Intelligent management and control method and device for operation and maintenance work order, program product and electronic equipment

Abstract

The invention relates to the technical field of network operation and maintenance, and relates to an intelligent management and control method and device for an operation and maintenance work order, a computer program product and electronic equipment. The method comprises the steps of performing intention recognition on demand description information in an operation and maintenance work order based on a work order management and control agent, and determining a work order type and a work order task of the operation and maintenance work order according to an intention recognition result; according to the work order type and the work order task, generating an operation and maintenance guidance scheme of the operation and maintenance work order based on the operation and maintenance corpus knowledge base through the work order management and control agent; determining a target operation and maintenance worker based on the work order type, a work order adaptation model and a work order intelligent scheduling strategy through a work order management and control agent, wherein the work order adaptation model is a model representing the adaptation degree of the operation and maintenance worker and the operation and maintenance work order; and automatically distributing the operation and maintenance work order and the operation and maintenance guidance scheme to the target operation and maintenance personnel, and performing automatic order staring management and control on the operation and maintenance work order through the work order management and control agent so as to complete the disposal of the operation and maintenance work order. The management and control processing efficiency and quality of the operation and maintenance work order can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of network operation and maintenance technology, and more specifically, to an intelligent management and control method for operation and maintenance work orders, an intelligent management and control device for operation and maintenance work orders, a computer program product, and an electronic device. Background Technology

[0002] The delivery and maintenance of operator services are fundamental services provided to customers and are also important for ensuring service quality and improving customer experience. Therefore, efficient and high-quality delivery and maintenance have always been the goals of operators.

[0003] Network maintenance work is primarily quantified and assigned to maintenance engineers through electronic work orders. These work orders record the completion status of multiple important customer service steps. Currently, the scheduling, dispatch, and quality control of maintenance work orders mainly rely on manual methods, with dedicated personnel monitoring the flow and processing of work orders. However, the sheer volume of daily work orders leads to low overall efficiency due to manual monitoring. For recurring faulty work orders, overdue work orders, and work orders from important customers requiring special attention, there is a risk of untimely anomaly warnings and delayed human intervention. Furthermore, operators currently primarily assign maintenance work orders to fixed maintenance engineers based on regional allocation, a method lacking flexibility. Therefore, efficient management of maintenance work orders is a pressing issue that needs to be addressed.

[0004] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide an intelligent management and control method for operation and maintenance work orders, an intelligent management and control device for operation and maintenance work orders, a computer program product, and an electronic device, thereby improving the efficiency and quality of management and processing 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] According to one aspect of this disclosure, an intelligent management and control method for operation and maintenance work orders is provided, comprising: performing intent recognition on the requirement description information in the operation and maintenance work order based on the work order management and control intelligent agent, and determining the work order type and work order task of the operation and maintenance work order based on the intent recognition result; generating an operation and maintenance guidance plan for the operation and maintenance work order based on the operation and maintenance corpus knowledge base by the work order management and control intelligent agent according to the work order type, work order adaptation model and work order intelligent scheduling strategy, wherein the work order adaptation model is a model representing the fit between the operation and maintenance personnel and the operation and maintenance work order; automatically dispatching the operation and maintenance work order and the operation and maintenance guidance plan to the target operation and maintenance personnel, and automatically monitoring and controlling the operation and maintenance work order through the work order management and control intelligent agent to complete the handling of the operation and maintenance work order.

[0008] In one exemplary embodiment of this disclosure, the work order management agent performs intent recognition on the requirement description information in the operation and maintenance work order, and determines the work order type and work order task based on the intent recognition result. This includes: using the work order management agent, performing intent recognition on the requirement description information using a network big data model to obtain the work order type; and using the work order type, classifying the requirement description information into tasks using a network big data model to obtain the work order task.

[0009] In one exemplary embodiment of this disclosure, the method further includes: determining a training corpus based on historical maintenance work orders, corresponding historical maintenance information, and maintenance theory knowledge; training and fine-tuning a large language model based on the training corpus to obtain a large network model; and storing the work order maintenance corpus in a maintenance corpus knowledge base, which is used to provide retrieval knowledge to the large network model.

[0010] In one exemplary embodiment of this disclosure, based on the work order type and work order task, an operation and maintenance guidance scheme for the operation and maintenance work order is generated by a work order management intelligent agent based on an operation and maintenance corpus knowledge base. This includes: the work order management intelligent agent using a large network model to analyze the work order type and work order task based on the operation and maintenance corpus knowledge base to obtain analysis results; and integrating the analysis results to obtain the operation and maintenance guidance scheme for the operation and maintenance work order.

[0011] In one exemplary embodiment of this disclosure, the target maintenance personnel are determined by a work order management intelligent agent based on work order type, work order adaptation model, and work order intelligent scheduling strategy. This includes: determining candidate maintenance personnel matching the work order type based on the work order intelligent scheduling strategy and the skill level of the maintenance personnel; determining reference maintenance personnel within the geographical range of the candidate maintenance personnel based on the geographical information of the maintenance work order; calculating the work order adaptation degree of the reference maintenance personnel based on the work order adaptation model; and determining the target maintenance personnel from the reference maintenance personnel based on the work order adaptation degree.

[0012] In one exemplary embodiment of this disclosure, the work order adaptation degree of the reference maintenance personnel is calculated based on the work order adaptation model, including: obtaining multi-dimensional features of the reference maintenance personnel, the multi-dimensional features including service evaluation value, travel time to complete maintenance work order and maintenance time; inputting the multi-dimensional features into the work order adaptation model to output the work order adaptation degree of the reference maintenance personnel.

[0013] In one exemplary embodiment of this disclosure, determining a target maintenance personnel from a pool of reference maintenance personnel based on work order suitability includes: determining a candidate maintenance personnel from the pool of reference maintenance personnel based on work order suitability; if the work order suitability of the candidate maintenance personnel meets a preset condition with respect to the historical average suitability, then the candidate maintenance personnel is determined as the target maintenance personnel, wherein the historical average suitability is determined based on the work order suitability of historical maintenance personnel corresponding to the work order type within a preset statistical period, and the preset condition is used to assess whether the candidate maintenance personnel is allowed to execute maintenance work orders; if the work order suitability of the candidate maintenance personnel does not meet the preset condition with respect to the historical average suitability, then the target maintenance personnel is determined from at least one higher skill level among the maintenance personnel.

[0014] In one exemplary embodiment of this disclosure, the method further includes: for each type of work order, updating the historical average fit of the work order type by using the work order fit of the target maintenance personnel of the maintenance work order under the work order type at preset time intervals.

[0015] In one exemplary embodiment of this disclosure, maintenance work orders and maintenance guidance plans are automatically dispatched to target maintenance personnel, and the maintenance work orders are automatically monitored and managed through a work order management intelligent agent. This includes: automatically dispatching maintenance work orders and maintenance guidance plans to target maintenance personnel; obtaining the execution information of target maintenance personnel at key management nodes, and managing the maintenance status of maintenance work orders based on the execution information; wherein, key management nodes include at least a service stage, a delivery stage, and a follow-up stage.

