A method for operating a ticket system and a related device

Abstract

The embodiment of the application provides a kind of dialog operation method and related equipment for work order system, belong to intelligent operation technology field.The method includes obtaining operation task type by carrying out intention recognition to user input text;According to operation task type, operation process is obtained by action arrangement, and the operation process includes multiple action steps with execution sequence;For each action step of operation process, the execution data of the action step is extracted according to the implementation of user input text, and the operation entrance of action step is generated, to obtain the action plan structure data of each action step;According to the execution sequence indicated by operation process and multiple action plan structure data, operation execution list for indicating operation work order system is obtained.The operation execution list of the scheme directly carries the operation entrance of each action step, and the corresponding action can be realized by executing the operation entrance that has been checked by rule and whitelist, so as to improve the operation efficiency of work order system and reduce error rate.

Description

Technical Field

[0001] This application relates to the field of intelligent operation and maintenance technology, and in particular to a conversational operation method and related equipment for a work order system. Background Technology

[0002] A work order system is a core software platform for modern enterprises to record, process, and track the completion of customer requests or internal tasks. It transforms previously scattered and disorganized customer inquiries or internal tasks into traceable units (i.e., work orders) with unique numbers, clear statuses, and complete processing histories, thereby significantly improving customer satisfaction and internal operational efficiency. Currently, work order systems integrate various functions, including but not limited to work order creation, work order data querying, data analysis and reporting, and email notifications. When users complete a task using a work order system, they typically need to rely on their own experience to write query statements and summarize data, a complex process that is inefficient and prone to errors. In related technologies, with the development of conversational language models, users can ask these models how to operate the work order system. However, these models usually only return a general text description of how to operate the system, still requiring users to manually operate the system according to this description, which remains inefficient and error-prone. Summary of the Invention

[0003] The main objective of this application is to propose a dialog-based operation method and related equipment for work order systems, aiming to improve the operational efficiency of work order systems and reduce error rates.

[0004] To achieve the above objectives, one aspect of this application proposes a dialog-based operation method for a work order system, comprising the following steps:

[0005] Get the user's input text; The user input text is subjected to intent recognition to obtain the operation task type; The operation flow is obtained by arranging actions according to the operation task type; the operation flow includes multiple action steps with an execution order. For each action step in the operation process, the data on the basis for the execution of the action step is extracted from the user input text, and an operation entry point for the action step is generated. The operation entry point is then validated by rules and whitelists to obtain an executable operation entry point, thereby obtaining the action plan structure data for each action step. Based on the execution sequence indicated by the operation process and multiple action plan structure data, an operation execution list is obtained to indicate the operation work order system.

[0006] In some embodiments, generating the operation entry point for implementing the action step includes the following steps: Determine whether the action type of the action step is a query type; When the action type is a query type, a first verification operation is performed based on the execution basis data of the action steps to obtain a first verification result; If the first verification result indicates that the action step is passed, an executable operation entry point is generated.

[0007] In some embodiments, the dialogic operation method for a work order system further includes the following steps: The text analysis actions in the operation execution list will be executed to obtain intermediate manuscript data; the intermediate manuscript data includes manuscript conclusions, operation entry points for corresponding action steps, execution basis data, and inference evidence; A second verification operation is performed on the manuscript conclusions based on the intermediate manuscript data to obtain a second verification result. If the second verification result indicates failure, the corresponding operation entry for the action step will be deleted or marked as unexecutable in the operation execution list, and a summary of the verification reason will be output.

[0008] In some embodiments, the dialogic operation method for a work order system further includes the following steps: If the second verification result indicates failure, a prompt text is generated based on the execution basis data; The prompt text is displayed on the user dialogue page to obtain the adjusted or confirmed execution basis data, and the action plan structure data of the corresponding action steps in the operation execution list is updated according to the newly obtained execution basis data.

[0009] In some embodiments, the dialogic operation method for a work order system further includes the following steps: The work order system is operated according to the operation execution list to obtain the execution result.

[0010] In some embodiments, the dialogic operation method for a work order system further includes the following steps: Obtain the audit requirement identifier for the current session; Based on the audit requirement identifier, a corresponding data storage strategy is adopted to selectively store session data and data during the execution of the operation list.

