Task work order generation method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention discloses a task work order generation method and device, a storage medium and electronic device.The method comprises the steps that in response to an automatic work order generation request input by a user to a target agent object, input work order material information is obtained, a work order task processing workflow for the user is determined based on the work order material information, and the work order task processing workflow is generated according to the determined work order task processing workflow. And extracting work order parameter field information from the work order material information according to the work order task processing workflow by adopting a work order processing large model, and carrying out work order generation processing by adopting the work order parameter field information in a working platform to obtain a target task work order, and outputting the target task work order and work order creation prompt information to a user based on the target agent object.

Description

Technical Field

[0001] The present invention relates to the field of digital data processing technology, and in particular to a method, device, storage medium and electronic device for generating a task work order. Background Art

[0002] In modern enterprise management, task tickets are a key service support tool responsible for efficiently processing and tracking transaction-related requests and issues. In order to ensure that the system can accurately and promptly process various types of tickets, it is necessary to finely manage the ticket processing process. The traditional method is to manually create task tickets. However, on the operation and maintenance side, users create task tickets many times to complete daily operation and maintenance needs. The manual creation of task tickets requires following certain work order creation standards, and the work order creation process is long and complicated, resulting in the problems of high complexity, long time, and inconvenience of manually creating work orders. Summary of the invention

[0003] The embodiments of this specification provide a method, device, storage medium and electronic device for generating a task work order, and the technical solution is as follows: In a first aspect, an embodiment of the present specification provides a method for generating a task work order, the method comprising: In response to a work order automatic generation request input by a user to a target agent object, the input work order material information is obtained, and a work order task processing workflow for the user is determined based on the work order material information; Using the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow, and using the work order parameter field information to perform work order generation processing in the work platform to obtain the target task work order; The target task work order and work order creation prompt information are output to the user based on the target agent object.

[0004] In a second aspect, an embodiment of the present specification provides a task work order generation device, the device comprising: A request processing module, configured to respond to a work order automatic generation request input by a user to a target agent object, obtain the input work order material information, and determine a work order task processing workflow for the user based on the work order material information; A work order generation module, used to extract work order parameter field information from the work order material information according to the work order task processing workflow using a work order processing large model, and to perform work order generation processing using the work order parameter field information in a work platform to obtain a target task work order; An information output module is used to output the target task work order and work order creation prompt information to the user based on the target intelligent agent object.

[0005] In a third aspect, an embodiment of the present specification provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0006] In a fourth aspect, an embodiment of the present specification provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0007] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least: In one or more embodiments of the present specification, the electronic device responds to the work order automatic generation request input by the user to the target intelligent agent object, determines the work order task processing workflow based on the acquired work order material information, uses the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow, and uses the work order parameter field information in the work platform to generate the target task work order, and then outputs the target task work order and the work order creation prompt information to the user based on the target intelligent agent object, thereby avoiding the limitation of manually creating work order tasks, and can realize the automation and intelligence of work order processing according to the work order task processing workflow based on the work order processing large model, significantly improve the efficiency and accuracy of work order creation and processing, can adapt to the changes in business needs for work order task processing, and improve user satisfaction and operation experience. The task work order generation method can not only improve employee work efficiency, but also optimize resource allocation, and enhance overall service quality and management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 This is a scenario diagram of a task work order generation system provided in an embodiment of this specification; Figure 2 It is a flowchart of a method for generating a task work order provided in an embodiment of this specification; Figure 3 It is a flowchart of determining a work order task processing workflow provided by an embodiment of this specification; Figure 4 It is a flowchart of another work order task processing workflow determination provided by an embodiment of this specification; Figure 5It is a schematic diagram of a process of extracting work order parameter field information provided by an embodiment of this specification; Figure 6 It is a structural diagram of a task work order generating device provided in an embodiment of this specification; Figure 7 It is a structural diagram of a request processing module provided in an embodiment of this specification; Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of the structure of the operating system and user space provided in the embodiment of the present application; Fig.10 yes Fig. 9 The architecture diagram of the Android operating system; Fig.11 yes Fig. 9 Architecture diagram of the IOS operating system. DETAILED DESCRIPTION

[0010] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0011] In the description of this specification, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In the description of this specification, it should be noted that, unless otherwise clearly specified and limited, "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. For those of ordinary skill in the art, the specific meanings of the above terms in this specification can be understood by specific circumstances. In addition, in the description of this specification, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are an "or" relationship.

