Work order processing method and system, computer equipment and storage medium
By using a pre-trained work order analysis model and a knowledge base to automatically match processing solutions, the system solves the problems of response delays and inaccurate processing caused by manual judgment in existing work order processing systems. This achieves efficient and standardized work order processing, improving system stability and user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING BAIJU YIXING TECH CO LTD
- Filing Date
- 2025-12-05
- Publication Date
- 2026-04-17
AI Technical Summary
The existing work order processing system relies on manual judgment, which leads to delayed response, strong subjectivity in manual judgment, and difficulty in quickly identifying potential online risks. Especially in scenarios with high business complexity and large work order volume, problems recur, processing priorities are unclear, and the stability of the system and user experience are affected.
The pre-trained work order analysis model automatically analyzes work order data, extracts key attribute information, matches and recommends processing solutions from the knowledge base based on the attribute information, and adjusts the work order dispatch process based on user feedback. Combined with multimodal information extraction and dynamic priority adjustment, it achieves automated processing.
It significantly reduces the initial response and processing time of work orders, avoids problems such as inaccurate or inefficient manual classification, significantly improves work order processing efficiency, shortens the resolution path of difficult work orders, and improves system stability and user experience.
Smart Images
Figure CN121883016A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence technology, and in particular to a work order processing method, system, computer device, and storage medium. Background Technology
[0002] In complex business systems such as service platforms, the work order system is an important tool for after-sales support and problem handling.
[0003] Currently, ticket processing relies heavily on manual judgment and workflow by customer service personnel. This approach suffers from issues such as delayed response times, strong subjectivity in human judgment, and difficulty in quickly identifying potential online risks from a massive volume of tickets. Especially in scenarios with high business complexity and a large volume of tickets, such as campaign configuration and multi-party reconciliation in the marketing domain, this method struggles to identify common online issues in a timely and accurate manner. This leads to recurring problems, unclear processing priorities, and negatively impacts overall system stability and user experience. Summary of the Invention
[0004] Therefore, it is necessary to provide a work order processing method, system, computer equipment, and storage medium to address at least one of the aforementioned technical problems.
[0005] In a first aspect, embodiments of this application provide a work order processing method, the method comprising: Perform work order analysis on the work order data to be processed to determine the attribute information of the work order data; the attribute information should at least include the target business domain to which the work order data belongs and the problem type.
[0006] Based on attribute information, recommended processing solutions corresponding to work order data are obtained from a pre-set work order processing knowledge base.
[0007] In response to an invalid request from a user regarding a recommended processing solution, the work order data is sent to the target processing object based on the attribute information to obtain an effective processing solution provided by the target processing object.
[0008] In some embodiments, the work order processing method may further include: After obtaining an effective processing solution from the target processing object, the attribute information corresponding to the work order data is updated, and based on the updated work order data and its corresponding effective processing solution, the work order analysis model is further trained, and the work order processing knowledge base is updated.
[0009] In some embodiments, the work order processing method may further include: Multimodal information is extracted from the text and images contained in the work order data, and the target business domain and problem type to which the work order data belongs are determined based on the extracted multimodal information.
[0010] In some embodiments, the attribute information of the work order data may also include the target priority corresponding to the work order data; accordingly, the work order processing method may further include: Determine the initial priority of the work order data based on the target business domain and issue type to which the work order data belongs; Within a preset time window, if there are N analyzed work order data belonging to the target business domain, the initial priority is increased to obtain the target priority corresponding to the work order data; where N is a positive integer.
[0011] In some embodiments, the work order processing method may further include: Based on the target priority, the work order data is stored in a preset target priority processing queue. When the work order data becomes the first element of the target priority processing queue, keyword matching is performed based on attribute information, and a recommended processing solution corresponding to the problem type is obtained from the work order processing knowledge base.
[0012] In some embodiments, the work order processing method may further include: Before sending work order data to the target processing object, if the invalid request contains preset public opinion keywords, the target priority will be updated to the highest priority.