[0011] To achieve the above objectives, another aspect of this application proposes a conversational operating system for a work order system, comprising: The interactive module is used to obtain user input text; The intent recognition module is used to recognize the intent of the user input text to obtain the operation task type; The action orchestration module is used to orchestrate actions according to the operation task type to obtain an operation flow; the operation flow includes multiple action steps with an execution order. The data analysis and routing module is used to extract the execution basis data of the user input text for each action step of the operation process, generate the operation entry point for the action step, perform rule and whitelist verification on the operation entry point to obtain the executable operation entry point, and then obtain the action plan structure data of each action step. The data integration module is used to obtain an operation execution list for instructing the operation work order system based on the execution sequence indicated by the operation process and multiple action plan structure data.

[0012] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0013] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0015] The embodiments of this application include at least the following beneficial effects: This application provides a conversational operation method, system, electronic device, storage medium, and program product for a work order system. This solution first performs intent recognition on the user's input text to obtain the operation task type, and then orchestrates actions according to the operation task type to obtain an operation flow. This operation flow includes multiple action steps with an execution order. For each action step in the operation flow, the execution basis data for implementing the action step is extracted from the user's input text, and an operation entry point for the action step is generated, obtaining action plan structure data for each action step. Then, based on the execution order indicated by the operation flow and the multiple action plan structure data, an operation execution list for instructing the operation of the work order system is obtained. The operation execution list of this solution directly carries the operation entry point for each action step. Executing this operation entry point, which has been verified by rules and a whitelist, can realize the corresponding action, enabling users to improve the efficiency of operating the work order system and reduce the error rate. Attached Figure Description

[0016] Figure 1 This is a flowchart of a dialog-based operation method for a work order system provided in an embodiment of this application; Figure 2 This is an overall flowchart of the dialog-based operation of the work order system provided in the embodiments of this application; Figure 3 This is a system architecture diagram provided in the embodiments of this application; Figure 4 This is a flowchart of the query link and security guardrail provided in the embodiments of this application; Figure 5 This is a flowchart of the export chain provided in the embodiments of this application; Figure 6 This is a flowchart of the email sending process provided in an embodiment of this application; Figure 7 This is a flowchart of the dispatch recommendation analysis provided in the embodiments of this application; Figure 8 This is a flowchart of the report generation process provided in an embodiment of this application; Figure 9 This is a flowchart of the hierarchical memory retrieval injection and generation audit process provided in the embodiments of this application; Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0019] This application provides a dialog-based operation method and related equipment for a work order system. This solution can improve the operation efficiency of the work order system and reduce the error rate.

[0020] The conversational operation method for a work order system provided in this application relates to the field of intelligent operation and maintenance technology. This conversational operation method for a work order system can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the conversational operation method for a work order system, but is not limited to the above forms.

[0021] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0022] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0023] Figure 1This is an optional flowchart of a dialog-based operation method for a work order system provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0024] S101, Obtain user input text; S102, Perform intent recognition on the user input text to obtain the operation task type; S103, Arrange actions according to the type of operation task to obtain the operation flow; the operation flow includes multiple action steps with an execution order. S104, for each action step in the operation process, extract the execution basis data of the user input text to realize the action step, generate the operation entry to realize the action step, perform rule and whitelist verification on the operation entry to obtain the executable operation entry, and then obtain the action plan structure data of each action step. S105. Based on the execution sequence indicated by the operation process and multiple action plan structure data, obtain the operation execution list for instructing the operation work order system.

[0025] In the embodiments of this application, steps S101 to S105 are shown. The operation execution list of this application embodiment directly carries the operation entry for each action step. Executing the operation entry can directly realize the corresponding action, so that users can improve the operation efficiency of the work order system and reduce the error rate.

[0026] In step S101 of some embodiments, the system may provide a user dialogue page to the user, who then engages in a dialogue with the system regarding the work order system, obtaining user input text. The dialogue method can be text or speech-to-text. For example, the user input text may be "Query the current handler of XX work order", "Export XX category work orders from the past week", "Generate an email for XX work order", etc.

[0027] In step S102 of some embodiments, intent recognition is performed on the user input text to obtain the operation task type. Intent recognition can be implemented using a deep learning-based neural network model. For example, the operation task type obtained through intent recognition may be querying data, exporting files, sending emails, generating reports, or dispatching orders, etc.