[0016] According to one aspect of this disclosure, an intelligent management and control device for operation and maintenance work orders is provided, comprising: an intent recognition module, used to perform intent recognition on the demand description information in the operation and maintenance work order based on the work order management intelligent agent, and determine the work order type and work order task of the operation and maintenance work order based on the intent recognition result; a solution generation module, used to generate an operation and maintenance guidance solution for the operation and maintenance work order based on the work order type and work order task through the work order management intelligent agent using an operation and maintenance corpus knowledge base; a determination module, used to determine the target operation and maintenance personnel through the work order management intelligent agent based on the work order type, work order adaptation model and work order intelligent scheduling strategy, wherein the work order adaptation model is a model representing the fit between the operation and maintenance personnel and the operation and maintenance work order; and a work order intelligent management and control module, used to automatically dispatch the operation and maintenance work order and the operation and maintenance guidance solution to the target operation and maintenance personnel, and to automatically monitor and manage the operation and maintenance work order through the work order management intelligent agent to complete the processing of the operation and maintenance work order.

[0017] According to one aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements any of the above methods.

[0018] According to one aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above methods by executing the executable instructions.

[0019] The intelligent management method for operation and maintenance work orders in the exemplary embodiments of this disclosure first performs intent recognition on the requirement description information in the operation and maintenance work order based on the work order management intelligent agent, and determines the work order type and work order task based on the intent recognition result; then, based on the work order type and work order task, the operation and maintenance guidance plan for the operation and maintenance work order is generated by the work order management intelligent agent based on the operation and maintenance corpus knowledge base; next, the target operation and maintenance personnel are determined by the work order management intelligent agent based on the work order type, work order adaptation model, and work order intelligent scheduling strategy, where the work order adaptation model is a model representing the fit between the operation and maintenance personnel and the operation and maintenance work order; finally, the operation and maintenance work order and the operation and maintenance guidance plan are automatically dispatched to the target operation and maintenance personnel, and the operation and maintenance work order is automatically monitored and managed by the work order management intelligent agent to complete the processing of the operation and maintenance work order.

[0020] On the one hand, starting from the generation of maintenance work orders, the intent of the requirement description information in the work order is identified and understood to clarify the work order type and task. Maintenance guidance plans are generated through content generation capabilities, and target maintenance personnel are determined based on the work order type, work order adaptation model, and intelligent work order scheduling strategy. This allows for the automatic dispatch of maintenance work orders and maintenance guidance plans to the target maintenance personnel. Intelligent orchestration capabilities enable automated management of the entire lifecycle of maintenance work orders, controlling the completion time and quality of work order flow, processing, and closure without manual intervention, effectively improving work order management efficiency and appropriately reducing personnel input. On the other hand, by using a work order management intelligent agent to determine target maintenance personnel based on work order type, work order adaptation model (representing the compatibility between maintenance personnel and maintenance work orders), and intelligent work order scheduling strategy, the accuracy and full utilization of human resources can be ensured, enabling more targeted and rapid completion of maintenance work orders and improving processing efficiency.

[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0022] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation.

[0023] Figure 1 The diagram illustrates an application environment related to an intelligent management method for operation and maintenance work orders, as exemplified by an exemplary embodiment of this disclosure.

[0024] Figure 2 A flowchart of an intelligent management method for operation and maintenance work orders according to an exemplary embodiment of the present disclosure is shown.

[0025] Figure 3 A technical architecture diagram of a network big model technology architecture according to an exemplary embodiment of the present disclosure is shown.

[0026] Figure 4 A flowchart illustrating a method for determining the work order type and work order task of an operation and maintenance work order according to an exemplary embodiment of the present disclosure is shown.

[0027] Figure 5 A schematic diagram of a method for generating operation and maintenance guidance according to an exemplary embodiment of the present disclosure is shown.

[0028] Figure 6 A flowchart illustrating the determination of target maintenance personnel according to an exemplary embodiment of this disclosure is shown.

[0029] Figure 7 A complete flowchart of intelligent management and control of operation and maintenance work orders according to an exemplary embodiment of this disclosure is shown.

[0030] Figure 8 A schematic diagram of the composition of an intelligent management and control device for maintenance work orders according to an exemplary embodiment of the present disclosure is shown.

[0031] Figure 9 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0032] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0033] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0034] Furthermore, the described features, structures, or characteristics 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 without one or more of the specific details described, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known structures, methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0035] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more software-hardened modules, or in different network and / or processor devices and / or microcontroller devices.

[0036] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0037] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0038] Machine learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and the theory of algorithmic complexity. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instruction-based learning.

[0039] Large Language Models (LLMs) are deep learning-based artificial intelligence systems that learn, understand, and generate human language by training on extremely large text datasets. LLMs can be built on the Transformer model architecture, whose core is the self-attention mechanism, enabling the model to efficiently process sequential data (such as word sequences) and understand the complex relationships between distant words in text.

[0040] The exemplary embodiments disclosed herein provide a technical solution involving large speech models and machine learning technology. By combining large language models and machine learning technology, automated management and control of the entire lifecycle of operation and maintenance work orders can be achieved, and the completion time and quality of work order flow, processing, and closure can be controlled.

[0041] It should be noted that the exemplary embodiments of this disclosure can be applied to scenarios requiring operation and maintenance work order management, such as the operation and maintenance work order management of operators, enterprises, communities, etc., and the exemplary embodiments of this disclosure do not limit this. The exemplary embodiments of this disclosure are illustrated using the operation and maintenance work order management of an operation and maintenance provider as an example.

[0042] The intelligent management method for operation and maintenance work orders provided in the exemplary embodiments of this disclosure can be applied to, for example... Figure 1 The application environment shown is illustrated. Terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102, or it can be located in the cloud or on another network server.

[0043] In one exemplary embodiment, the intelligent management method for operation and maintenance work orders provided by the exemplary embodiment of this disclosure can be executed by server 102, and correspondingly, the processing device for operation and maintenance work orders is set in server 102. Correspondingly, in this method of execution by server 102, server 102 can start executing the steps in the technical solution of the exemplary embodiment of this disclosure in response to a triggering command, wherein the triggering command can be sent by a terminal used by a user, or can be triggered locally by the server in response to some automated events.

[0044] Server 102 can be a standalone physical server, a server cluster or distributed system composed 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, and big data and artificial intelligence platforms. Server 102 can execute background tasks.

[0045] Furthermore, in another exemplary embodiment, terminal 101 may also have similar functions to server 102, thereby executing the intelligent management method for operation and maintenance work orders provided by the exemplary embodiments of this disclosure.

[0046] The terminal 101 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, IoT device, or portable wearable device. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. The terminal 101 can also be referred to as a mobile terminal, terminal device, mobile device, etc. The exemplary embodiments of this disclosure do not limit the type of terminal 101.