[0013] In some embodiments, the work order processing method may further include: Based on the target business domain and problem type, determine the target processing object corresponding to the work order data; Send the work order data to the target processing object and issue warnings to the target processing object according to the target priority.
[0014] In a second aspect, embodiments of this application provide a work order processing system, the system comprising: The analysis module is used to analyze the work order data to be processed and determine the attribute information of the work order data; the attribute information includes at least the target business domain to which the work order data belongs and the problem type; The filtering module is used to obtain recommended processing solutions for work order data from a preset work order processing knowledge base based on attribute information. The response module is used to respond to invalid requests from users regarding the recommended processing solutions. Based on the attribute information, it sends the work order data to the target processing object to obtain an effective processing solution provided by the target processing object.
[0015] In a third aspect, embodiments of this application provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the work order processing method provided in any embodiment of the first aspect of this application.
[0016] In a fourth aspect, embodiments of this application provide a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the work order processing method provided in any embodiment of the first aspect of this application.
[0017] The aforementioned work order processing methods, systems, computer equipment, and storage media automatically analyze work orders and extract key attribute information through pre-trained models, replacing the traditional process that relies entirely on manual understanding and classification of work orders. This significantly reduces the initial response and processing time of work orders and avoids inaccurate classification or inefficiency caused by differences in the business skills of customer service personnel. By automatically matching recommended processing solutions from a knowledge base based on attribute information, a large number of repetitive and common problems can be quickly and standardizedly resolved at the first moment of user interaction, significantly improving the efficiency of work order processing. By assigning work orders based on attribute information for invalid user requests, the communication costs and time delays caused by manual secondary sorting, cross-departmental inquiries, or assignment errors are completely avoided, greatly shortening the resolution path for difficult work orders. Attached Figure Description
[0018] Figure 1 This is a diagram illustrating the application environment of the work order processing method in some embodiments; Figure 2 This is a flowchart illustrating the work order processing method in some embodiments; Figure 3 This is a flowchart illustrating the target priority steps in some embodiments; Figure 4 Here are some block diagrams of the work order processing system in some embodiments; Figure 5 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation
[0019] To make the technical solutions and advantages of this application clearer, the embodiments and related technical content of this application will be further described in detail below with reference to the accompanying drawings and text description. It should be understood that the embodiments described below are only used to explain the technical solutions of the embodiments of this application and are not intended to limit more possible implementations of this application.
[0020] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0021] It should be noted that relational terms such as "first" and "second" appearing in this document are used only to distinguish things, states, or actions, and do not necessarily indicate or imply relative importance or order. The terms "including," "comprising," or any other variations thereof are used to indicate non-exclusive inclusion, and the included objects may not be limited to those listed in this document. The terms "multiple" or other variations are used to indicate that the number of objects is two or more.
[0022] The steps of the work order processing method provided in this application can be executed by a server or a terminal without any special restrictions.
[0023] For ease of understanding, Figure 1 An application environment is illustrated, in which a pre-trained work order analysis model is configured in server 101 to execute the steps of the work order processing method. During execution, server 101 can communicate with terminal 102 via a network to obtain the work order data to be processed sent by terminal 102. Server 101 can be implemented using a standalone server or a server cluster consisting of multiple servers, and terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.
[0024] Server 101 may be implemented using at least one of the following hardware forms: programmable logic array (PLA), field-programmable gate array (FPGA), digital signal processor (DSP), application-specific integrated circuit (ASIC), general-purpose processor, or other programmable logic device.
[0025] Of course, the configuration method for travel service software provided in this disclosure can also be applied to more scenarios not shown.
[0026] In a first aspect, embodiments of this application provide a work order processing method. This method can be applied to, for example... Figure 1 The application environment shown is for use in [the following context]. Figure 1 Taking server 101 as an example, in some embodiments, such as Figure 2 As shown, the work order processing method includes steps S201, S202, and S203 that can be executed by server 101. Each step is described in detail below.
[0027] Step S201: Perform work order analysis on the work order data to be processed to determine the attribute information of the work order data.