[0012] See also Figure 1 , is a scenario diagram of a task work order generation system provided in this specification. Figure 1 As shown, the task work order generation system may include at least a client cluster and a service platform 100 .

[0013] The client cluster may include at least one client, such as Figure 1 As shown, it specifically includes client 1 corresponding to user 1, client 2 corresponding to user 2, ..., client n corresponding to user n, where n is an integer greater than 0.

[0014] Each client in the client cluster may be an electronic device with communication function, including but not limited to: wearable device, handheld device, personal computer, tablet computer, vehicle-mounted device, smart phone, computing device or other processing device connected to a wireless modem, etc. Electronic devices may be called different names in different networks, such as: user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), electronic devices in 5G network or future evolution network, etc.

[0015] The service platform 100 can be a separate server device, such as a rack-mounted, blade, tower, or cabinet-mounted server device, or a workstation, mainframe computer, or other hardware device with strong computing power; it can also be a server cluster composed of multiple servers, and the servers in the service cluster can be composed in a symmetrical manner, wherein each server has equivalent functions and status in the transaction link, and each server can provide services to the outside independently, and the independent service can be understood as not requiring the assistance of other servers.

[0016] In one or more embodiments of the present specification, the service platform 100 may establish a communication connection with at least one client in the client cluster, and complete the data interaction during the task work order generation process based on the communication connection.

[0017] For example, a user may send an automatic work order generation request inputted for a target agent object to the service platform 100 through a client; For another example, the service platform 100 may respond to a work order automatic generation request input by a user to a target agent object, obtain the input work order material information, determine a work order task processing workflow for the user based on the work order material information, extract work order parameter field information from the work order material information according to the work order task processing workflow using a work order processing large model, and perform work order generation processing using the work order parameter field information in the work platform to obtain a target task work order; For another example, the service platform 100 may generate a work order creation prompt information for the target task work order, and then the service platform 100 sends the work order creation prompt information to the client; For another example, the client may output work order creation prompt information for the target task work order to the user based on the target agent object.

[0018] It should be noted that the service platform 100 and at least one client in the client cluster establish a communication connection through a network for interactive communication, wherein the network can be a wireless network or a wired network, the wireless network includes but is not limited to a cellular network, a wireless local area network, an infrared network or a Bluetooth network, and the wired network includes but is not limited to Ethernet, a universal serial bus (USB) or a controller local area network. In one or more embodiments of the specification, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data (such as a target compressed package) exchanged through the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0019] The task work order generation system embodiment provided in this specification and the task work order generation method in one or more embodiments belong to the same concept. The execution subject corresponding to the task work order generation method involved in one or more embodiments of the specification can be an electronic device, and the electronic device can be the above-mentioned service platform 100; the execution subject corresponding to the task work order generation method involved in one or more embodiments of the specification can also be an electronic device corresponding to the client, which is specifically determined based on the actual application environment. The implementation process of the task work order generation system embodiment can be detailed in the following method embodiment, which will not be repeated here.

[0020] The present specification is described in detail below with reference to specific embodiments.

[0021] In one embodiment, Figure 1As shown, a task work order generation method is proposed, which can be implemented by a computer program and can be run on a task work order generation device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application. The task work order generation device can be an electronic device.

