Enterprise it service management ticket processing method and apparatus
By generating precise orchestration suggestions through work order analysis agents and knowledge bases, and automatically determining the handlers and execution recommendations, the problem of low work order processing efficiency in ITSM systems has been solved, and a highly efficient work order processing workflow has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA CONSTRUCTION BANK
- Filing Date
- 2026-03-23
- Publication Date
- 2026-06-19
Smart Images
Figure CN122243408A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of intelligent operation and maintenance, and more specifically, to a method and apparatus for processing work orders in enterprise IT service management. Background Technology
[0002] In the field of enterprise IT service management technology, ITSM (IT Service Management) systems are the core infrastructure supporting the efficient operation of enterprise IT services. Their main function is to standardize the management of the entire enterprise IT service process, covering all aspects of IT service planning, design, deployment, operation, and optimization. Among these, the work order processing module, as a core component of the ITSM system, bears the crucial responsibility of receiving IT service requests (such as system fault reports, feature inquiries, and request submissions) submitted by internal employees or external users, allocating processing resources, tracking processing progress, and providing feedback on processing results. It is a vital support for ensuring the continuity of enterprise IT services and improving user satisfaction.
[0003] Currently, ITSM systems in related technologies generally adopt manual order acceptance or order matching based on predefined fixed rules in the work order processing process. Under this model, the formulation, updating, verification, and maintenance of work order processing rules all rely on professional technicians to complete manually. This not only consumes a lot of manpower and time costs, but is also prone to errors due to human operation, which can lead to deviations and delays in the rules, thereby affecting the accuracy and timeliness of work order matching.
[0004] Of particular note is that the above-mentioned work order processing mode is highly dependent on predefined rules. For abnormal work orders, special work orders, or new types of work orders that are outside the scope of predefined rules, automatic matching and quick acceptance are often not possible. The work order processing mode can only rely on manual investigation and judgment before being assigned and processed. This not only leads to untimely response to work order acceptance and prolongs the overall processing cycle of work orders, but also makes the work order processing process time-consuming, labor-intensive, and inefficient. Summary of the Invention
[0005] This application provides a method and apparatus for processing work orders in enterprise IT service management, which at least solves the problem of low efficiency in work order processing in related technologies.
[0006] According to one embodiment of this application, a method for processing work orders in enterprise IT service management is provided, including:
[0007] The work order analysis agent obtains analysis results based on the content of the work orders to be processed, and then classifies and sorts the work orders to be processed based on the analysis results to obtain classification results and sorting results. Among them, the analysis results include: scope of action, subject of action, environment, and flow status.
[0008] The agent generates action recommendations based on the analysis results; these recommendations include: orchestration recommendations based on the execution history and new orchestration recommendations.
[0009] The work order dispatching intelligent agent determines the work order handler based on the classification results, sorting results, and personnel information, sends the handling suggestions to the work order handler, and generates an execution prompt;
[0010] The agent executes the disposal suggestions based on the confirmation result of the execution prompt.
[0011] In one implementation, a work order dispatching agent determines the work order handler based on classification results, ranking results, and personnel information, including:
[0012] Configuration of the interface for generating personnel information based on classification results;
[0013] Personnel information is obtained based on the personnel information interface; the personnel information includes: area of responsibility, skill coverage, and workload status.
[0014] The classification results, sorting results, and personnel information are matched to determine the person responsible for processing the work order.
[0015] In one implementation, a disposal agent generates disposal recommendations based on analysis results; wherein the disposal recommendations include: orchestration recommendations based on the execution history and new orchestration recommendations; including:
[0016] Based on the analysis results, the work order knowledge base is retrieved, and handling recommendations are determined based on whether there are historical handling experiences in the work order knowledge base that correspond to the analysis results.
[0017] If there is historical handling experience in the work order knowledge base that corresponds to the analysis results, the first handling arrangement corresponding to the historical handling experience will be determined as the historical arrangement suggestion.
[0018] If no historical handling experience corresponding to the analysis results exists in the work order knowledge base, a second handling arrangement is generated to determine the second handling arrangement as a new arrangement suggestion.
[0019] In one implementation, if historical handling experience corresponding to the analysis results exists in the work order knowledge base, the first handling arrangement corresponding to the historical handling experience is determined as the historical arrangement suggestion, including:
[0020] Analyze the matching degree between the analysis results and historical handling experience;
[0021] When there are multiple matching values, the first processing arrangement corresponding to the historical processing experience with the highest matching value is selected;
[0022] The first disposal is determined to be arranged as a historical arrangement.
[0023] In one implementation, if no historical handling experience corresponding to the analysis results exists in the work order knowledge base, a second handling arrangement is generated to determine the second handling arrangement as a new arrangement suggestion, including:
[0024] Based on the analysis results, obtain multiple handling experiences related to the analysis results;
[0025] Generate disposal suggestion text based on multiple disposal experiences;
[0026] A second disposal arrangement is generated based on the disposal recommendation text, and the second disposal arrangement is identified as the new arrangement recommendation.
[0027] In one implementation, the action execution agent executes a action suggestion in response to a confirmation result of the execution prompt, including:
[0028] If the proposed action is a historical orchestration suggestion, an execution prompt is generated to determine whether to execute the action directly. The historical orchestration suggestion includes: task number, task description, task execution content, and historical experience tags.
[0029] If the confirmation result of the execution prompt is to execute directly, the historical orchestration suggestions will be executed sequentially based on the task sequence number.