[0028] The attribute information includes at least the target business domain to which the work order data belongs and the problem type.
[0029] Pre-trained models are an artificial intelligence technique that uses large-scale datasets to pre-train models, enabling them to learn general features and knowledge. In this application, the pre-trained work order analysis model specifically refers to an intelligent model that has been pre-trained on large-scale text and image data and further fine-tuned using manual annotations (such as business domains and problem types) corresponding to historical work order datasets. Its core capability is to understand work order data (such as user-submitted text descriptions, screenshots, etc.) and output structured attribute information.
[0030] For example, historical work order data can be analyzed using large AI models such as Tongyi Qianwen, Wenxin Yiyan, and GPT, enabling them to learn the characteristics of work order data from different business domains and problem types, thereby gaining the ability to analyze the latest work order data.
[0031] Attribute information is metadata that is generated by the work order analysis model from the work order data to be processed. It is used to characterize the core characteristics of the work order and serves as the basis for decision-making that drives the work order processing flow.
[0032] In business systems such as service platforms, classifying work orders is fundamental to efficient processing and dispatch. Business domains are used to categorize the functional modules or departments to which an issue belongs, such as marketing or control domains; issue types are used to distinguish the nature of the issue, such as functional failures, operational inquiries, or optimization suggestions.
[0033] In some optional embodiments, in addition to business domain and problem type, the attribute information may also include tags such as problem keywords and problem severity, and this application does not impose any restrictions on this.
[0034] For example, in a customer support scenario of a travel SaaS (Software as a Service) platform, user A encounters a problem where the "commission reduction card cannot be used" and submits a work order containing a problem description and screenshots of the error. The work order analysis model receives the corresponding work order data, analyzes the text and screenshots, and outputs that the target business domain of the work order data is "marketing domain" and the problem type is "functional failure".
[0035] Step S202: Based on attribute information, obtain the recommended processing solution corresponding to the work order data from the preset work order processing knowledge base.
[0036] In the field of information technology, a knowledge base refers to a structured collection of information used for storing, organizing, and sharing knowledge. In this application, the work order processing knowledge base is not a static document library, but a structured solution database deeply associated with the output of the work order analysis model. The work order processing knowledge base contains processing solution texts for different work orders, and each processing solution text is mapped to attribute tags such as its applicable business domain, problem type, or keywords. This enables the server to perform fast and accurate retrieval and matching based on the attribute information analyzed by the work order analysis model.
[0037] Recommended solutions refer to one or more possible problem-solving steps or answers that the server automatically matches and returns from the work order processing knowledge base, based on the attribute information of the work order data determined by the work order analysis model and using it as search criteria.
[0038] For example, based on the attributes "marketing domain" and "functional failure," the server matches a solution for "commission reduction card cannot be used" from the ticket processing knowledge base: "Please check if the commission reduction card is valid and try refreshing the page." This solution can be recommended to the user.
[0039] Step S203: In response to the user's invalid request for the recommended processing solution, the work order data is sent to the target processing object according to the attribute information to obtain the valid processing solution provided by the target processing object.
[0040] An invalid request is a signal from a user that the recommended handling solution provided by the server is not applicable or unresolved, and it is the decision trigger point for the server to execute the work order dispatch logic.
[0041] The target processing object is an entity with corresponding processing capabilities and responsibilities, dynamically determined based on the attribute information of work order data through predefined routing rules or matching algorithms. This entity can be a human team (such as the marketing domain technical group), a specific role (such as a system administrator), or a subsequent automated processing flow.
[0042] Specifically, if the problem persists after trying the recommended solutions, an invalid request is returned, for example, by clicking the "Still Unresolved" option. The server then sends the work order data to the target processing object based on the determined attribute information, and the target processing object provides an effective solution, thereby realizing the intelligent switching from automated service to human intervention.
[0043] For example, the server sends the ticket data and its contextual information (original problem description, attribute information, historical communication records, etc.) to the collaboration platform of the marketing domain technical group for processing. The marketing domain technical group is the target processing object for this ticket data. The collaboration platform can be a work group or an internal ticket system; this application does not limit this.