[0028] In step S103 of some embodiments, actions are orchestrated according to the identified operation task type to obtain an operation flow. The operation flow includes multiple action steps with an execution order. Specifically, action orchestration can be achieved by querying the operation knowledge base of the work order system, which stores the operation flows for completing each task. The knowledge base can represent the operation flow of each task in the form of a directed graph. Each node in the directed graph represents an action step, and the edges between nodes represent the next action step. Representing each operation flow using a directed graph can save storage space and facilitate the expansion and querying of operation flows. By querying the knowledge base according to the operation task type to perform action orchestration, the corresponding operation flow can be obtained. The action steps in the operation flow can be a certain operation action of the work order system (such as "edit text", "list selection", etc.) or a certain atomic capability (such as "login service", "page crawling", etc.).

[0029] In step S104 of some embodiments, for each action step in the operation process, the execution basis data for implementing the action step is extracted from the user input text. Specifically, after obtaining the user input text, the user input text can be standardized first, and key elements such as time range, object, and conditions can be extracted. Then, relevant data is extracted from the user input text processed according to the execution basis data required for the action step. The execution basis data refers to the key parameters required to execute the action step, such as work order number, time range, and filtering conditions. Further, an operation entry point for the action step is generated based on the execution basis data, and an executable operation entry point is obtained after rule and whitelist verification. The operation entry point can be a resource locator (URL) or a call entry point carrying atomic capabilities with call parameters. This operation entry point is used to complete the action step, that is, the user or system can automatically access the operation entry point to realize the action step. The action plan structure data for each action step includes the execution basis data and operation entry point extracted above. Furthermore, the action plan structure data may also include the step number of the action step in the operation process, the action type (query / export / generate / send / jump), the step dependency, whether it is read-only data, whether the operation entry point requires secondary confirmation, and the expected entry point type generated by the step (jump / download / edit).

[0030] In step S105 of some embodiments, an operation execution list for instructing the operation work order system is obtained based on the execution order indicated by the operation flow and multiple action plan structure data. In one example, the system can return the operation execution list to the user's dialogue page, specifically in a structured form of "text reply + evidence + executable entry point," allowing the user to complete the task they want to perform through the operation entry points in the operation execution list. In another example, the system can automatically operate the work order system according to each operation entry point in the operation execution list, directly completing the task the user wants to achieve. In this embodiment, the system first generates an "action plan" and then executes it; that is, the system breaks down the intent into a list of executable steps and clarifies the sequence and dependencies, supporting the chaining of multiple actions (query → export → generate → send). Furthermore, in this embodiment, the dialogue does not only "answer" but "gives actions," meaning that each output simultaneously provides an executable operation entry point (jump / download / edit), allowing the result to be immediately implemented and executed.

[0031] In some embodiments, the operation entry point for generating the action step in step S104 may include, but is not limited to, the following steps: S201, Determine whether the action type of the action step is a query type; S202, when the action type is query type, perform the first verification operation based on the data on which the action steps are executed, and obtain the first verification result; S203, if the first verification result indicates that the action step is passed, generate an executable operation entry point.

[0032] In this embodiment, the execution basis data includes key parameters and user ID. The first verification operation is a security check, which may include, but is not limited to, checking user permissions, checking read-only scope, returning row count verification, and abnormal risk verification (such as untrusted device, untrusted network, etc.). A first verification result indicating success is obtained when all checks are passed; otherwise, a first verification result indicating failure is obtained. If the first verification result indicates success, an executable operation entry point for the action step is generated; otherwise, no operation entry point is generated, or the generated operation entry point is marked as unexecutable or empty, preventing the user or system from executing the risky action step. Furthermore, if the action plan structure data of the action step requires secondary confirmation, the first verification operation may also include a secondary confirmation verification, which refers to the need for manual review of the execution of the action step by an auditor. This embodiment improves the system's data security by performing security verification on data query-type action steps.

[0033] Directly generating database query statements may pose security risks such as exceeding privileges, misoperation, or causing system performance problems. To further improve system data security, this embodiment limits query-type action steps to "read-only action plans" to avoid the risk of misoperation by "generating and executing". It strictly limits the tables, fields, number of rows, and sorting methods that can be accessed, and does not allow direct writing or exceeding privileges.

[0034] In some embodiments, the dialogic operation method for a work order system according to this application may also include, but is not limited to, the following steps: S301, The action steps related to text analysis in the operation execution list are to be executed to obtain intermediate manuscript data; the intermediate manuscript data includes manuscript conclusions, operation entry points for corresponding action steps, execution basis data, and inference evidence; S302, Perform a second verification operation on the manuscript conclusions based on the intermediate manuscript data to obtain the second verification result; S303 If the second verification result indicates that the operation entry of the corresponding action step is not executed, the operation entry of the corresponding action step will be deleted or marked as unexecutable in the operation execution list, and a summary of the verification reason will be output.