[0030] In one implementation, the action execution agent executes a action suggestion in response to a confirmation result of the execution prompt, including:
[0031] If the proposed action is a new arrangement suggestion, an execution prompt will be generated to review and modify the new arrangement suggestion. The new arrangement suggestion includes: task number, task description, task execution content, and non-historical experience tags.
[0032] If the confirmation result of the execution prompt is "confirmed after review and modification", then execute the new arrangement suggestion after review and modification.
[0033] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and the computer program is configured to perform the steps in any of the above method embodiments when it is run.
[0034] According to yet another embodiment of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.
[0035] According to yet another embodiment of this application, a computer program product is also provided, including computer instructions that, when executed by a processor, implement the steps in any of the above method embodiments.
[0036] In one embodiment of this application, based on the work order analysis intelligent agent as the starting point of the collaborative process, the agent first parses the work order content to be processed to obtain analysis results such as the scope of action, the subject of action, the environment, and the flow status. Then, classification and sorting processes are used to obtain classification and sorting results, providing accurate data support for subsequent collaborative steps. The disposal generation intelligent agent takes over the analysis results output by the work order analysis intelligent agent and generates disposal suggestions that include historical execution scheduling suggestions and new execution scheduling suggestions, clarifying the specific direction and plan for work order processing and building a bridge between analysis and execution. The work order dispatch intelligent agent integrates the classification and sorting results and personnel information given by the work order analysis intelligent agent to accurately determine the appropriate work order handler, and simultaneously sends the disposal suggestions formulated by the disposal generation intelligent agent. The system generates execution prompts for handlers, achieving efficient matching of work orders and processing resources, avoiding the lag and bias of manual allocation. The execution agent, as the endpoint of the collaborative process, responds to the handler's confirmation of the execution prompts, implements the execution suggestions, and completes the closed loop of work order processing. The four agents have clear division of labor, are interconnected, and work together to replace the manual operation and fixed rule matching mode in related technologies. It eliminates the need for professional personnel to manually maintain processing rules and can automatically complete work order analysis, solution formulation, personnel allocation, and execution. In particular, it can efficiently handle abnormal, special, and novel work orders that exceed the scope of predefined rules, significantly shortening the work order response and processing cycle, reducing human time costs, and thus effectively solving the problem of low work order processing efficiency in related technologies, ultimately achieving the technical effect of improving work order processing efficiency. Attached Figure Description
[0037] The accompanying drawings, which are included to provide a further understanding of the embodiments of this application and constitute a part of the embodiments of this application, illustrate exemplary embodiments of this application and, together with their descriptions, serve to explain the embodiments of this application and do not constitute an improper limitation of the embodiments of this application. In the drawings:
[0038] Figure 1 This is a hardware structure block diagram of the enterprise IT service management work order processing method according to an embodiment of this application;
[0039] Figure 2 This is a schematic diagram of the system structure for implementing the enterprise IT service management work order processing method according to an embodiment of this application;
[0040] Figure 3 This is a flowchart of an enterprise IT service management work order processing method according to an embodiment of this application;
[0041] Figure 4 This is a flowchart of a method for obtaining disposal suggestions based on analysis results by a disposal-generating intelligent agent according to an embodiment of this application;
[0042] Figure 5 This is a flowchart of a method for determining the first disposal arrangement corresponding to the historical disposal experience as a historical arrangement suggestion when there is historical disposal experience in the work order knowledge base that corresponds to the analysis results, according to an embodiment of this application.
[0043] Figure 6 This is a flowchart of a method for generating a second handling arrangement and determining the second handling arrangement as a new arrangement suggestion when there is no historical handling experience corresponding to the analysis result in the work order knowledge base, according to an embodiment of this application.
[0044] Figure 7 This is a flowchart of a method for determining the work order handler based on classification results, sorting results, and personnel information by a work order dispatching intelligent agent according to an embodiment of this application.
[0045] Figure 8 This is a flowchart of a method for determining the work order handler based on classification results, sorting results, and personnel information by a work order dispatching intelligent agent according to an embodiment of this application.
[0046] Figure 9 This is a flowchart of a method for executing a disposal suggestion by a disposal execution agent in response to the confirmation result of an execution prompt, according to an embodiment of this application;
[0047] Figure 10 This is a flowchart of an integrated operation and maintenance tool and a method for building a work order knowledge base according to an embodiment of this application. Detailed Implementation
[0048] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of this application can be combined with each other.
[0049] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of the embodiments of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.
[0050] The collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0051] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.
[0052] The methods and embodiments provided in this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of the enterprise IT service management work order processing method according to an embodiment of this application, such as... Figure 1 As shown, a hardware board may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor (MCU) or programmable logic device, etc.) and a memory 104 for storing data are also shown. The computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.
[0053] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the enterprise IT service management work order processing method in this embodiment. The processor 102 executes various functional applications and implements the above-described methods by running the computer programs stored in the memory 104. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0054] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a telecommunications provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a gateway to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.
[0055] Figure 2 This is a schematic diagram of the system structure for implementing the enterprise IT service management work order processing method according to an embodiment of this application, such as... Figure 2 As shown, the system includes: a work order analysis agent, a disposal generation agent, a work order dispatch agent, a disposal execution agent, and a work order knowledge base. The work order analysis agent obtains work order data from the ITSM system through a work order data acquisition module. The work order analysis agent is connected to the disposal generation agent, the disposal generation agent is connected to the work order dispatch agent, the work order dispatch agent is connected to the disposal execution agent, and the work order knowledge base is connected to both the disposal generation and disposal execution agents.