[0044] By automatically analyzing work orders and extracting key attribute information through pre-trained models, the traditional process of relying entirely on manual understanding and classification of work orders has been replaced. This significantly reduces the initial response and processing time of work orders and avoids inaccurate classification or inefficiency caused by differences in the business skills of customer service personnel. By automatically matching and recommending processing solutions from the knowledge base based on attribute information, a large number of repetitive and common problems can be resolved quickly and in a standardized manner at the first moment of user interaction, significantly improving the efficiency of work order processing. By assigning work orders based on attribute information for invalid user requests, the communication costs and time delays caused by manual secondary sorting, cross-departmental inquiries, or assignment errors have been completely avoided, greatly shortening the resolution path of difficult work orders.
[0045] In some embodiments, the work order processing method may further include the following steps: after obtaining an effective processing solution provided by the target processing object, updating the attribute information corresponding to the work order data, and supplementing the training of the work order analysis model based on the updated work order data and its corresponding effective processing solution, and updating the work order processing knowledge base.
[0046] Specifically, once the target processing object provides a final effective processing solution, it means that the work order data to be processed has been effectively resolved. At this point, the target processing object may confirm or correct the attribute information initially identified by the work order analysis model.
[0047] For example, the work order analysis model initially categorized work order data as "marketing domain - functional failure", but after the target processing object processed the work order, it was confirmed that the work order data should be "marketing domain - data configuration error".
[0048] Based on the more precise business domain, problem type, and other attribute information confirmed after the target processing object has processed the work order, the attribute information initially generated by the work order analysis model for the work order data can be corrected or supplemented, thus forming a training sample with higher annotation quality.
[0049] The high-confidence work order samples (including the original work order data and the updated attribute information) that have been manually corrected are used as new training data and input into the work order analysis model. By adjusting the model parameters, the model learns a more accurate mapping relationship from work order content to attribute information, thereby achieving continuous self-optimization of model performance.
[0050] At the same time, the verified and effective processing solutions provided by the target processing object are associated with their corresponding manually confirmed or corrected attribute information, and are added as new processing solution entries to the work order processing knowledge base; or the content and attribute tags of existing entries in the work order processing knowledge base are modified, so that the content of the work order processing knowledge base iterates with business development and maintains the timeliness and accuracy of its problem-solving capabilities.
[0051] By supplementing the work order analysis model with the final effective processing solutions and results, continuous supervision and optimization of the model are achieved, enabling the model's recognition accuracy to continuously improve during use. This effectively overcomes the performance degradation problem caused by insufficient initial training data or business changes. Furthermore, by synchronously updating the verified effective solutions and corrected attribute information to the knowledge base, the knowledge base is automated and intelligently evolved, enabling it to solve more emerging problems.
[0052] In some embodiments, when the server performs step S201, it may also include the following steps: extracting multimodal information from the text and images contained in the work order data, and determining the target business domain and problem type to which the work order data belongs based on the extracted multimodal information.
[0053] Multimodal information extraction refers to the use of technologies such as optical character recognition, computer vision, and natural language processing to identify and extract structured features and semantic information that can be used for analysis from the text description or image attachments of work order data, and to fuse these features from different modalities to form a comprehensive digital representation of the work order data.
[0054] The work order analysis model takes the fused multimodal feature vector as input, performs calculations and inferences through its internal multi-layer neural network, and outputs the business domain and problem classification to which the work order data is most likely to belong.
[0055] By introducing multimodal information extraction technology, the complementary information contained in the text descriptions and image screenshots in the work order data is fully utilized, making the work order analysis model's understanding of the work order content more comprehensive, objective, and in-depth. Based on the fused multimodal information, the business domain and problem type are determined, significantly improving the accuracy and robustness of attribute information recognition.
[0056] In some embodiments, the attribute information of the work order data also includes the target priority corresponding to the work order data. For example... Figure 3 As shown, the work order processing method may also include steps S301 and S302. The following is a detailed explanation of each step.