[0035] In this embodiment, the system can first attempt to execute the text analysis actions in the operation execution list. These actions involve performing algorithmic inference on the input content, such as email content generation or order placement recommendations. This text analysis can be implemented based on a large language model. "Planned execution" means executing the text analysis actions to obtain intermediate draft data, but without outputting the results to the user or applying them to the work order system; that is, the results of the planned execution do not have any practical effect. By first attempting to execute the text analysis actions to obtain intermediate draft data for the inference process, and then performing a self-check on this intermediate draft data, the system can then formally provide users with executable operation entry points or execution procedures, thereby improving the reliability of the work order system operation.

[0036] The intermediate draft data in this embodiment may include draft conclusions (such as the generated draft content, order recommendation results, or analysis conclusions of data reports), operation entry points for corresponding action steps, execution basis data (i.e., key parameters), and inferred evidence (such as evidence preview summaries). The second verification operation can be a self-checking operation. After generating intermediate draft data, the system combines "draft conclusions, proposed executable entry points, key parameters, and evidence preview summaries" into information to be verified. Through the self-checking operation, it can output "whether it passes, risk level, and handling suggestions (release / downgrade / block / prompt for supplementary information)," etc.

[0037] In one example, the self-check operation verifies at least three types of consistency: ① whether the assertion is consistent with the entry point (key parameters such as entry point type, work order number, and time range are consistent); ② whether the assertion is consistent with the evidence (the evidence can support the conclusion); ③ whether the entry point source is traceable (the entry point URL must come from the work order link / export preview / explicit link, and comply with the allowed types and domain / path rules).

[0038] In one example, the handling methods corresponding to the self-check operation (i.e., the second verification operation) are as follows: if it fails, the system does not directly provide an executable operation entry (e.g., deletes the corresponding operation entry of the action step in the operation execution list or marks it as non-executable); if it passes, the system directly provides the executable operation entry of the action step in the operation execution list. Further, according to the set verification rules, if the second verification operation indicates a slight inconsistency, when providing feedback to the user, a textual response can be retained, but the entry can be downgraded to non-executable or marked as requiring review. For example, a guaranteed failure (blocking) includes inconsistent work order numbers, inconsistent time ranges, entry domain names or paths not within the allowed range, and entry points that cannot be generated from evidence or templates; slight inconsistencies (downgrade) include conclusions that are not rigorous enough but the evidence matches the entry point, or sufficient evidence but the entry point lacks necessary parameters (e.g., a missing ID), in which case only an evidence preview is provided without an executable entry point. The specific handling methods for the self-check operation can be set at different levels according to requirements, and this application embodiment does not impose specific limitations.

[0039] In some embodiments, the dialogic operation method for a work order system according to this application may also include, but is not limited to, the following steps: S401, if the second verification result indicates that the verification failed, generate a prompt text based on the execution basis data; S402, display prompt text on the user dialogue page to obtain the adjusted or confirmed execution basis data, and update the action plan structure data of the corresponding action steps in the operation execution list according to the newly obtained execution basis data.

[0040] In this embodiment, if the self-check of intermediate draft data fails, a prompt text can be generated based on the execution basis data and displayed on the user's dialog page. This prompt text prompts the user to narrow down the scope, add conditions, or reconfirm. For example, in a task assignment recommendation, if a user wants to find an employee in the management department to handle maintenance work, and the self-check determines that there are no maintenance personnel in the management department, a prompt text composed of execution basis data such as "management department" and "maintenance work" can be displayed to the user, prompting the user to modify the execution basis data, such as adding "maintenance department" as the execution basis data. The system obtains the adjusted or confirmed execution basis data and updates the action plan structure data of the corresponding action steps in the operation execution list based on the newly obtained execution basis data, improving the reliability of the subsequent operation work order system.

[0041] In some embodiments, the dialogic operation method for a work order system according to this application may also include, but is not limited to, the following steps: S501: Perform operations on the work order system according to the operation execution list and obtain the execution results.

