledge retrieval scheme, which includes at least one of knowledge graph retrieval, expert corpus retrieval, and knowledge retrieval enhancement. The large-scale model knowledge management module performs knowledge retrieval based on the knowledge retrieval scheme to determine the knowledge associated with the maintenance work order.

6. The method according to claim 1, characterized in that, The method further includes: The maintenance work order and the response plan for the maintenance work order are sent to the expert object so that the expert object can evaluate the response plan; Receive the expert's evaluation of the return receipt scheme; Based on the maintenance work order, the return receipt scheme, and the evaluation, the large model knowledge management module is updated and optimized.

7. An operation and maintenance data processing system, characterized in that, include: Large model used to obtain operation and maintenance work orders; Key information is extracted from the maintenance work order to obtain key work order information; wherein, the key work order information includes at least one of the following: complaint type, involved business, and user request; based on the key work order information, the business diagnosis system is invoked to perform anomaly diagnosis and obtain the returned anomaly diagnosis opinion; based on the involved business, the corresponding return order solution template is matched from the scenario knowledge base; based on the key work order information, the anomaly diagnosis opinion, and the return order solution template, a return order solution is generated for the maintenance work order.

8. An electronic device, characterized in that, include: Memory and processor; The memory is used to store computer program instructions; the processor calls the computer program instructions stored in the memory to implement the operation and maintenance data processing method as described in any one of claims 1-6.

9. A computer-readable storage medium storing computer program instructions thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the operation and maintenance data processing method as described in any one of claims 1-6.

10. A computer program product comprising computer program instructions stored in a computer-readable storage medium, characterized in that, When the computer program instructions are executed by the processor, they implement the method according to any one of claims 1-6.

Images