[0057] Step S301: Determine the initial priority of the work order data based on the target business domain and problem type to which the work order data belongs.
[0058] Step S302: If there are N analyzed work order data belonging to the target business domain within the preset time window, the initial priority is increased to obtain the target priority corresponding to the work order data.
[0059] Where N is a positive integer.
[0060] Priority is a crucial metric used in task management to prioritize resource allocation. Initial priorities are typically pre-set based on the inherent attributes of the problem; for example, issues involving financial security usually have a higher initial priority than UI optimization suggestions.
[0061] Priority can include multiple levels, such as P0, P1, P2, P3, P4, etc., where P0 is the highest priority.
[0062] The initial priority is assigned by the server based on the identified attribute information by querying a predefined priority rule table, which ensures the standardization and consistency of priority judgment.
[0063] Increasing the initial priority is to enable dynamic priority adjustment, thereby changing the priority order of tasks.
[0064] Specifically, if the number of analyzed work order data within the same business domain reaches a preset threshold within a preset time window, it indicates that a common problem affecting multiple users may be emerging in that business domain. In this case, the server will increase the initial priority of the work order data by one level, thus obtaining the final target priority. The preset time window can be one hour, and the preset threshold is N, whose value can be dynamically adjusted according to the actual scenario.
[0065] By establishing initial priorities, it is ensured that work orders receive an urgency label that matches their attribute information from the very beginning, avoiding the subjectivity and delay of manually judging priorities one by one. By introducing a dynamic priority enhancement mechanism based on the number of work orders aggregated within a preset time window, it is possible to automatically highlight seemingly independent but actually related work order clusters that reflect systemic failures or major defects from ordinary problems, thus achieving proactive detection and early warning of potential online crises.
[0066] In some embodiments, the work order processing method may further include the following steps: storing work order data in a preset target priority processing queue according to the target priority, and when the work order data becomes the first element of the target priority processing queue, performing keyword matching based on attribute information to obtain a recommended processing solution corresponding to the problem type from the work order processing knowledge base.
[0067] Specifically, the server places work order data into corresponding queues based on target priority. For example, there may be multiple queues with different priorities, such as A0, A1, and A2. Multiple work order data in the same queue have the same target priority, and are arranged sequentially in the queue according to their submission time. When all work order data in the high-priority queue has been processed, work order data in the low-priority queue can be processed sequentially. In this way, physical separation and logical sorting of work order data can be achieved, ensuring that high-priority work orders are processed independently and with priority.
[0068] Keyword matching based on attribute information is an efficient retrieval strategy. When work order data is about to be processed, combining its attribute information with other possible contextual information for precise matching can improve the timeliness and relevance of the recommended processing solution.
[0069] By storing work order data into different processing queues according to target priority, high-priority work orders can be quickly processed and responded to in a dedicated channel that is not blocked by low-priority tasks, ensuring the timeliness of handling urgent issues.
[0070] In some embodiments, the work order processing method may further include the following steps: before sending the work order data to the target processing object, if the invalid request contains preset public opinion keywords, the target priority is updated to the highest priority.
[0071] Public opinion keywords are words or phrases used to identify and track specific public opinion trends. The list of public opinion keywords is usually based on historical experience or domain knowledge.
[0072] Specifically, when a user expresses dissatisfaction with the recommended processing solution sent by the server, the supplementary description or emotional expression provided by the user can be used as the content of the invalid request. If the invalid request contains preset public opinion keywords that represent strong dissatisfaction or crisis signals, such as "complaint", "315", "exposure", "very angry", etc., the server will unconditionally update the priority of the work order data to the predefined highest priority, such as P0, thereby triggering the highest level of response process.
[0073] By establishing a mandatory coverage rule that triggers the highest priority based on public opinion keywords, we ensure that extreme dissatisfaction or complaint intentions of individual users can be automatically identified and elevated to the highest level. This avoids delays in processing such high-risk work orders due to their ranking according to conventional technical priorities, thereby improving business risk control capabilities in the response mechanism.