[0056] This application provides a method for processing work orders in enterprise IT service management. Figure 3 This is a flowchart of an enterprise IT service management work order processing method according to an embodiment of this application, such as... Figure 3 As shown, the process includes:
[0057] Step S301: The work order analysis agent obtains analysis results based on the work order content of the work order to be processed, and classifies and sorts the work orders to be processed based on the analysis results to obtain classification results and sorting results; wherein, the analysis results include: scope of action, subject of action, environment, and flow status.
[0058] In one exemplary implementation, for example, a work order list is obtained in real time from the ITSM system via a work order data acquisition module to obtain the work orders to be processed and their specific contents. A work order analysis agent converts the work orders to be processed and their specific contents into structured data and analyzes this structured data to obtain analysis results. These analysis results include: scope of action, subject of action, environment, and flow status. Based on the analysis results, the work orders to be processed are classified and sorted to obtain classification and sorting results. The processing priority is determined based on the classification and sorting results.
[0059] Step S302: The agent generates a disposal suggestion based on the analysis results; wherein, the disposal suggestion includes: the orchestration suggestion for executing the history and the orchestration suggestion for executing the new one.
[0060] In one exemplary implementation, for example, after the action generation agent receives the analysis results from the work order analysis agent, it first searches the work order knowledge base to determine if there is a corresponding historical action experience. If it does, it analyzes the matching degree between the two and selects the historical action experience with the highest matching degree as the first action arrangement, so as to use the first action arrangement as a historical arrangement suggestion. If it does not exist, it extracts multiple action experiences related to the analysis results and generates a second action arrangement, so as to use the second action arrangement as a new arrangement suggestion. The first action arrangement and the second action arrangement include the fields: task number, task description, and task execution content. For example, for a high-priority network operation and maintenance work order, if three historical experiences of "server network connection timeout" are retrieved, the interface arrangement of "check server network card configuration, test cloud network link, restart network service" with a matching degree of 95% is selected as a historical suggestion. If there is no historical experience, it integrates relevant experiences of "network fault troubleshooting" and "cloud server operation and maintenance" to generate suggestion text, and then transforms it into a new arrangement suggestion containing "confirm server IP configuration, contact cloud service provider to check link, check firewall rules". Therefore, providing targeted and readily implementable solutions bridges the gap between analysis and execution, reduces the time cost for those involved in the process to explore independently, and enhances the professionalism and efficiency of solution development.
[0061] Step S303: The work order dispatching intelligent agent determines the work order handler based on the classification results, sorting results, and personnel information, sends the handling suggestions to the work order handler, and generates an execution prompt;
[0062] In one exemplary implementation, for example, the work order dispatching agent first generates a personnel information interface configuration based on the work order classification results. Through this interface, it obtains information such as the operator's area of responsibility, skill coverage, and workload status. Then, it performs multi-dimensional matching of the classification results (e.g., network maintenance), sorting results (e.g., high priority), and personnel information to filter out suitable work order handlers. Finally, it sends the handling suggestions to the handler's work terminal and generates a corresponding execution prompt. For example, for the aforementioned high-priority network maintenance work order, the agent obtains information through the interface from operator Li, who is responsible for cloud server network maintenance (area of responsibility), possesses link troubleshooting skills (skill coverage), and currently only handles one low-priority work order (idle workload). It identifies Li as the handler, sends historical handling suggestions, and generates an execution prompt asking "Should this historical orchestration suggestion be executed directly?". Therefore, it avoids the subjectivity and lag of manual allocation, achieves precise matching between work orders and suitable processing resources, ensures that high-priority work orders are quickly transferred to appropriate personnel, and improves the efficiency and accuracy of work order dispatch.
[0063] Step S304: The processing agent responds to the confirmation result of the execution prompt and executes the processing suggestion.
[0064] In one exemplary implementation, for example, the action execution agent responds to different confirmation results based on the type of action suggestion. If it is a historical orchestration suggestion, after receiving confirmation of "execute directly" from the handler, it triggers the corresponding interface tools or scripts to execute the action operation sequentially according to the task sequence number. If it is a new orchestration suggestion, after receiving feedback of "confirm execution after review and modification" from the handler, it executes the operation according to the modified task sequence. For example, after Mr. Li confirms the direct execution of a historical suggestion, the action execution agent first calls the network card configuration check tool according to the sequence number, then triggers the network link test interface, and finally executes the network service restart script, implementing the entire process sequentially. If it is a new orchestration suggestion, after Mr. Li adds the step of "checking server security group rules" and confirms it, the agent executes all operations according to the modified sequence. Therefore, standardizing the action execution process ensures the orderly implementation of action suggestions. By adapting to historical reuse and new scenarios through human-computer interaction, it not only ensures the efficient execution of regular work orders but also takes into account the flexible handling of special work orders, completing the closed loop of work order processing.