[0042] In this embodiment, the work order system is operated according to the operation execution list to obtain the execution result, such as performing queries, page redirects, exporting, or generating content according to plan. This can automatically complete the user's desired operation tasks. Specifically, the system can first display the operation execution list on the user's dialog page, and after the user confirms the operation execution list, the entire operation process is executed to obtain the execution result. The system then provides feedback on whether the execution was successful or failed on the user's dialog page. The execution result may also include intermediate manuscript data generated by the relevant action steps. Saving the execution result facilitates subsequent review or self-inspection.

[0043] This embodiment avoids accidental operations and unauthorized access by performing permission and read-only checks and limiting the number of rows before execution, and performing consistency checks after execution. For query-type operations, only reading data within a limited scope is allowed, while writing and high-risk operations are prohibited.

[0044] In some embodiments, the dialogic operation method for a work order system according to this application may also include, but is not limited to, the following steps: S601, Obtain the audit requirement identifier for the current session; S602, based on the audit requirement identifier, adopt the corresponding data storage strategy to selectively store session data and data during the execution of operation checklists.

[0045] In this embodiment, each execution result provides verifiable preview / evidence and other data, and the relevant data of each session and execution process are selectively stored in the database according to the audit switch, such as selectively recording data such as trace_id, input summary, action plan summary, evidence summary and entry summary, so as to facilitate playback and traceability.

[0046] Specifically, the system pre-configures an audit switch, policy number, and version number. When the audit switch is enabled (i.e., the audit requirement indicator indicates that auditing is required), the system generates a trace_id for each session and writes the policy number / version number into the current audit record for easy playback by version. Specifically, it may record the trace_id, session identifier, user input summary, evidence summary, entry point summary, self-inspection conclusion, and final handling result (allow / downgrade / block), and record the policy number and version number. Fields are saved in text / JSON digest format for easy playback and review. When the switch is disabled (i.e., the audit requirement indicator indicates that auditing is not required), no information is recorded, or only the minimum necessary information is recorded. The minimum necessary information can be set according to actual needs, such as only retaining the final output summary and necessary error codes / risk levels for this session, without recording evidence and entry point details. In this embodiment, when the audit switch is enabled, the system can replay the "input summary, action plan summary, evidence summary, entry point summary, and handling result" by trace_id, facilitating auditing of self-inspection operations. During the audit process, the system can encapsulate the output structure for the audit terminal, generate evidence previews, and record retrieval hits, action plans, and execution results.

[0047] This embodiment binds a policy number and a version number to each output and can enable auditing as configured, thereby supporting subsequent playback and review by version and avoiding the problem of not being able to interpret historical results after policy iteration.

[0048] In some embodiments, the dialogic operation method for a work order system according to this application may also include, but is not limited to, the following steps: The historical information in the current conversation is filtered to obtain the user input text.

[0049] This embodiment uses a memory guardrail mechanism to retrieve only the "currently needed historical information" from long conversations, saves the conversation context, and retrieves and filters historical information as needed to avoid old information interfering with new decisions.

[0050] In this embodiment, when the output of the relevant algorithm model (such as the large language model) in the system is unstable, it automatically switches to the rule flow to ensure that the results are stable and usable.

[0051] According to some embodiments of this application, please refer to Figure 2The flowchart shown in the diagram illustrates the overall operation process of the dialogue-based work order system. After preprocessing user input, intent recognition is performed. Based on the operation task type identified by the intent, actions are orchestrated to determine each action step. The system then routes the corresponding capability links based on these action steps and executes them securely. The execution results are then self-checked, and relevant data is encapsulated based on the self-check and execution results. Finally, the encapsulated data is stored in the database for statistical analysis. In this embodiment, the user only needs to describe their intent. The system first understands the user's intent, then breaks it down into executable action steps. Security checks are performed before execution, and after execution, results, evidence, and executable entry points are provided. The entire process is recorded and self-checked.

[0052] This application also provides a dialog-based operating system for work order systems, including: The interactive module is used to obtain user input text; The intent recognition module is used to recognize the intent of user input text and obtain the operation task type; The action orchestration module is used to orchestrate actions according to the type of operation task to obtain the operation flow; the operation flow includes multiple action steps with an execution order. The data analysis and routing module is used to extract the execution basis data of the user input text for each action step in the operation process, generate the operation entry point for the action step, perform rule and whitelist verification on the operation entry point to obtain the executable operation entry point, and then obtain the action plan structure data for each action step. The data integration module is used to generate an operation execution list for instructing the operation work order system based on the execution sequence indicated by the operation process and multiple action plan structure data.