[0047] Furthermore, the technical solutions of the exemplary embodiments of this disclosure can also be executed collaboratively by terminal 101 and server 102. In this collaborative execution method, some steps of the technical solutions provided by the exemplary embodiments of this disclosure are executed by terminal 101, while other steps are executed by server 102. It should be noted that in this collaborative execution method, the steps executed by terminal 101 and server 102 respectively can be dynamically adjusted according to actual circumstances, and no special restrictions are placed on this. Terminal 101 and server 102 can be directly or indirectly connected via wireless communication, and the exemplary embodiments of this disclosure do not impose any special restrictions here.

[0048] Network maintenance work is primarily quantified and assigned to maintenance engineers through electronic work orders. These work orders record the completion status of multiple important customer service steps. Currently, the scheduling, dispatch, and quality control of maintenance work orders mainly rely on manual methods, with dedicated personnel monitoring the flow and handling of work orders. However, the sheer volume of daily work orders makes manual monitoring inefficient. For recurring issues, overdue work orders, and work orders from important customers requiring special attention, there is a risk of delayed alerts and insufficient human intervention. Furthermore, operators currently assign maintenance work orders to fixed maintenance engineers based on designated areas, a method lacking flexibility.

[0049] Based on one or more of the above-mentioned problems, exemplary embodiments of this disclosure provide an intelligent management and control method for operation and maintenance work orders, such as... Figure 2 The diagram shown is a flowchart of an intelligent management method for operation and maintenance work orders, an exemplary embodiment of this disclosure. The method includes: Step S210: Based on the work order management intelligent agent, perform intent recognition on the requirement description information in the operation and maintenance work order, and determine the work order type and work order task of the operation and maintenance work order according to the intent recognition result.

[0050] Step S220: Based on the work order type and work order task, the work order management intelligent agent generates an operation and maintenance guidance plan for the operation and maintenance work order based on the operation and maintenance corpus knowledge base.

[0051] Step S230: The work order management intelligent agent determines the target maintenance personnel based on the work order type, work order adaptation model and work order intelligent scheduling strategy. The work order adaptation model is a model that represents the degree of adaptation between maintenance personnel and maintenance work orders.

[0052] Step S240: Automatically dispatch maintenance work orders and maintenance guidance plans to the target maintenance personnel, and automatically monitor and manage the maintenance work orders through the work order management intelligent agent to complete the processing of maintenance work orders.

[0053] According to the exemplary embodiments of this disclosure, the intelligent management method for operation and maintenance work orders, on the one hand, starts from the generation of the operation and maintenance work order. By identifying and understanding the intent of the requirement description information in the work order, the work order type and work order task are clarified. An operation and maintenance guidance plan is generated through content generation capabilities, and the target operation and maintenance personnel are determined based on the work order adaptation model. The operation and maintenance work order and the operation and maintenance guidance plan are then automatically dispatched to the target operation and maintenance personnel. Intelligent orchestration capabilities enable automated management and control of the entire lifecycle of the operation and maintenance work order, ensuring the completion time and quality of work order flow, handling, and closure without manual intervention. This effectively improves work order management efficiency and appropriately reduces personnel input. On the other hand, by using a work order management intelligent agent to determine the target operation and maintenance personnel based on the work order type, the work order adaptation model (representing the compatibility between operation and maintenance personnel and the operation and maintenance work order), and the intelligent work order scheduling strategy, the accurate and full utilization of human resources can be guaranteed, thereby enabling more targeted and rapid completion of operation and maintenance work orders and improving processing efficiency.

[0054] Steps S210 to S240 will be described in more detail below.

[0055] In step S210, the work order management intelligent agent performs intent recognition on the requirement description information in the operation and maintenance work order, and determines the work order type and work order task based on the intent recognition result.

[0056] In the exemplary embodiments disclosed herein, the work order management intelligent agent is a core intelligent processing unit, not a simple program or module. The work order management intelligent agent should be understood as a software entity that encapsulates an artificial intelligence (AI) model, business rules, decision-making logic, and data processing capabilities. Its "intelligence" is reflected in its ability to autonomously or semi-autonomously perceive (read work order information), understand (identify intent), reason (determine type and task), make decisions (dispatch and manage work orders), and execute actions (generate solutions and dispatch work orders). The work order intelligent agent can utilize large network models and machine learning models to execute maintenance work order processing methods.

[0057] Optionally, the work order management intelligent agent may include or call network large models and machine learning models, including but not limited to large language models, natural language processing models, intent classification models, text classification models, named entity recognition models, etc., operation and maintenance knowledge base (which stores professional knowledge, business logic and judgment rules in the operation and maintenance field to assist reasoning and decision-making), and API (Application Programming Interface) interfaces for data interaction with other components such as operation and maintenance knowledge base, personnel database, and work order system.

[0058] The requirement description information is free text filled in by maintenance personnel or users when submitting a work order, used to describe the fault phenomenon, operational needs, or change requests. This is the primary data source for intelligent agents to recognize intent. Work order type is a high-level, standardized classification of work orders based on the nature and process of the maintenance work; for example, it may include work orders for new service activation or work orders for repairing existing service faults. Work order task is a more granular classification than work order type, specifically specifying the maintenance operations to be performed, directly related to the subsequent maintenance guidance plan to be generated and the skills of the target maintenance personnel to be matched. Examples include broadband new customer installation or broadband internet access failure.

[0059] In some optional embodiments, the work order management intelligent agent is based on a large language model, leveraging the intent recognition and intelligent orchestration capabilities of the large model to construct intelligent agent applications in the operator network domain. This can be understood as training and learning from the professional knowledge and unique data of the operator network domain on the basis of a general large language model to generate a network large model. This model possesses rule-based understanding of network knowledge content and intelligent decision-making capabilities, empowering network AI applications. The network large model technical architecture mainly includes a foundation layer, an algorithm model layer, a service layer, and an application layer.

[0060] Specifically, such as Figure 3 The diagram shown is a technical architecture diagram of a large-scale network model, which endows the work order agent with AI capabilities. The technical architecture diagram will be explained first.

[0061] The foundational layer comprises high-performance hardware resources and a multimodal corpus (such as a training corpus). Compared to traditional AI models, large-scale models have training parameters in the hundreds of billions, trained using massive amounts of multimodal data to achieve higher performance and accuracy. Accordingly, the exemplary embodiments of this disclosure utilize servers equipped with graphics processing units (GPUs) and AI chips to form a high-performance intelligent computing cluster, providing support and assurance for the large-scale model training process and inference capabilities.

[0062] Among them, the training corpus sample library serves as the knowledge source for the learning and training of large models. It mainly includes pre-training sample data based on general knowledge and fine-tuning sample data based on network domain expertise. It unifies and organizes scattered multi-category knowledge content to form a high-quality network large model corpus sample library, providing a solid corpus foundation for network large models.

[0063] The algorithm model layer includes the Transformer algorithm, Retrieval-Augmented Generation (RAG), and various AI model capabilities related to network operation and maintenance. The large-scale network model is built on the underlying Transformer algorithm, adopting a decoder-only architecture. It is pre-trained using large-scale unlabeled general knowledge data, and then fine-tuned using a small amount of labeled high-quality network domain-specific knowledge data. During iterative training, the large-scale network model develops strong semantic and contextual understanding capabilities. By mining the potential connections between knowledge, it can perform reasonable logical reasoning and content integration and arrangement based on known content to generate high-quality content that meets the needs of operator network applications.