[0065] Through steps S301 to S304, based on the work order analysis agent as the starting point of the collaborative process, the analysis results, such as the scope of action, the subject of action, the environment, and the flow status, are first parsed from the work order content to be processed. Then, classification and sorting processes are used to obtain classification and sorting results, providing accurate data support for subsequent collaborative steps. The disposal generation agent takes over the analysis results output by the work order analysis agent and generates disposal suggestions that include historical execution scheduling suggestions and new execution scheduling suggestions, clarifying the specific direction and plan for work order processing and building a bridge between analysis and execution. The work order dispatch agent integrates the classification and sorting results and personnel information given by the work order analysis agent to accurately determine the appropriate work order handler, and simultaneously sends the disposal suggestions formulated by the disposal generation agent. The system sends work orders to the handler and generates execution prompts, achieving efficient matching between work orders and processing resources and avoiding the lag and bias of manual allocation. The execution agent, as the endpoint of the collaborative process, responds to the handler's confirmation of the execution prompts, implements the execution suggestions, and completes the closed loop of work order processing. The four agents have clear division of labor, are interconnected, and work together to replace the manual operation and fixed rule matching mode in related technologies. There is no need for professional personnel to manually maintain the processing rules. It can automatically complete work order analysis, solution formulation, personnel allocation, and execution. In particular, it can efficiently handle abnormal, special, and new work orders that exceed the scope of predefined rules, significantly shortening the work order response and processing cycle, reducing human time costs, and thus effectively solving the problem of low work order processing efficiency in related technologies, ultimately achieving the technical effect of improving work order processing efficiency.
[0066] Figure 4 This is a flowchart of a method for obtaining disposal suggestions based on analysis results by a disposal-generating intelligent agent according to an embodiment of this application, such as... Figure 4 As shown, in one implementation, a disposal agent generates disposal suggestions based on analysis results; wherein, the disposal suggestions include: orchestration suggestions based on the execution history and new orchestration suggestions; including:
[0067] Step S401: Based on the analysis results, retrieve the work order knowledge base to determine the handling recommendations based on whether there are historical handling experiences in the work order knowledge base that correspond to the analysis results;
[0068] In one exemplary implementation, for example, the action generation agent receives the analysis results output by the work order analysis agent (e.g., the domain is "server maintenance," the subject is "office area X1 server," the environment is "internal network," and the status is "initial report"). Using this core information as search criteria, it queries the work order knowledge base that stores historical action experience (including documents, images, and other multimodal data) to determine whether there is historical action experience in the knowledge base that perfectly matches the analysis results. Therefore, quickly completing the core judgment of "whether there is reusable experience" provides a clear direction for the generation of subsequent action suggestions, avoids blindly designing action plans, reduces ineffective workload, and improves the relevance of the generated suggestions.
[0069] Step S402: If there is historical handling experience in the work order knowledge base that corresponds to the analysis results, the first handling arrangement corresponding to the historical handling experience is determined as the historical arrangement suggestion.
[0070] In one exemplary implementation, for example, when a historical handling experience corresponding to the analysis result is retrieved from the work order knowledge base, the first handling arrangement associated with that historical experience is directly extracted and identified as a historical arrangement suggestion. For example, if the analysis result "Office area X1 server reports failure to boot on intranet for the first time" retrieves a matching historical experience, the first handling arrangement corresponding to this experience is "call the server hardware status detection interface, query the data center power supply monitoring interface, and execute the server remote wake-up interface," the handling generation agent will then output this interface arrangement as a historical arrangement suggestion. Therefore, mature handling solutions that have been proven in practice can be directly reused without redesigning the process, ensuring the reliability and feasibility of the handling suggestions while significantly shortening the time for developing handling solutions and improving the efficiency of work order processing.
[0071] Step S403: If there is no historical handling experience corresponding to the analysis results in the work order knowledge base, a second handling arrangement is generated to determine the second handling arrangement as a new arrangement suggestion.
[0072] In one exemplary implementation, for example, if no historical handling experience corresponding to the analysis result is found in the work order knowledge base, the handling generation agent first retrieves multiple handling experiences related to the analysis result from the knowledge base (e.g., if the analysis result is "first-time report of database connection failure in the R&D area X2 server cloud environment," related experiences include "X2 server network configuration troubleshooting," "cloud environment database permission management," and "remote database connection testing"). Based on these related experiences, a structured handling suggestion text is generated, and then the text is transformed into a second handling orchestration that can directly call operation and maintenance tools (e.g., "call the X2 network configuration query interface, cloud database permission verification interface, and remote database connection testing interface"), which is then identified as a new orchestration suggestion. Therefore, this effectively solves the problem of generating handling solutions for new, special, or work orders that exceed the scope of historical experience. By integrating relevant experience, the professionalism and rationality of the new suggestions are ensured, avoiding confusion in handling direction due to the lack of historical precedents, and balancing the flexibility and feasibility of the solution.
[0073] Through steps S401 to S403, the processing agent first searches the work order knowledge base to determine if there is any directly reusable historical experience, and then outputs targeted historical or new orchestration suggestions. This method achieves efficient reuse of routine work order processing experience, ensuring the reliability and efficiency of suggestions; it also solves the problem of missing solutions for new and special work orders, generating professional suggestions through the integration of relevant experience, taking into account both flexibility and adaptability. The entire process requires no manual intervention in solution design, automatically generating structured and implementable interface orchestration suggestions, successfully building a bridge between work order analysis and execution, providing clear guidance for subsequent processing and execution stages, and significantly improving the coherence and overall efficiency of work order processing.