[0053] It is understood that the methods described in the above method embodiments are applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0054] According to some embodiments of this application, the solutions of this application can be applied to the following system architectures, please refer to... Figure 3 The system architecture diagram shown mainly includes the following parts: Interaction module: Receives user requests and displays results, evidence, and execution entry points.

[0055] The parsing and routing module extracts key elements and routes requests to the corresponding capabilities.

[0056] Action orchestration module: Breaks down intents into action plans, handles the order and dependencies, and outputs an executable list.

[0057] Security Execution Module: Performs unified permission verification, read-only verification, line count limit, and timeout control.

[0058] Data acquisition and page operation module: Completes actions such as work order query, page redirection, export and download.

[0059] Content generation module: Generates editable content such as email drafts and report summaries.

[0060] Self-checking module: performs consistency checks on intermediate drafts, outputs conclusions only, and does not directly rewrite the data.

[0061] Memory management module: Saves the dialogue context and allows for the retrieval and filtering of historical information as needed.

[0062] Policy and audit configuration: The system pre-configures the audit switch, policy number, and version number; when the switch is turned on, the system generates a trace_id for each session and writes the policy number / version number into the current audit record for easy playback by version.

[0063] The results encapsulation and auditing module encapsulates the output structure, generates evidence previews, and records search hits, action plans, and execution results.

[0064] According to some embodiments of this application, the following problems that are prone to occur in work order systems in related technologies are addressed: Data processing is both technically demanding and error-prone: Statistical analysis and trend forecasting rely on professionals writing database queries, which presents significant technical challenges and security risks. Manually compiling data and composing emails is prone to omissions and errors, and lacks a traceable chain of evidence.

[0065] Lack of intelligent decision support: Decisions such as order dispatch often rely on human experience and it is difficult to comprehensively consider explanatory evidence such as process constraints, historical efficiency and real-time load.

[0066] This embodiment automatically converts user requests into executable actions such as work order query, page redirection, data export, email generation and sending, work order recommendation and report generation through natural language dialogue interaction, which can complete each process efficiently and reliably.

[0067] Example 1: Please search Figure 4 The query path and safety barrier process shown demonstrate how the system enables quick querying of single work order fields. The user inputs "Query the current handler of a specific work order." The system recognizes the field query, locates the work order, and returns the field values ​​and a link to the work order, allowing the user to access the processing page with a single click.

[0068] Example 2: The system implements conditional filtering queries and a results table preview. Users input "select a number of work orders from the last 7 days whose titles contain a specific keyword." The system generates a read-only query based on the conditions, returns the table header and several preview rows as evidence, and provides a download link.

[0069] Example 3: Please refer to Figure 5 The export process shown demonstrates how the system exports a list and allows for previewing and downloading. The user inputs "Export work orders of a specific category from the past week." The system generates an action plan (Filter → Export → Generate File), executes it, and then returns an entry point for file preview and download.

[0070] Example 4: Please refer to Figure 6 The email sending process shown demonstrates how to generate and send an email draft. The user inputs "Generate an email for a certain work order." The system retrieves the work order and attachment information, generates a draft, provides an editing interface, and sends the email after user confirmation.

[0071] Example 5: Please refer to Figure 7 The dispatch recommendation and analysis process shown demonstrates how the system recommends dispatch orders. The user inputs "Analyze who is most suitable to dispatch this work order next." The system combines process rules, historical efficiency, and current load to output recommendations and justifications. If the model is unavailable, the system uses the rules as a fallback.

[0072] Example 6: Please refer to Figure 8 The report generation process shown demonstrates how the system generates daily and weekly reports. The user inputs "Generate today's daily work order report." The system then summarizes and compiles the data, generating a summary and report, and providing preview and download options.

[0073] Example 7: The system implements multi-turn dialogue and contextual memory (memory railing). The user first enters "Filter completed work orders from the past week", then enters "View only event-type work orders", and then enters "Generate email for the first ten". The system only retrieves historical information relevant to the current task, forms a series of actions, and outputs the results.

[0074] Example 8: The system implements self-check blocking and prompts for review. The user inputs "Export historical work orders and send them directly to XXX email address." The system identifies a risk, issues a "fail" conclusion during the self-check, and prompts the user to adjust the scope or perform a second confirmation to prevent errors from being implemented.