[0064] One key issue is the "illusion problem" in large-scale network models. This problem arises when large-scale models generate inaccurate, incomplete, and misleading content without any factual basis, especially when inputting personalized content or content not included in the training data. Currently, this problem cannot be effectively solved through algorithm optimization. Therefore, this exemplary embodiment combines large-scale network models with RAG (Relational Analytics Group) technology to construct a RAG knowledge base (i.e., an operational corpus knowledge base) that vectorizes and stores general knowledge and network domain expertise. During the process of generating output content based on the input, the large-scale network model dynamically retrieves highly relevant information from the knowledge base using RAG to assist in its response. This precise matching of knowledge content ensures controllable content generation, significantly improving the accuracy of the generated content and effectively resolving the illusion problem.

[0065] In specific high-demand application scenarios, the large network model, combined with the capabilities of small AI models (such as work order adaptation models) and API interfaces, can better leverage the value of the large model. By combining the dynamic information obtained from small AI models and API interfaces, the large network model can generate highly accurate content in a targeted manner, empowering more diverse and complex scenarios.

[0066] The service layer includes large-scale model capabilities such as intent understanding, text generation, and image generation. Supported by high-performance computing power and high-quality data, the model is trained using the Transformer algorithm and specialized network domain knowledge and unique data to form a large-scale network model that can provide generative AI services. This large-scale network model can generate text, images, audio, code, and other content with a certain degree of logic and fluency based on the input content and model rules. For specific needs of network application scenarios, the services provided by the large-scale network model can be encapsulated, invoked, and customized to solve practical problems according to the requirements of the application scenario.

[0067] The application layer includes large-scale model applications such as knowledge-based question answering, solution generation, and intelligent agents. The capabilities of the large network model are orchestrated according to the application requirements of different scenarios to build intelligent tools that assist in network operation and maintenance.

[0068] The work order management intelligent agent uses a large network model as its central brain. It acquires text information based on natural language understanding to analyze and locate problems, and provides corresponding decision-making solutions based on experience and knowledge. It also calls appropriate APIs to execute corresponding operations, completing the automatic closed loop of the handling process. The intelligent agent application, which combines large and small models (the large network model and the machine learning model), can realize the automation of the handling process.

[0069] In some alternative embodiments, such as Figure 4 As shown, the work order management intelligent agent performs intent recognition on the requirement description information in the maintenance work order, and determines the work order type and work order task based on the intent recognition result, including: Step S410: Through the work order management intelligent agent, the network big data model is used to perform intent recognition on the demand description information to obtain the work order type.

[0070] By leveraging a large network model to perform semantic understanding and intent recognition on the demand description information, the work order type is determined, such as a new service activation work order or an existing service fault repair work order. Since the operations and tools required by maintenance personnel differ under different work order types, and the key aspects of work order management also differ, clearly defining the work order type facilitates the intelligent orchestration of subsequent calls by the work order management agent.

[0071] Step S420: Based on the work order type, use the network big data model to classify the requirement description information into tasks to obtain the work order tasks.

[0072] After determining the work order type, the network big data model can be used to perform graph requirement classification, i.e., task classification, on the requirement description information, thereby obtaining the specific work order tasks under the work order type. For example, broadband new customer installation or broadband inability to access the internet, etc.

[0073] The exemplary embodiments disclosed herein, through a large-scale network model possessing hundreds of billions of parameters and operational knowledge pre-trained on massive amounts of text, can deeply understand the context, semantics, and implicit intent within requirement descriptions. Even if the requirement descriptions contain new terms, combinations, or ambiguous expressions never seen in the training data, the large-scale network model can make reasonable inferences and classifications based on its powerful language generation and understanding capabilities, greatly reducing misjudgments and failures to identify requirements, and improving recognition accuracy and generalization ability. Furthermore, by first determining the work order type and then the work order task, the first stage (intent recognition) focuses on macro-level qualitative analysis, shielding against detailed interference to determine the work order type; the second stage (task classification) performs precise positioning within the known macro-framework, i.e., determining the work order task. This processing method has a clear logical structure, reducing the complexity of each model decision.

[0074] In step S220, based on the work order type and work order task, the work order management agent generates an operation and maintenance guidance plan for the operation and maintenance work order based on the operation and maintenance corpus knowledge base.

[0075] In the exemplary embodiments of this disclosure, the operations and maintenance corpus knowledge base is a deeply processed and organized, machine-readable and understandable structured knowledge system that serves as the logical basis and knowledge reserve for the network large-scale model. The operations and maintenance corpus knowledge base may include historical operations and maintenance work order information, including but not limited to detailed records of resolved work orders, such as problem descriptions, root causes, resolution steps, commands used, solutions, personnel involved, and time taken, which can be vectorized and stored in the operations and maintenance corpus knowledge base.

[0076] The operation and maintenance guidance plan is an actionable guide automatically generated by the work order management intelligent agent, specifically for operation and maintenance work orders. Leveraging the solution generation capabilities of the network big data model, the operation and maintenance work order management intelligent agent generates handling plan guidance based on the work order task requirements, assisting operation and maintenance personnel in their operations. This is particularly helpful for novice operation and maintenance personnel or for handling the installation and faults of newly launched services, providing guidance to enable them to handle certain issues and improving the efficiency and quality of operation and maintenance work.

[0077] For example, for new service activation work orders, based on the customer's installation requirements, we provide a solution guide that includes installation activation steps and the tools to bring; for fault repair work orders, based on the customer's description of the fault phenomenon, we provide a solution guide that includes fault cause prediction and handling steps.

[0078] In some alternative embodiments, a large network model can be obtained by fine-tuning a pre-trained large language model and constructing an operational corpus knowledge base.

[0079] Specifically, a training corpus can be determined first based on historical maintenance work orders, corresponding historical maintenance information, and maintenance theory knowledge. Then, based on the training corpus, the large language model can be trained and fine-tuned to obtain the large network model. Finally, the work order maintenance corpus is stored in the maintenance corpus knowledge base, which is used to provide retrieval knowledge to the large network model.

[0080] Historical maintenance work orders are raw data assets, which may include structured data of the work orders themselves, such as work order ID, creation time, work order status, requirement description information, work order type (manually annotated), work order task (manually annotated), assigned personnel, resolution time, etc. Historical maintenance information is richer process and result data related to historical maintenance work orders, including but not limited to solution details, dialogue records, monitoring snapshots, and other relevant information. Maintenance theory knowledge refers to a collection of systematic principles, methods, concepts, best practices, and frameworks supporting IT maintenance work. It transcends specific, fragmented operational skills, providing in-depth logical explanations, guiding principles, and decision-making basis for maintenance work. For example, maintenance theory knowledge may include basic principles, such as computer operating system principles and network protocols, and may also include framework layers, such as IT service management frameworks. The training corpus is a high-quality dataset specifically used for training or fine-tuning large models, obtained from the above raw data after cleaning, transformation, alignment, and formatting. Retrieval knowledge is knowledge fragments stored in the maintenance corpus knowledge base that can be quickly and accurately found by retrieval algorithms. This knowledge serves as the factual basis and reference material for the network's large-scale model to generate answers.