[0022] Specifically, the task work order generation method includes: S102: In response to a work order automatic generation request input by a user to a target agent object, the input work order material information is obtained, and a work order task processing workflow for the user is determined based on the work order material information; In this specification, the target intelligent agent object (which can be regarded as an agent object service) is an intelligent agent service computer program with perception, reasoning, and decision-making based on electronic devices. The target intelligent agent object is the service carrier object of the intelligent agent agent, relying on the work order processing big model in this specification to automatically generate requests for user work orders, provide with the help of the determined work order task processing workflow, use the work order processing big model to gradually process the work order task, propose work order parameter field information, and link the work platform to automatically create the target task work order; Optionally, the target intelligent agent object may be a service control that carries an intelligent agent service and has a task work order generation function. The target intelligent agent object may be integrated into a work transaction application that a user uses daily. The user may trigger the service control corresponding to the target intelligent agent object and enter a work order automatic generation request in the intelligent agent service interface corresponding to the service control. The work order automatic generation request generally includes the work order material information entered by the user for the generation of this task work order. Exemplarily, the target agent object is pre-developed or integrated into the work application used by the user on a daily basis, and then a user interface is configured, through which the user can conveniently input a work order automatic generation request to the target agent object, and in the process of inputting the work order automatic generation request, the user will input the work order material information accordingly; Furthermore, when the user inputs a work order to automatically generate a request for the target intelligent agent object, the work order material information carried in the request is automatically cracked through the target intelligent agent object.

[0023] It should be noted that the information modality of the work order material information is not limited, including but not limited to one or more fittings of text modality information, video modality information, image modality information, etc.; Work order material information usually refers to the original data and content required for creating and processing work orders that are entered by the user in the work order automatic generation request. The work order material information may include requester information, problem description, time information, priority, related equipment or service information, history, status mark, etc. based on the actual user input situation; For example: Requester information: basic information of the user or department that submitted the work order, such as name, department, contact information, etc.

[0024] For example: Problem description: A detailed description of the problem or requirement, which can include text descriptions, pictures, videos, etc., to help better understand and solve the problem.

[0025] For example: Timestamp: The time the ticket was created, and sometimes the expected resolution deadline.

[0026] For example: Priority: Indicates the urgency of the work order, usually divided into high, medium, and low levels.

[0027] For example: Related equipment or service information: If the work order is related to a specific device or service, this information may include the device model, serial number, service type, etc.

[0028] For example: History: If the issue related to the current work order has been processed in the past.

[0029] For example: Status mark: the current processing status of the work order, such as unprocessed, in progress, resolved, etc.

[0030] Illustratively, these work order material information is used to subsequently determine the work order task processing workflow for the user.

[0031] In the embodiments of the present specification, the work order task processing workflow instructs the work order processing big model to design a big model processing flow for a standardized target task work order, and subsequently uses the work order processing big model to gradually extract the work order parameter field information according to the work order task processing workflow, and uses the work order parameter field information in the work platform to perform work order generation processing to obtain the target task work order.

[0032] Specifically, data analysis is performed on the work order material information to determine the target work order task type, and a work order task processing workflow for the user is generated based on the target work order task type; In a feasible implementation manner, user work order requirement information may be extracted from the work order material information, and the target work order task type may be determined based on the user work order requirement information; In a feasible implementation manner, the work order material information may be subjected to intent analysis to obtain the work order processing intent, and the target work order task type may be determined based on the work order processing intent; Optionally, several work order task types are predefined, and different work order task types are defined according to the business needs and common problem types of the enterprise and users. Work order task types include but are not limited to technical support work orders, equipment maintenance work orders, software update requests, etc.

[0033] In a feasible implementation, a general work order task processing workflow is set for each work order task type.