[0075] Example 9: Please search Figure 9The layered memory retrieval injection and generation audit process shown in the diagram enables system audit playback and review. When a user reports "The data in this table is inconsistent," the system replays the input, retrieval hits, and execution results based on the audit logs, identifies the discrepancies, and provides correction suggestions.

[0076] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0077] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0078] Please see Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901. The 903 input / output interface is used to implement information input and output. The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0079] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0080] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0081] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0082] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0083] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] This application provides a dialog-based operation method and related equipment for a work order system, which has at least one of the following beneficial effects: Lowering the barrier to entry: Even people unfamiliar with the system can complete complex operations through dialogue.

[0085] Improve efficiency: Reduce time spent switching pages and manually organizing data.

[0086] Verifiable: The results include evidence previews and executable entry points, facilitating verification and secondary operations.

[0087] More secure: Verification and restrictions are in place before and after execution to prevent accidental operations and unauthorized access.

[0088] Traceable: The entire process is recorded, facilitating playback and accountability.

[0089] Explainable and implementable: Order dispatch and recommendation are based on established criteria, and rules can be used as a fallback when the model is unstable.

[0090] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0091] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0092] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0094] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0095] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0096] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0097] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0099] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0100] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A dialog-based operation method for a work order system, characterized in that, Includes the following steps: Get the user's input text; The user input text is subjected to intent recognition to obtain the operation task type; The operation flow is obtained by arranging actions according to the operation task type. The operation process includes multiple action steps with an execution sequence; For each action step in the operation process, the data on the basis for the execution of the action step is extracted from the user input text, and an operation entry point for the action step is generated. The operation entry point is then validated by rules and whitelists to obtain an executable operation entry point, thereby obtaining the action plan structure data for each action step. Based on the execution sequence indicated by the operation process and multiple action plan structure data, an operation execution list for instructing the operation work order system is obtained; The work order system is operated according to the operation execution list to obtain the execution result; Obtain the audit requirement identifier for the current session; Based on the audit requirement identifier, a corresponding data storage strategy is adopted to selectively store session data and data during the execution of the operation list.

2. The dialogic operation method for a work order system according to claim 1, characterized in that, The process of generating the operation entry point for implementing the action steps includes the following steps: Determine whether the action type of the action step is a query type; When the action type is a query type, a first verification operation is performed based on the execution basis data of the action steps to obtain a first verification result; If the first verification result indicates that the action step is passed, an executable operation entry point is generated.

3. The dialogic operation method for a work order system according to claim 1, characterized in that, The dialogic operation method for the work order system also includes the following steps: The text analysis actions in the operation execution list will be executed to obtain intermediate manuscript data; the intermediate manuscript data includes manuscript conclusions, operation entry points for corresponding action steps, execution basis data, and inference evidence; A second verification operation is performed on the manuscript conclusions based on the intermediate manuscript data to obtain a second verification result. If the second verification result indicates failure, the corresponding operation entry for the action step will be deleted or marked as unexecutable in the operation execution list, and a summary of the verification reason will be output.

4. The dialogic operation method for a work order system according to claim 3, characterized in that, The dialogic operation method for the work order system also includes the following steps: If the second verification result indicates failure, a prompt text is generated based on the execution basis data; The prompt text is displayed on the user dialogue page to obtain the adjusted or confirmed execution basis data, and the action plan structure data of the corresponding action steps in the operation execution list is updated according to the newly obtained execution basis data.

5. A conversational operating system for a work order system, characterized in that, include: The interactive module is used to obtain user input text; The intent recognition module is used to recognize the intent of the user input text to obtain the operation task type; The action orchestration module is used to orchestrate actions according to the operation task type to obtain the operation flow; The operation process includes multiple action steps with an execution sequence; The data analysis and routing module is used to extract the execution basis data of the user input text for each action step of the operation process, generate the operation entry point for the action step, perform rule and whitelist verification on the operation entry point to obtain the executable operation entry point, and then obtain the action plan structure data of each action step. The data integration module is used to obtain an operation execution list for instructing the operation work order system based on the execution order indicated by the operation process and multiple action plan structure data; The dialogic operating system for the work order system is also used for: The work order system is operated according to the operation execution list to obtain the execution result; Obtain the audit requirement identifier for the current session; Based on the audit requirement identifier, a corresponding data storage strategy is adopted to selectively store session data and data during the execution of the operation list.

6. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 4.

Images