[0081] As an example, the training corpus can contain relevant knowledge such as installation requirements and activation steps, fault information and troubleshooting steps. Simultaneously, it can acquire work order maintenance corpora and build an maintenance corpus knowledge base based on them, serving as the logical basis and knowledge reserve for the network's large-scale model to generate solutions for complex or unpredictable situations.

[0082] By fine-tuning the large-scale model in the operations and maintenance (O&M) domain, it becomes an O&M expert, generating professional and accurate work order types, tasks, and solutions, thus improving the accuracy of O&M work order processing. The O&M corpus knowledge base provides the model with authentic and reliable factual evidence. In other words, during the process of the large-scale network model generating output content based on input content, RAG dynamically retrieves highly relevant information from the O&M corpus knowledge base to assist the large-scale model in answering questions. Accurate matching of knowledge content ensures controllable generation of content, significantly improving the accuracy of generated content and effectively solving the illusion problem.

[0083] In some optional embodiments, based on the work order type and task, the work order management agent generates an operation and maintenance guidance scheme for the operation and maintenance work order based on the operation and maintenance corpus knowledge base, including: First, the work order management intelligent agent uses a large network model and an operations and maintenance corpus knowledge base to analyze work order types and tasks, obtaining the analysis results. Then, the analysis results are integrated to obtain the operations and maintenance guidance plan for the work orders.

[0084] Specifically, based on the network big data model and RAG, analysis is performed on work order types and work order tasks, namely intent understanding and knowledge retrieval, to obtain analysis results. Then, the analysis results are summarized to obtain operation and maintenance guidance solutions.

[0085] like Figure 5 The diagram shows a schematic of generating an operation and maintenance guidance plan. The network big data model analyzes work order tasks and work order types, and combines them with knowledge retrieval to obtain the operation and maintenance guidance plan. Thus, when the operation and maintenance work order is automatically dispatched, the operation and maintenance guidance plan is simultaneously dispatched to the target operation and maintenance personnel along with the operation and maintenance work order.

[0086] By decoupling the solution generation process into two sequential stages, analysis and integration, the error rate of the generated operation and maintenance guidance solution is significantly reduced, the content is more actionable, and the illusion of a general large model is effectively avoided.

[0087] In step S230, the target maintenance personnel are determined by the work order management intelligent agent based on the work order type, work order adaptation model and work order intelligent scheduling strategy. The work order adaptation model is a model that represents the degree of adaptation between maintenance personnel and maintenance work orders.

[0088] In the exemplary embodiments of this disclosure, the intelligent work order scheduling strategy refers to the strategy used when scheduling work orders, such as selecting maintenance personnel within a specific range or selecting maintenance personnel whose business level matches the work order level. It can be understood that the intelligent work order scheduling strategy is a decision-making rule and execution plan for the automated and intelligent assignment and prioritization of maintenance work orders. Based on the intelligent work order scheduling strategy, the correct work order can be dynamically assigned to the most suitable maintenance personnel at the correct time to achieve optimization of overall efficiency, quality, and resource utilization. The work order adaptation model quantifies the suitability of a maintenance personnel to handle a specific work order. Based on the work order adaptation model, the work order assignment decision is transformed from a fuzzy process based on experience or polling into a precise calculation problem based on data and algorithms.

[0089] In some alternative embodiments, such as Figure 6 As shown, the process of determining the target maintenance personnel through the work order management intelligent agent based on the work order type, work order adaptation model, and work order intelligent scheduling strategy may include: Step S610: Based on the work order intelligent scheduling strategy, determine the candidate maintenance personnel that match the work order type according to the skill level of the maintenance personnel.

[0090] Based on the intelligent work order scheduling strategy, and considering that the skill level classification of maintenance personnel is directly related to the difficulty of business product delivery and maintenance, the following classifications are made: For example, maintenance personnel with the ability to handle basic services such as broadband, fixed-line telephone, and high-definition television can be classified as junior maintenance engineers; those with the ability to handle upgraded and basic services such as smart home can be classified as intermediate maintenance engineers; and those with the ability to handle new and upgraded services such as cloud services and video networking can be classified as senior maintenance engineers. Of course, the method of classifying skill levels is not limited to this.

[0091] After determining the work order type, priority can be given to selecting maintenance personnel within the corresponding skill level as candidate maintenance personnel based on the work order type.

[0092] Step S620: Based on the geographical information of the maintenance work order, determine the reference maintenance personnel within the geographical information range from the candidate maintenance personnel.

[0093] After identifying candidate maintenance personnel with matching skill levels, reference maintenance personnel within the specified geographical area can be selected from the candidate personnel based on the geographical information in the maintenance work order. These reference personnel can be within a pre-defined range, such as within 5 kilometers or 10 kilometers, without any special restrictions.

[0094] Step S630: Based on the work order adaptation model, calculate the work order adaptation degree of the reference maintenance personnel.

[0095] After selecting reference maintenance personnel, the work order fit degree of the reference maintenance personnel can be calculated based on the work order adaptation model to determine the most suitable maintenance personnel from the reference maintenance personnel.

[0096] Specifically, based on the work order adaptation model, calculating the work order adaptation degree of the reference maintenance personnel can include: First, obtain the multi-dimensional characteristics of the reference maintenance personnel, including service evaluation scores, travel time to complete maintenance work orders, and maintenance time. Then, input the multi-dimensional characteristics into the work order matching model to output the work order matching degree of the reference maintenance personnel.

[0097] Specifically, a work order matching model is constructed based on service evaluations of maintenance personnel (such as satisfaction scores), the number of times the work order type has been served, and time costs. This model comprehensively considers multiple characteristics, and the maintenance personnel with the highest fit for the work order are selected from among several reference maintenance personnel. For example, priority is given to maintenance personnel with high service satisfaction scores, multiple service experiences with the same work order customer, and the shortest travel time.

[0098] As an example, the work order adaptation model can be represented by Formula 1: Formula 1 Where SS is the Satisfaction Score (SS), C is the number of services (Count, C), T is the time cost (Time, T), and T is the sum of the time required to complete the previous work order and the travel time required for this work order. " indicates product.

[0099] Based on Formula 1, the product of satisfaction score and service frequency can be obtained. The ratio of the sum of the time required to complete the previous work order and the travel time required for the current work order to this score is then used to determine the work order fit of the reference maintenance personnel. A smaller work order fit value indicates a higher fit between the maintenance personnel and the corresponding work order. Furthermore, the target maintenance personnel can be determined from the reference maintenance personnel based on their work order fit. Additionally, the work order fit of the target maintenance personnel can also be recorded simultaneously. .

[0100] Step S640: Based on the work order suitability, determine the target maintenance personnel from the reference maintenance personnel.