[0074] In some embodiments, the work order processing method may further include the following steps: determining the target processing object corresponding to the work order data based on the target business domain and problem type; sending the work order data to the target processing object and providing early warning prompts to the target processing object according to the target priority.
[0075] Specifically, the server calculates the most suitable receiver identifier for the work order data based on a pre-defined mapping table with business domain and issue type as the composite key, or a routing algorithm. This identifier has the corresponding processing responsibilities and capabilities, such as team ID or work group link. The server then sends the work order data to the target processing object based on the receiver identifier.
[0076] The system can transmit work order data and its context to the receiving end of the target processing object, while simultaneously providing alerts to the target processing object according to its priority. For example, lower priorities such as P3 or P4 may simply be added silently to the task list of the target processing object; higher priorities such as P2 may trigger a normal in-application notification; priorities such as P1 may trigger multiple notifications and alert relevant members; and the highest priority, P0, may trigger strong alerts such as SMS, phone calls, or large screen flashing.
[0077] By combining sending actions with alerts, high-urgency issues are ensured to receive immediate attention from handlers, while low-urgency issues are queued in a non-disruptive manner. This optimizes the overall attention allocation and workflow of the handling team and reduces the risk of important notifications being buried.
[0078] It should be understood that, although Figure 2 and Figure 3 The steps in the flowchart are shown sequentially according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Figure 2 and Figure 3 Unless otherwise expressly stated herein, the steps illustrated and other steps involved in the embodiments are not subject to strict order restrictions and may be performed in other orders. Furthermore, at least some steps in the foregoing embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.
[0079] In a second aspect, embodiments of this application provide a work order processing system, such as... Figure 4 As shown, the work order processing system 400 includes: an analysis module 401, a filtering module 402, and a response module 403.
[0080] Analysis module 401 is used to perform work order analysis on the work order data to be processed and determine the attribute information of the work order data; the attribute information includes at least the target business domain to which the work order data belongs and the problem type; The filtering module 402 is used to obtain the recommended processing solution corresponding to the work order data from the preset work order processing knowledge base based on attribute information. The response module 403 is used to respond to invalid requests from users regarding the recommended processing solution, and to send the work order data to the target processing object based on the attribute information in order to obtain an effective processing solution provided by the target processing object.
[0081] In some embodiments, the work order processing system 400 may further include: The update module (not shown) is used to update the attribute information corresponding to the work order data after obtaining the effective processing solution provided by the target processing object, and to supplement the training of the work order analysis model and update the work order processing knowledge base based on the updated work order data and its corresponding effective processing solution.
[0082] In some embodiments, the analysis module 401 may further include: The feature analysis unit (not shown) is used to extract multimodal information from the text and images contained in the work order data, and to determine the target business domain and problem type to which the work order data belongs based on the extracted multimodal information.
[0083] In some embodiments, the attribute information of the work order data may also include the target priority corresponding to the work order data. Accordingly, the analysis module 401 may further include: The initial priority determination unit (not shown) is used to determine the initial priority of the work order data based on the target business domain and problem type to which the work order data belongs. The priority adjustment unit (not shown) is used to increase the initial priority of N analyzed work order data belonging to the target business domain within a preset time window, so as to obtain the target priority corresponding to the work order data; where N is a positive integer.
[0084] In some embodiments, the work order processing system 400 may further include: The processing solution matching unit (not shown) is used to store work order data into a preset target priority processing queue according to the target priority. When the work order data becomes the first element of the target priority processing queue, keyword matching is performed based on attribute information to obtain a recommended processing solution corresponding to the problem type from the work order processing knowledge base.
[0085] In some embodiments, the work order processing system 400 may further include: The priority update unit (not shown) is used to update the target priority to the highest priority if the invalid request contains preset public opinion keywords before sending the work order data to the target processing object.
[0086] In some embodiments, the response module 403 may further include: The object determination unit (not shown) is used to determine the target processing object corresponding to the work order data based on the target business domain and problem type. The sending unit (not shown) is used to send work order data to the target processing object and provide early warning prompts to the target processing object according to the target priority.