[0074] Figure 5 This is a flowchart illustrating a method for determining the first disposal arrangement corresponding to the historical disposal experience as a historical arrangement suggestion when historical disposal experience corresponding to the analysis results exists in the work order knowledge base, according to an embodiment of this application. Figure 5 As shown, in one implementation, if historical handling experience corresponding to the analysis results exists in the work order knowledge base, the first handling arrangement corresponding to the historical handling experience is determined as the historical arrangement suggestion, including:
[0075] Step S501: Analyze the matching degree value between the analysis results and historical handling experience;
[0076] In one exemplary implementation, for example, the action generation agent first extracts the core dimensions (scope of action, subject of action, environment, and status of operation) of the work order analysis results, and then aligns these dimensions with each historical action experience retrieved from the work order knowledge base. A preset algorithm (such as a weighted scoring method) is used to calculate the matching degree value between the two. For example, if a work order analysis result is "Finance Department X1 computer (subject of action) first reported (status of operation) Excel startup crashes on the office intranet (environment) (scope of action: office software maintenance)," the matching degree is scored against each dimension of three historical experiences (10 points for a complete match, 5 points for a partial match, and 0 points for no match), and the total matching degree value for each historical experience is finally calculated. Therefore, the fuzzy judgment of "whether it matches" is transformed into quantitative matching degree data, avoiding experience selection bias caused by subjective judgment and providing an objective basis for subsequent selection of the optimal solution.
[0077] Step S502: When there are multiple matching values, select the first processing arrangement corresponding to the historical processing experience with the highest matching value;
[0078] In one exemplary implementation, for example, when multiple historical handling experiences corresponding to the analysis results are retrieved from the work order knowledge base, and their respective matching scores are different (e.g., in the example above, the matching scores of the three historical experiences are 92%, 85%, and 78%, respectively), the handling generation agent automatically selects the historical handling experience with the highest matching score and extracts its corresponding first handling arrangement. Therefore, it ensures that the selected historical experience has the highest degree of relevance to the current work order, maximizing the relevance and reliability of the handling suggestions and avoiding redundancy or poor results in the handling process due to selecting suboptimal experience.
[0079] Step S503: Determine the first disposal arrangement as a historical arrangement suggestion.
[0080] In one exemplary implementation, for example, the disposal generation agent directly determines the first disposal arrangement corresponding to the historical disposal experience with the highest matching degree value selected in step S502 as the historical arrangement suggestion for the current work order, and adds a "historical experience tag" to it, clearly marking the task number, task description, and task execution content (such as in the example above, determining "1. Call the software version detection interface, 2. Clear the Excel cache interface, 3. Repair the Office installation interface" as the historical arrangement suggestion). Therefore, it quickly outputs a structured and directly implementable disposal solution without additional secondary processing, providing clear and explicit operation guidance for subsequent work order assignment and execution, and reducing the time spent on process connection.
[0081] Through steps S501 to S503, the problem of blindly reusing experience is avoided by accurately quantifying and matching historical handling experience. By selecting the solution with the highest matching degree, the high degree of fit between the handling suggestions and the current work order is ensured. Finally, a structured first handling arrangement is clearly output, providing reliable support for subsequent processes. The entire process requires no manual intervention and automatically completes the selection and transformation of optimal historical experience. This not only ensures the accuracy and reliability of historical experience reuse but also significantly improves the efficiency of handling suggestion generation, further enhancing the automation and standardization of work order processing.
[0082] Figure 6 This is a flowchart illustrating a method for generating a second handling arrangement when no historical handling experience corresponding to the analysis result exists in the work order knowledge base, according to an embodiment of this application, and determining the second handling arrangement as a new arrangement suggestion. Figure 6 As shown, in one implementation, if no historical handling experience corresponding to the analysis results exists in the work order knowledge base, a second handling arrangement is generated to determine the second handling arrangement as a new arrangement suggestion, including:
[0083] Step S601: Based on the analysis results, obtain multiple treatment experiences related to the analysis results;
[0084] In one exemplary implementation, for example, when there is no historical handling experience directly corresponding to the analysis result in the work order knowledge base, the handling generation agent uses the core dimensions of the analysis result (scope of action, subject of action, environment, and flow status) as search conditions to filter out multiple handling experiences associated with each dimension from the knowledge base. For example, if the analysis result of a work order is "The R&D department's X2 server (subject of action) reported for the first time (flow status) container service startup failure in the private cloud environment (environment) (scope of action: container operation and maintenance)," the agent retrieves three relevant handling experiences: "X2 server service startup dependency component investigation," "cloud environment container network configuration verification," and "container image integrity detection." Therefore, it breaks the limitation that "no suggestions can be generated without direct experience," and obtains usable indirect experience through associated retrieval, providing sufficient material for the generation of subsequent handling suggestions and ensuring the professional basis of the suggestions.
[0085] Step S602: Generate a second treatment arrangement based on multiple treatment experiences, and determine the second treatment arrangement as a new arrangement recommendation.
[0086] In one exemplary implementation, for example, the action generation agent logically integrates and structures multiple relevant action experiences obtained in step S601, generates a second action orchestration according to the process logic of "problem investigation, configuration verification, and fault repair," and adds "non-historical experience tags." For example, the above multiple relevant action experiences are transformed into: "1. Call the X2 component query interface (parameter: container service name), 2. Call the cloud container network configuration verification interface (parameter: server IP, container ID), 3. Call the container image detection interface (parameter: image name, version number), 4. Call the container restart interface (parameter: container ID), 5. Call the log query interface (parameter: container ID, time range)," and this sequence is determined to be a new orchestration suggestion. Therefore, the action suggestions in text form are transformed into a structured interface process that the agent can directly execute, opening up the link from "suggestion text" to "actual execution," ensuring that the new orchestration suggestions can be implemented quickly, and at the same time, the type is distinguished by tags, providing a basis for the generation of prompts in subsequent execution stages.