[0101] After determining the work order suitability of the reference maintenance personnel, the target maintenance personnel can be identified accordingly. Specifically, identifying the target maintenance personnel from the reference maintenance personnel based on the work order suitability may include: Based on the work order suitability, candidate maintenance personnel are selected from the reference maintenance personnel. If the work order suitability of the candidate maintenance personnel meets the preset conditions with the historical average suitability, then the candidate maintenance personnel are determined as the target maintenance personnel. The historical average suitability is determined based on the work order suitability of historical maintenance personnel corresponding to the work order type within a preset statistical period. The preset conditions are used to evaluate whether the candidate maintenance personnel are allowed to execute maintenance work orders.

[0102] The historical average adaptability can be obtained by taking the average of the adaptability of the historical maintenance personnel who handled this type of maintenance work order in the previous time period (preset time period). This historical average adaptability can be used as the basic capability requirement for executing this type of maintenance work order.

[0103] Based on this, the selected maintenance personnel can be reviewed a second time based on the historical average fit, thereby ensuring that the dispatched maintenance personnel are capable of handling maintenance work orders.

[0104] Correspondingly, if the work order fit of the candidate maintenance personnel does not meet the preset conditions compared with the historical average fit, the target maintenance personnel will be selected from at least one higher skill level than the existing maintenance personnel.

[0105] This can be understood as follows: Candidate maintenance personnel matching the work order type can be obtained from the skill level one level higher than the maintenance personnel's skill level. Then, based on the geographical information of the maintenance work order, reference maintenance personnel within the geographical range are identified from the candidate maintenance personnel. Based on the work order adaptation model, the work order fit degree of the reference maintenance personnel is calculated, and the target maintenance personnel are determined from among the reference maintenance personnel according to the work order fit degree. In other words, a similar method is used to determine the target maintenance personnel from the skill level one level higher than the maintenance personnel's skill level. This process continues until a final target maintenance personnel can be determined from the maintenance personnel at the skill levels two levels higher than the maintenance personnel's skill level.

[0106] As an example, if there is an operation and maintenance work order 'a', the average adaptability of handling this type of operation and maintenance work order in the previous time period (preset time period) can be used as a reference. The suitability of work orders for selected maintenance personnel A second review will be conducted. If the work order of the maintenance worker (F) is suitable... Below or equal to average fit If the candidate maintenance personnel is selected, the maintenance work order will be assigned to that personnel. Conversely, if the maintenance personnel's... Above average fit This indicates that the candidate maintenance personnel does not yet meet the conditions for handling work order a, meaning there are currently no suitable maintenance personnel within this skill level. Therefore, within the skill level range of maintenance personnel to be upgraded for work order a, maintenance personnel with a higher work order suitability will be selected from maintenance personnel at a higher skill level to determine the final target maintenance personnel.

[0107] The exemplary embodiments of this disclosure, under the premise that the skill level of the maintenance personnel matches the difficulty of implementing the business products involved in the maintenance work order, and further considering factors such as the maintenance personnel's customer satisfaction, service frequency, and travel costs to determine the work order suitability, select the maintenance engineers who can provide customers with more efficient and high-quality services. The business work order dispatch method based on personnel skills can ensure the full utilization of human resources, prioritize the maintenance personnel whose skill level best matches the difficulty of business implementation, and ensure that the maintenance personnel fully understand the relevant content of the business products they are handling, so that they can complete the operation more quickly and in a more targeted manner.

[0108] In some optional embodiments, the historical average fit of each work order type can be updated at preset time intervals using the work order fit of the target maintenance personnel of the maintenance work orders under the work order type.

[0109] The preset time period is a fixed time length set in advance to trigger update operations, which determines the frequency of system learning and adaptation. If the period is too short, the average value will fluctuate greatly due to random factors; if the period is too long, the system cannot reflect the overall skill improvement of maintenance personnel or changes in the environment in a timely manner. For example, it can be set to Monday morning, the 1st of each month, etc., and can be flexibly set according to the actual scenario without any restrictions.

[0110] Based on this, the effectiveness of the secondary review of selected maintenance personnel can be guaranteed, the scheduling of maintenance work orders can be completed more quickly and reasonably, and the accuracy of intelligent scheduling of maintenance work orders can be improved.

[0111] In step S240, the operation and maintenance work order and operation and maintenance guidance plan are automatically dispatched to the target operation and maintenance personnel, and the operation and maintenance work order is automatically monitored and managed by the work order management intelligent agent to complete the processing of the operation and maintenance work order.

[0112] In an exemplary embodiment of this disclosure, after identifying the target maintenance personnel, maintenance work orders and maintenance guidance plans can be simultaneously dispatched to the target maintenance personnel. Optionally, maintenance work orders and maintenance guidance plans can be automatically dispatched electronically to the target maintenance personnel, or they can be notified via SMS or AI outbound calls.

[0113] In some optional embodiments, automatically dispatching maintenance work orders and maintenance guidance plans to target maintenance personnel, and automatically monitoring and managing maintenance work orders through a work order management intelligence agent may include: First, maintenance work orders and maintenance guidance plans are automatically dispatched to the target maintenance personnel. The system then obtains the execution information of these personnel at key control points and manages the maintenance status of the work orders based on this information. These key control points include at least the service phase, the delivery phase, and the follow-up phase.

[0114] Specifically, the entire work order processing flow can be monitored down to the minute level during the service phase. For example, maintenance personnel can be required to complete designated actions such as scheduling an appointment with the customer within a specified time before on-site visits. For abnormal situations, such as maintenance personnel failing to contact the customer promptly after accepting the order, or the customer urging maintenance personnel to come to the site, alarms are automatically triggered, and the handling personnel's level is automatically escalated (e.g., reporting to a higher-level manager for reminder or reassignment). Alternatively, reminders can be sent again via SMS or AI-powered outbound calls. If the issue remains unresolved for an extended period, dedicated management personnel will intervene.

[0115] During the delivery phase, after the maintenance personnel confirm their arrival, the location of the maintenance personnel is detected to ensure it matches the customer's address, and the arrival time is automatically recorded. After the maintenance personnel complete the service activation or repair service, the system automatically and remotely quantifies quality indicators according to the delivery standards, such as speed and light attenuation. In case of abnormal situations, such as service verification failure or excessive time spent by the maintenance personnel at the customer's home, an alarm is automatically triggered, and dedicated management personnel intervene in a timely manner to confirm the on-site situation with the maintenance personnel.

[0116] During the follow-up process, after the maintenance personnel finish their on-site service, an AI-powered outbound call is automatically triggered to conduct a customer satisfaction survey on the maintenance personnel's service. If the survey results are unsatisfactory or incomplete, an alarm is automatically triggered, and dedicated management personnel will intervene to handle the situation.

[0117] Of course, the exemplary embodiments of this disclosure can set other key control links and obtain corresponding execution information according to the operation and maintenance scenario, thereby performing automatic monitoring and control. The exemplary embodiments of this disclosure include, but are not limited to, the key control links described above.