[0034] For example, a general work order task processing workflow may be: 1. distinguishing the material types in the work order material information to determine the material type (such as text type, image type) corresponding to each material; 2. using different material identification methods for different material types to identify the work order parameter information in the material; 3. extracting the work order parameter fields of each work order processing step required for the work order setting from the work order parameter information to obtain the work order parameter field information, calling the work order interface in the work platform to create an initial work order, and writing the work order parameter field information into the initial work order to generate the target task work order; For example, a general work order task processing workflow can be 1. Determine the task assignment information from the work order material information, such as determining which departments or individuals are responsible for handling this type of work order. For example, IT issues are handled by the technical support team, while hardware-related issues are handled by the equipment maintenance team. 2. Set specific work order processing steps for the work order, such as preliminary diagnosis, on-site inspection, problem solving, feedback confirmation, etc. 3. Set a timeline for each work order processing step; 4. Extract the work order parameter field information of each work order processing step required for the work order setting; 5. Call the work order interface in the work platform to create an initial work order, write the work order parameter field information into the initial work order, and then generate the target task work order; S104: extracting work order parameter field information from the work order material information according to the work order task processing workflow using the work order processing large model, and performing work order generation processing using the work order parameter field information in the work platform to obtain a target task work order; Optionally, the work order parameter field information may be the work order parameter field constituting each work order processing step in the task work order; that is, the work order component elements filled in the work order may be determined based on the work order parameter field information.

[0035] In a feasible implementation, the work order processing large model can be obtained by training the model for the task work order generation scenario based on the basic large model. The basic large model (Large Language Model, LLM) is an artificial intelligence content generation model that aims to understand and generate human language. The basic large model is trained on a large amount of data and can perform a wide range of tasks, including text summarization, translation, sentiment analysis, etc.

[0036] Optionally, the basic big model may be the Tongyi Qianwen big model, the Bailing big model, the GPT system big model, etc.; In some embodiments, a trained basic big model can be obtained, and the basic big model can be adapted to the task work order generation scenario to obtain the task work order generation big model. Usually, the basic big model is directly applied to process the work order in the task work order generation scenario, which is difficult to adapt to the new task work order generation scenario. Based on this, the basic big model is first obtained to create an initial task work order generation big model, and sample data is obtained in the new task work order generation scenario. Since the basic big model is usually a trained AIGC model with content generation capabilities, based on this, this specification only needs to adapt it to the task work order generation scenario. Specifically, the sample data can be used to perform model fine-tuning training on the initial task work order generation big model. After the model fine-tuning training is completed, the task work order generation big model adapted to the task work order generation scenario is obtained.

[0037] In one or more embodiments of the present specification, a work order workflow processing prompt word is generated based on the work order task processing workflow, the work order workflow processing prompt word is input into the task work order processing big model, at least one target work order processing step of the work order task processing workflow is parsed by the work order processing big model, and work order parameter field information is extracted from the work order material information based on the target work order processing step, such as the problem type field, the urgency field, the relevant department field, etc., and then the work order processing big model applies the extracted work order parameter field information to the work order generation template in the work platform, and automatically fills in various parts of the work order according to the work order generation template and the work order parameter field information to generate a complete target task work order, thereby completing the step of using the work order parameter field information to perform work order generation processing on the work platform to obtain the target task work order.

[0038] Schematically, the work order workflow processing prompt word is task description information for instructing the work order processing large model to perform task work order generation processing on the work order material information according to one or more target work order processing steps of the work order task processing workflow; In a feasible implementation, the following method can be used to generate a work order using the work order parameter field information in the work platform to obtain a target task work order: A2: Get the work order creation interface of the work platform; A4: Generate a work order creation request based on the work order creation interface and the work order parameter field information, and create a target task work order in the work platform based on the work order creation request using the work order parameter field information.

[0039] The work order processing model obtains the work order creation interface of the work platform, and uses the work order creation interface to create and generate work orders on the work platform; Before deploying the work order processing model, the work order creation interface of the work platform is configured in the function call tool set function_call of the work order processing model. During the model training phase of the work order processing model, the work order creation interface of the work platform is registered in the function call tool set function_call. After the work order processing model is actually deployed online, the work order processing model can call the work order creation interface to use the work order generation template to create an initial task work order of the target work order task type, and then use the work order generation template and the work order parameter field information to automatically fill in various parts of the work order to generate a complete target task work order.