[0087] Through steps S601 to S602, the professionalism of the recommendations is ensured by retrieving relevant experience; the feasibility of the recommendations is achieved by logically integrating and generating a second handling arrangement. The entire process requires no manual intervention in designing the solution, automatically completing the transformation from experience screening to an executable process. This balances the flexibility and adaptability of the handling recommendations with the standardization and implementation of the process, significantly improving the processing efficiency of new work orders and further enhancing the full-scenario coverage capability of work order handling recommendation generation.
[0088] Figure 7 This is a flowchart illustrating a method for determining the work order handler based on classification results, sorting results, and personnel information using a work order dispatching intelligent agent, according to an embodiment of this application. Figure 7 As shown, in one implementation, the work order dispatching agent determines the work order handler based on classification results, sorting results, and personnel information, including:
[0089] Step S701: Configure the interface for generating personnel information based on the classification results;
[0090] In one exemplary implementation, for example, the work order dispatching agent first obtains the work order classification results (e.g., "Network Operations and Maintenance, Cloud Server Network Fault Work Orders"), and then clarifies the dimensions of personnel information to be queried based on this classification. It needs to match "Responsible Areas Include Cloud Server Network Operations and Maintenance" and "Skill Coverage Includes Cloud Network Link Troubleshooting." Based on these dimensions, configuration parameters for the personnel information interface are generated (e.g., interface request fields, filtering conditions, data return format, etc.). For example, if the classification result is "Database Operations and Maintenance, MySQL Performance Optimization Work Orders," then the configured interface needs to filter personnel information whose "Responsible Area is MySQL Database" and "Skill Coverage Includes Performance Tuning." Therefore, clarifying the query direction and scope of personnel information avoids the interface obtaining irrelevant personnel data, ensuring that the subsequently obtained personnel information is highly relevant to the work order classification, laying the foundation for accurate matching.
[0091] Step S702: Obtain personnel information based on the personnel information interface; wherein, personnel information includes: area of responsibility, skill coverage, and workload status;
[0092] In one exemplary implementation, for example, the work order dispatching agent, based on the interface configuration generated in step S701, calls the personnel information interface of the enterprise personnel management system to obtain personnel information that meets the screening criteria. This information specifically includes each person's area of responsibility (e.g., "cloud server network maintenance," "desktop office software maintenance"), skill coverage (e.g., "cloud network link troubleshooting," "MySQL index optimization"), and workload status (e.g., the number of work orders currently received, work order priority distribution). For example, for "cloud server network failure work orders," the interface retrieves information about Zhang (area of responsibility: cloud server network maintenance, skill: link troubleshooting / firewall configuration, workload: 1 low-priority work order) and Wang (area of responsibility: cloud server network maintenance, skill: link troubleshooting / IP configuration, workload: 3 medium-priority work orders). Therefore, a precise pool of candidate personnel is quickly obtained, avoiding the tedious manual screening process. Simultaneously, the workload status data provides a basis for "optimal matching," improving the rationality of the dispatch.
[0093] Step S703: Match the classification results, sorting results, and personnel information to determine the person responsible for processing the work order.
[0094] In one exemplary implementation, for example, the work order dispatching agent performs multi-dimensional matching of the work order's classification results (e.g., "cloud server network failure"), sorting results (e.g., "high priority"), and the personnel information obtained in step S702. First, it filters out personnel whose responsible areas and skill coverage match the classification results (e.g., Zhang and Wang). Then, it prioritizes matching personnel with less workload based on the sorting results (high priority), ultimately determining the work order handler. For example, in the above example, both Zhang and Wang meet the classification matching requirements, but Zhang has a lighter workload and his skill coverage is more closely aligned with "network failure," therefore Zhang is determined as the handler. Thus, it avoids the subjectivity and lag of manual allocation, achieving comprehensive matching of "work order type, personnel skills, processing priority, and workload," ensuring that work orders are assigned to the most suitable and least busy personnel, improving the response speed and quality of work order processing.
[0095] Through steps S701 to S703, the query scope is clearly defined through interface configuration to ensure the relevance of personnel information; core personnel information is quickly obtained through interface calls, reducing data acquisition time; and optimal matching between work orders and handlers is achieved through multi-dimensional matching. The entire process requires no manual intervention, automatically completing the accurate assignment from classification results to handlers. It takes into account the suitability of work order type and personnel skills, the correlation between work order priority and processing efficiency, and the balance of personnel workload, greatly improving the accuracy, efficiency, and rationality of work order assignment, and providing key support for the efficient processing of subsequent work orders.