[0118] The exemplary embodiments disclosed herein utilize the intelligent orchestration capabilities of large network models. By orchestrating and executing related models and API capabilities, work orders are automatically controlled at key stages such as work order flow, processing, and closure according to the service process. The completion time and quality of work orders at important stages are monitored, related operations are assisted, and timely alarms are issued in case of abnormalities. This achieves full-process automatic monitoring and control of maintenance work orders, ensuring that maintenance work orders are completed accurately, timely, and efficiently.

[0119] Figure 7 This diagram illustrates a complete flowchart for processing maintenance work orders. The following section combines... Figure 7 The method for processing operation and maintenance work orders in an operator scenario is described using an example.

[0120] First, the work order management intelligent agent performs intent recognition on the requirement description information in the operation and maintenance work order, and determines the work order type and work order task based on the intent recognition result.

[0121] Among them, after generating an operation and maintenance work order based on customer requests, the system can obtain the detailed description of user requirements recorded in the operation and maintenance work order and input it into the work order management intelligent agent. The work order management intelligent agent can understand the intent of the work order content, identify the work order type and work order task (requirement classification).

[0122] Secondly, based on the work order type and work order task, the work order management agent generates an operation and maintenance guidance plan for the operation and maintenance work order based on the operation and maintenance corpus knowledge base.

[0123] Among them, by understanding the content of the work order, the work order management intelligent agent can generate operation and maintenance guidance solutions that are embedded in the work order information and automatically dispatched along with the work order.

[0124] Next, the work order management intelligent agent determines the target maintenance personnel based on the work order type, work order adaptation model, and intelligent work order scheduling strategy. The work order adaptation model represents the fit between maintenance personnel and maintenance work orders. Specifically, based on the intelligent work order scheduling strategy and the skill level of maintenance personnel, candidate maintenance personnel matching the work order type are first determined. Then, based on the geographical information of the maintenance work order, reference maintenance personnel within the geographical range are determined from the candidate maintenance personnel. The work order adaptation degree of the reference maintenance personnel is calculated based on the work order adaptation model, and then the candidate maintenance personnel are determined from the reference maintenance personnel based on the work order adaptation degree. If the work order adaptation degree of the candidate maintenance personnel meets the preset conditions with the historical average adaptation degree, the candidate maintenance personnel are determined as the target maintenance personnel. If the work order adaptation degree of the candidate maintenance personnel does not meet the preset conditions with the historical average adaptation degree, the target maintenance personnel are determined from at least one skill level higher than the previous maintenance personnel.

[0125] Then, the operation and maintenance work orders and operation and maintenance guidance plans are automatically dispatched to the target operation and maintenance personnel, and the operation and maintenance work orders are automatically monitored and managed through the work order management intelligent agent.

[0126] The system features fully automated monitoring and control throughout the entire lifecycle of maintenance work orders. Before on-site service, maintenance personnel are required to complete designated actions such as scheduling appointments with customers within a specified time. In case of anomalies, the system prioritizes escalating the handling personnel's level and automatically reminds them again via SMS or AI-powered outbound calls. During the on-site delivery phase, the system confirms the maintenance personnel's location and automatically performs remote quality checks according to delivery standards after completing the necessary procedures. After the maintenance personnel leave, an AI-powered outbound call is automatically triggered to assess customer satisfaction with the service provided. Based on the detection and execution results throughout the entire process, if no anomalies are found, the work order management AI agent manages all key aspects of work order flow, handling, and closure. If an anomaly is detected at a control point, an alarm is automatically triggered, prompting timely manual intervention by dedicated management personnel.

[0127] It should be noted that the details of each step have been described in the exemplary embodiments above, and will not be repeated here.

[0128] The method for processing maintenance work orders in the exemplary embodiments of this disclosure first performs intent recognition on the requirement description information in the maintenance work order based on the work order management intelligence agent, and determines the work order type and work order task based on the intent recognition result; then, based on the work order type and work order task, the maintenance guidance plan for the maintenance work order is generated by the work order management intelligence agent based on the maintenance corpus knowledge base; next, the target maintenance personnel are determined by the work order management intelligence agent based on the work order type, work order adaptation model, and work order intelligent scheduling strategy, where the work order adaptation model is a model representing the fit between the maintenance personnel and the maintenance work order; finally, the maintenance work order and maintenance guidance plan are dispatched to the target maintenance personnel, and the maintenance work order is monitored and managed by the work order management intelligence agent to complete the maintenance work order. On the one hand, starting from the generation of maintenance work orders, the intent of the requirement description information in the maintenance work order is identified and understood to clarify the work order type and work order tasks. Maintenance guidance plans are generated through content generation capabilities, and target maintenance personnel are determined based on the work order adaptation model. The maintenance work order and maintenance guidance plan are then dispatched to the target maintenance personnel. Intelligent orchestration capabilities enable automated management and control of the entire lifecycle of maintenance work orders, ensuring the completion time and quality of work order flow, processing, and closure without manual intervention. This effectively improves work order management efficiency and appropriately reduces personnel input. On the other hand, by using a work order management intelligent agent to determine target maintenance personnel based on work order type, work order adaptation model (representing the compatibility between maintenance personnel and maintenance work orders), and intelligent work order scheduling strategies, the accurate and full utilization of human resources can be guaranteed. This allows for more targeted and rapid completion of maintenance work orders, improving processing efficiency.

[0129] In an exemplary embodiment of this disclosure, an intelligent management and control device for maintenance work orders is also provided, such as... Figure 8 As shown, the intelligent management and control device 800 for this maintenance work order includes: The intent recognition module 810 is used to recognize the intent of the requirement description information in the operation and maintenance work order based on the work order management intelligent agent, and determine the work order type and work order task based on the intent recognition result; the solution generation module 820 is used to generate the operation and maintenance guidance solution for the operation and maintenance work order based on the operation and maintenance corpus knowledge base through the work order management intelligent agent according to the work order type and work order task; the determination module 830 is used to determine the target operation and maintenance personnel through the work order management intelligent agent based on the work order type, work order adaptation model and work order intelligent scheduling strategy, where the work order adaptation model is a model representing the fit between the operation and maintenance personnel and the operation and maintenance work order; the work order intelligent management module 840 is used to automatically dispatch the operation and maintenance work order and the operation and maintenance guidance solution to the target operation and maintenance personnel, and automatically monitor and manage the operation and maintenance work order through the work order management intelligent agent to complete the processing of the operation and maintenance work order.

[0130] Since the details of each functional module of the intelligent management and control device for maintenance work orders in the exemplary embodiments of this disclosure have been described in the exemplary embodiments of the intelligent management and control method for maintenance work orders described above, they will not be repeated here.

[0131] It should be noted that although several modules or units of the intelligent management and control device for operation and maintenance work orders have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0132] Exemplary embodiments of this disclosure also provide a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the aforementioned intelligent management method for maintenance work orders.

[0133] In one implementation, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing a computer program, such as read-only memory, NAND flash memory, etc.

[0134] In one implementation, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.