[0087] For more specific limitations regarding the work order processing system, please refer to the limitations of the work order processing method above. The work order processing system can also be used to execute more steps of the work order processing method in the embodiments of this application, which will not be repeated here. Each module in the above-described work order processing system can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0088] In a third aspect, embodiments of this application provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the work order processing method provided in any embodiment of the first aspect of this application.
[0089] In some embodiments, the computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores work order data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the work order processing method in any embodiment of this document.
[0090] Those skilled in the art will understand that Figure 5 The structures shown are merely block diagrams of some structures related to the embodiments of this application and do not constitute a limitation on the computer devices on which the embodiments of this application are applied. Specific computer devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.
[0091] In a fourth aspect, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the work order processing method provided in any embodiment of the first aspect of this application.
[0092] The computer-readable storage medium may be Figure 5 The computer-readable storage medium in the computer device shown.
[0093] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The aforementioned computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments of this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0094] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0095] The above embodiments merely illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of protection of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.
Claims
1. A work order processing method, characterized by, The method, applied to a pre-trained work order analysis model, includes: Perform work order analysis on the work order data to be processed to determine the attribute information of the work order data; the attribute information includes at least the target business domain to which the work order data belongs and the problem type. Based on the attribute information, a recommended processing solution corresponding to the work order data is obtained from a preset work order processing knowledge base; In response to an invalid request from the user regarding the recommended processing solution, the work order data is sent to the target processing object based on the attribute information to obtain an effective processing solution provided by the target processing object.
2. The method according to claim 1, characterized in that, The method further includes: After obtaining the effective processing solution provided by the target processing object, the attribute information corresponding to the work order data is updated, and based on the updated work order data and its corresponding effective processing solution, the work order analysis model is supplemented and trained, and the work order processing knowledge base is updated.
3. The method according to claim 1, characterized in that, The pre-trained work order analysis model is used to analyze the work order data to be processed, and to determine the attribute information of the work order data, including: Multimodal information is extracted from the text and images contained in the work order data, and the target business domain and problem type to which the work order data belongs are determined based on the extracted multimodal information.
4. The method according to claim 1, characterized in that, The attribute information of the work order data also includes the target priority corresponding to the work order data; The step of performing work order analysis on the work order data to be processed and determining the attribute information of the work order data also includes: The initial priority of the work order data is determined based on the target business domain and problem type to which the work order data belongs. If there are N analyzed work order data belonging to the target business domain within a preset time window, the initial priority is increased to obtain the target priority corresponding to the work order data; where N is a positive integer.
5. The method according to claim 4, characterized in that, The method further includes: According to the target priority, the work order data is stored in a preset target priority processing queue. When the work order data becomes the first element of the target priority processing queue, keyword matching is performed based on the attribute information, and a recommended processing solution corresponding to the problem type is obtained from the work order processing knowledge base.
6. The method according to claim 4, characterized in that, The method further includes: Before sending the work order data to the target processing object, if the invalid request contains preset public opinion keywords, the target priority is updated to the highest priority.
7. The method according to any one of claims 4 to 6, characterized in that, The step of responding to an invalid request from a user regarding the recommended processing solution, and sending the work order data to the target processing object based on the attribute information, includes: Based on the target business domain and the problem type, determine the target processing object corresponding to the work order data; The work order data is sent to the target processing object, and an early warning is issued to the target processing object according to the target priority.
8. A work order processing system, characterized in that, The system includes: The analysis module is used to perform work order analysis on the work order data to be processed and determine the attribute information of the work order data; the attribute information includes at least the target business domain to which the work order data belongs and the problem type; The filtering module is used to obtain the recommended processing scheme corresponding to the work order data from a preset work order processing knowledge base based on the attribute information. The response module is used to respond to invalid requests from users regarding the recommended processing solution, and to send the work order data to the target processing object based on the attribute information in order to obtain an effective processing solution provided by the target processing object.
9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.
10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.