[0096] Figure 8 This is a flowchart illustrating a method for determining the work order handler based on classification results, sorting results, and personnel information using a work order dispatching intelligent agent, according to an embodiment of this application. Figure 8 As shown, in one embodiment, the action execution agent executes a action suggestion in response to the confirmation result of the execution prompt, including:
[0097] Step S801: If the handling suggestion is a historical orchestration suggestion, generate an execution prompt on whether to directly execute the handling; wherein, the historical orchestration suggestion includes: task number, task description, task execution content, and historical experience tags;
[0098] In one exemplary implementation, for example, when the disposal suggestion is a historical orchestration suggestion (which includes a task number, task description, task execution content, and historical experience tags, such as "1. Call the server memory detection interface to query memory usage; historical experience tag: verified to be effective multiple times" or "2. Call the process cleanup interface to terminate redundant processes; historical experience tag: adapted to X1 server"), the disposal execution agent automatically generates an execution prompt: "Should we directly execute this historical orchestration suggestion? (This suggestion has been verified through multiple practices and is adapted to the current work order scenario)" and sends it to the work order handler's terminal. Therefore, clearly informing the handler of the reliability and adaptability of the suggestion simplifies the handler's decision-making process, avoids repeated review of mature disposal solutions, and lays the foundation for rapid execution.
[0099] In step S802, if the confirmation result of the execution prompt is to execute directly, the historical orchestration suggestions are executed sequentially based on the task sequence number.
[0100] In one exemplary implementation, for example, after the work order handler reviews the execution prompts and confirms "Execute Directly," the intelligent action will trigger the corresponding operation and maintenance tool interfaces to perform operations sequentially according to the task sequence numbers in the historical orchestration suggestions. For example, it might first call the server memory detection interface to obtain memory usage data (Task 1), and after confirming the existence of redundant processes, call the process cleanup interface to terminate the redundant processes according to specified parameters (Task 2). The entire process is completed automatically and sequentially, without the need for manual step-by-step operation. Therefore, by strictly following the proven handling process, it avoids omissions or sequence errors caused by manual operation, ensures the stability of the handling effect, and significantly shortens the execution time, thereby improving the efficiency of work order processing.
[0101] Through steps S801 to S802, the historical arrangement suggestions not only ensure the handler's right to know and decision-making through clear prompts, but also simplify the operation process through automatic sequential execution. This logic fully utilizes mature historical handling experience, avoiding redundant steps of repeated review, ensuring the standardization and accuracy of the execution process, effectively improving the processing efficiency of routine work orders, and reducing the risk of human error, allowing historical experience to be quickly and reliably transformed into actual handling results.
[0102] Figure 9 This is a flowchart of a method for executing a disposal suggestion by a disposal execution agent in response to a confirmation result of an execution prompt, according to an embodiment of this application. Figure 9 As shown, in one embodiment, the action execution agent executes a action suggestion in response to the confirmation result of the execution prompt, including:
[0103] Step S901: If the proposed action is a new orchestration suggestion, generate an execution prompt to review and modify the new orchestration suggestion; wherein, the new orchestration suggestion includes: task number, task description, task execution content, and non-historical experience tags;
[0104] In one exemplary implementation, for example, when the proposed action is a new orchestration suggestion (which includes a task number, task description, task execution content, and non-historical experience tags, such as "1. Call the AI server resource monitoring interface to query CPU / memory usage, non-historical experience tags", "2. Call the private cloud task scheduling interface to view the model training queue priority, non-historical experience tags", "3. Call the storage IO test interface to detect data read / write speed, non-historical experience tags"), the action execution agent automatically generates an execution prompt: "This suggestion is a new scenario orchestration and needs to be reviewed and modified before execution. Please confirm whether to adjust the task steps, supplement execution parameters, or optimize the interface call logic," along with complete details of the new orchestration suggestion, and sends it to the work terminal of the work order handler. Therefore, clearly indicating that the new suggestion lacks historical verification basis guides the handler to conduct professional review, avoiding execution risks caused by inadequate consideration of the new solution, and ensuring the safety and rationality of the action process.
[0105] Step S902: If the confirmation result of the execution prompt is "confirmed after review and modification", execute the new arrangement suggestion after review and modification.
[0106] In one exemplary implementation, for example, after reviewing the execution prompts and new orchestration suggestions, the work order handler modifies them based on actual operation and maintenance experience. For instance, they might add the task step "4. Call the network bandwidth test interface to check cross-node data transmission latency," or adjust the calling parameters of some interfaces (e.g., changing the memory usage query frequency from 10 seconds / time to 5 seconds / time). After confirming the modifications, they provide feedback "Review and modification completed, ready to execute." Upon receiving this confirmation, the execution agent triggers the corresponding operation and maintenance tool interfaces sequentially according to the modified task number and execution content to complete the operation. Therefore, by manually reviewing and optimizing the new solution, the potential for insufficient scenario coverage when the agent generates suggestions is compensated for, ensuring that the final executed solution is both practical and operable, while retaining the flexibility and innovation of the new solution.
[0107] Through steps S901 to S902, for new orchestration suggestions lacking historical experience support, the system clarifies risk points through execution prompts, guides professional personnel to review the proposals, and allows for iterative optimization by reserving room for modification. This logic avoids blindly executing new work order handling solutions, ensuring the safety and accuracy of operation and maintenance, while fully leveraging the supplementary role of human experience. This makes the new solutions generated by the intelligent agent more aligned with real-world scenarios, effectively solving the challenges of implementing new and special work orders and achieving a balance between innovation and reliability.
[0108] Figure 10 This is a flowchart of the integrated operation and maintenance tool and the method for building a work order knowledge base according to embodiments of this application, such as... Figure 10 As shown, in one implementation, the method further includes: integrating the operation and maintenance tool interface using a function call module, converting the enterprise interface document into a function call format, and integrating the interface into the intelligent agent application through interface registration. Therefore, the operation and maintenance tool is integrated.