[0135] Computer program code can be written in one or more programming languages. The program code can execute entirely on the user's computing device, or partially on the user's computing device, or as a standalone software package, or partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or it can be connected to an external computing device (e.g., through an internet connection provided by a mobile network operator).

[0136] Computer programs can be carried or transmitted via signals such as electricity, magnetism, light, electromagnetic fields, and infrared radiation. Electronic devices can convert signals carrying computer programs into digital signals, thereby running the computer programs. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, the processor of the electronic device to execute) the method steps of various exemplary embodiments of this disclosure, such as the steps of the above-described maintenance work order processing method.

[0137] Furthermore, in exemplary embodiments of this disclosure, an electronic device capable of implementing the above-described methods is also provided. Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be specifically implemented as: entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as "circuit," "module," or "system."

[0138] The following reference Figure 9 To describe an electronic device 900 according to such an embodiment of the present disclosure. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0139] like Figure 9 As shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processing unit 910, at least one storage unit 920, a bus 930 connecting different system components (including storage unit 920 and processing unit 910), and a display unit 940.

[0140] The storage unit stores program code that can be executed by the processing unit 910, causing the processing unit 910 to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this disclosure.

[0141] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0142] Storage unit 920 may also include a program / utility 924 having a set (at least one) program module 925, such program module 925 including but not limited to: 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.

[0143] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0144] Electronic device 900 can also communicate with one or more external devices 1000 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, electronic device 900 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 960. As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0145] 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 according to 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, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0146] 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.

[0147] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention 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 embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method for intelligent management and control of maintenance work orders, characterized in that, include: Based on the work order management intelligent agent, the intent of the requirement description information in the operation and maintenance work order is identified, and the work order type and work order task of the operation and maintenance work order are determined according to the intent identification result. Based on the work order type and work order task, the work order management intelligent agent generates an operation and maintenance guidance plan for the operation and maintenance work order based on the operation and maintenance corpus knowledge base; The work order management intelligent agent determines the target maintenance personnel based on the work order type, work order adaptation model, and work order intelligent scheduling strategy. The work order adaptation model is a model that characterizes the compatibility between maintenance personnel and maintenance work orders. The operation and maintenance work order and the operation and maintenance guidance plan are automatically dispatched to the target operation and maintenance personnel, and the operation and maintenance work order is automatically monitored and managed by the work order management intelligence to complete the processing of the operation and maintenance work order.

2. The method according to claim 1, characterized in that, The work order management intelligent agent performs intent recognition on the requirement description information in the maintenance work order, and determines the work order type and work order task based on the intent recognition result, including: The work order management intelligent agent uses a large network model to perform intent recognition on the demand description information to obtain the work order type. Based on the work order type, the network big data model is used to classify the requirement description information into tasks to obtain the work order tasks.

3. The method according to claim 1, characterized in that, The method further includes: The training corpus is determined based on historical operation and maintenance work orders, corresponding historical operation and maintenance information, and operation and maintenance theoretical knowledge. Based on the training corpus, the large language model is trained and fine-tuned to obtain the large network model. The work order maintenance corpus is stored in the maintenance corpus knowledge base, which is used to provide retrieval knowledge to the network big model.

4. The method according to claim 3, characterized in that, Based on the work order type and task, the work order management agent generates an operation and maintenance guidance plan for the operation and maintenance work order using an operation and maintenance corpus knowledge base, including: The work order management intelligent agent uses the network big model and the operation and maintenance corpus knowledge base to analyze the work order type and the work order task, and obtains the analysis results; The analysis results are integrated to obtain the operation and maintenance guidance plan for the operation and maintenance work order.

5. The method according to claim 1, characterized in that, The process of determining the target maintenance personnel through the work order management intelligence agent based on the work order type, work order adaptation model, and work order intelligent scheduling strategy includes: Based on the work order intelligent scheduling strategy, candidate maintenance personnel matching the work order type are determined according to the skill level of the maintenance personnel. Based on the geographical information of the maintenance work order, select reference maintenance personnel within the geographical information range from the candidate maintenance personnel; Based on the work order adaptation model, the work order adaptation degree of the reference maintenance personnel is calculated; Based on the work order suitability, the target maintenance personnel are determined from the reference maintenance personnel.

6. The method according to claim 5, characterized in that, The step of calculating the work order compatibility of the reference maintenance personnel based on the work order adaptation model includes: Obtain the multi-dimensional characteristics of the reference maintenance personnel, including service evaluation value, travel time to complete the maintenance work order, and maintenance time; The multi-dimensional features are input into the work order adaptation model to output the work order adaptation degree of the reference maintenance personnel.

7. The method according to claim 5, characterized in that, The step of determining the target maintenance personnel from the reference maintenance personnel based on the work order suitability includes: Based on the work order suitability, candidate maintenance personnel are determined from the reference maintenance personnel. If the work order fit of the candidate maintenance personnel meets the preset conditions with the historical average fit, then the candidate maintenance personnel is determined as the target maintenance personnel. The historical average fit is determined based on the work order fit of the historical maintenance personnel corresponding to the work order type within the preset statistical period. The preset conditions are used to evaluate whether the candidate maintenance personnel are allowed to execute the maintenance work order. If the work order fit of the candidate maintenance personnel does not meet the preset condition compared with the historical average fit, then the target maintenance personnel will be determined from at least one higher skill level than the maintenance personnel's skill level.

8. The method according to claim 7, characterized in that, The method further includes: For each type of work order, the historical average fit of the work order type is updated at preset time intervals using the work order fit of the target maintenance personnel of the work order under that work order type.

9. The method according to claim 1, characterized in that, The step of automatically dispatching the maintenance work order and the maintenance guidance plan to the target maintenance personnel, and automatically monitoring and managing the maintenance work order through the work order management intelligence agent, includes: The maintenance work order and the maintenance guidance plan are automatically dispatched to the target maintenance personnel. Obtain the execution information of the target maintenance personnel at key control nodes, and control the maintenance status of the maintenance work order based on the execution information; The key control nodes include at least the service stage, the delivery stage, and the follow-up stage.

10. An intelligent management and control device for maintenance work orders, characterized in that, include: The intent recognition module is used to recognize the intent of the requirement description information in the operation and maintenance work order based on the work order management intelligent agent, and to determine the work order type and work order task of the operation and maintenance work order based on the intent recognition result. The solution generation module is used to generate an operation and maintenance guidance solution for the operation and maintenance work order based on the operation and maintenance corpus knowledge base through the work order management intelligent agent, according to the work order type and work order task. The determination module is used to determine the target maintenance personnel through the work order management intelligent agent based on the work order type, work order adaptation model and work order intelligent scheduling strategy. The work order adaptation model is a model that characterizes the fit between maintenance personnel and maintenance work orders. The work order intelligent management module is used to automatically dispatch the operation and maintenance work order and the operation and maintenance guidance plan to the target operation and maintenance personnel, and to automatically monitor and manage the operation and maintenance work order through the work order management intelligence to complete the processing of the operation and maintenance work order.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 9.

12. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 9 by executing the executable instructions.

Images