[0109] In one exemplary implementation, the interface registration module is designed as follows:
[0110] Collect open API information for operation and maintenance tools, including URL, payload, headers, authorization, etc.; write interface call template functions, which include: scenario definition, parameter definition, URL call function, and result output definition. The result output needs to filter out empty fields. Integrate new tool information (scenario definition, parameter definition, URL call function, and result output definition) according to the requirements of the template function to construct a function that the agent can call; for newly registered tools, store the new tool information in a vector knowledge base, using the scenario description as the retrieval field and other information as metadata.
[0111] like Figure 10 As shown, in one implementation, the method further includes: using a multimodal vector model to transform the enterprise's historical work order processing experience into vector representations. The knowledge types include documents, images, etc. Specifically, the multimodal vector model (bge-visualized-m3) is used to convert documents and images into vectors, which are then stored in the vector knowledge base chromadb. Thus, a work order knowledge base is constructed.
[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by adding necessary general-purpose hardware platforms with the aid of software. Of course, they can also be implemented using hardware, but in many cases, the former is a better implementation method. Based on this understanding, the technical solutions of the embodiments of this application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the embodiments of this application.
[0113] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.
[0114] This application also provides a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when it is run.
[0115] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.
[0116] This application also provides an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.
[0117] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.
[0118] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.
[0119] Specific examples in the embodiments of this application can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.
[0120] Obviously, those skilled in the art should understand that the modules or steps of the embodiments of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of this application are not limited to any particular combination of hardware and software.
[0121] The above description is merely a preferred embodiment of the present application and is not intended to limit the embodiments of the present application. For those skilled in the art, various modifications and variations can be made to the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the embodiments of the present application should be included within the protection scope of the embodiments of the present application.
Claims
1. A method for processing work orders in enterprise IT service management, characterized in that, include: The work order analysis agent obtains analysis results based on the content of the work orders to be processed, and classifies and sorts the work orders to be processed based on the analysis results to obtain classification results and sorting results; wherein, the analysis results include: scope of action, subject of action, environment, and flow status; The agent generates action recommendations based on the analysis results; wherein, the action recommendations include: historical orchestration recommendations and new orchestration recommendations. The work order dispatching agent determines the work order handler based on the classification results, the sorting results, and personnel information, sends the handling suggestions to the work order handler, and generates an execution prompt. The action agent executes the action suggestion in response to the confirmation result of the action prompt.
2. The method according to claim 1, characterized in that, The work order dispatching agent determines the work order handler based on the classification results, the sorting results, and personnel information, including: Configuration of the interface for generating personnel information based on the classification results; Personnel information is obtained based on the personnel information interface; wherein, the personnel information includes: area of responsibility, skill coverage, and workload status; The classification results, the sorting results, and the personnel information are matched to determine the person responsible for processing the work order.
3. The method according to claim 1, characterized in that, The agent generates action recommendations based on the analysis results; wherein, the action recommendations include: orchestration recommendations for executing historical data and new orchestration recommendations for executing new data; including: Based on the analysis results, the work order knowledge base is retrieved to determine the handling recommendations based on whether there are historical handling experiences in the work order knowledge base that correspond to the analysis results. If there is historical handling experience corresponding to the analysis results in the work order knowledge base, the first handling arrangement corresponding to the historical handling experience is determined as the historical arrangement suggestion; If no historical handling experience corresponding to the analysis results exists in the work order knowledge base, a second handling arrangement is generated to determine the second handling arrangement as a new arrangement suggestion.
4. The method according to claim 3, characterized in that, If historical handling experience corresponding to the analysis results exists in the work order knowledge base, the first handling arrangement corresponding to the historical handling experience is determined as a historical arrangement suggestion, including: Analyze the matching degree between the analysis results and historical handling experience; When there are multiple matching values, the first treatment arrangement corresponding to the historical treatment experience with the highest matching value is selected. The first disposal arrangement is determined to be a historical arrangement suggestion.
5. The method according to claim 3, characterized in that, If no historical handling experience corresponding to the analysis results exists in the work order knowledge base, a second handling arrangement is generated to determine the second handling arrangement as a new arrangement suggestion, including: Based on the analysis results, several treatment experiences related to the analysis results are obtained; A second disposal arrangement is generated based on the aforementioned multiple disposal experiences, and this second disposal arrangement is identified as a new arrangement recommendation.
6. The method according to claim 1, characterized in that, The action execution agent executes the action suggestion in response to the confirmation result of the execution prompt, including: If the proposed action is a historical orchestration suggestion, an execution prompt is generated to indicate whether to execute the action directly. The historical orchestration suggestion includes: task number, task description, task execution content, and historical experience tags. If the confirmation result of the execution prompt is to execute directly, the historical orchestration suggestions are executed sequentially based on the task sequence number.
7. The method according to claim 5, characterized in that, The action execution agent executes the action suggestion in response to the confirmation result of the execution prompt, including: If the proposed action is a new orchestration suggestion, an execution prompt is generated to review and modify the new orchestration suggestion; wherein, the new orchestration suggestion includes: task number, task description, task execution content, and non-historical experience tags; If the confirmation result of the execution prompt is "confirm execution after review and modification", then execute the new arrangement suggestion after review and modification.
8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is executed by a processor to perform the method described in any one of claims 1 to 7.
9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method of any one of claims 1 to 7.
10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the method of any one of claims 1 to 7.