[0040] S106: Outputting the target task work order and work order creation prompt information to the user based on the target intelligent agent object.

[0041] The work order creation prompt information is the confirmation information of the creation status of the target task work order and the display information of the target task work order. For example, the confirmation information of the creation status may be the work order information of successful creation, for example, the confirmation information of the creation status may be the work order information of creation error, etc.; By outputting the target task work order and the work order creation prompt information for the target task work order to the user in the target agent object, the work order creation status can be fed back instantly; In one or more embodiments of the present specification, the electronic device responds to the work order automatic generation request input by the user to the target intelligent agent object, determines the work order task processing workflow based on the acquired work order material information, uses the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow, and uses the work order parameter field information in the work platform to generate the target task work order, and then outputs the target task work order and the work order creation prompt information to the user based on the target intelligent agent object, thereby avoiding the limitation of manually creating work order tasks, and can realize the automation and intelligence of work order processing according to the work order task processing workflow based on the work order processing large model, significantly improve the efficiency and accuracy of work order creation and processing, can adapt to the changes in business needs for work order task processing, and improve user satisfaction and operation experience. The task work order generation method can not only improve employee work efficiency, but also optimize resource allocation, and enhance overall service quality and management efficiency.

[0042] See also Figure 3 , Figure 3 This is a flow chart of determining a work order task processing workflow proposed in this specification. To perform the work order task processing workflow for the user based on the work order material information, the following method can be referred to: S202: extracting user work order requirement information from the work order material information, and determining a target work order task type based on the user work order requirement information; For example, the work order material information is first parsed, and the user work order requirement information is extracted from it using text analysis technology (such as keyword extraction, intent recognition, etc.). The user work order requirement information may include, for example, fault description, type of service requested, expected response time, etc.

[0043] Then, the task type is determined according to the work order requirement information, and the task type of the tool body to be created is determined according to the extracted requirement information, that is, the target work order task type; Optionally, work order keywords may be extracted from the work order requirement information, a first mapping relationship between reference work order keywords and work order task types is preset, and the target work order task type in the first mapping relationship may be queried for the work order keywords; Optionally, a work order task type identification model created based on a machine learning model can be used to identify the work order task type, and the work order requirement information is input into the work order task type identification model to identify the work order task type and output the target work order task type.

[0044] S204: Generate a work order task processing workflow for the user based on the target work order task type.

[0045] In a feasible implementation manner, a general work order task processing workflow corresponding to the target work order task type is acquired, and a work order task processing workflow for the user is obtained based on the general work order task processing workflow.

[0046] According to some embodiments, several work order task types are predefined, and different work order task types are defined according to the business needs and common problem types of enterprises and users. Work order task types include but are not limited to technical support work orders, equipment maintenance work orders, software update requests, etc., and a general work order task processing workflow is set for each work order task type.

[0047] In a feasible implementation, historical data, user-specific preferences, and automated processes can be used to generate a work order task processing workflow, aiming to provide personalized and efficient work order processing services. Figure 4 , Figure 4 This is another flowchart of the work order task processing workflow proposed in this specification. Specifically: S3002: Acquire a general work order task processing workflow corresponding to the target work order task type, and acquire a reference task work order template corresponding to the target work order task type; Pre-saved historical task orders of the same work order task type that have been completed. The historical task orders can be used as reference task order templates for the same work order task type. In actual applications, the general work order task processing workflow corresponding to the target work order task type is obtained, and the reference task work order template corresponding to the target work order task type can also be obtained to assist in the creation of a new work order.

[0048] S3004: Determine a first target work order general processing step from the general work order task processing workflow; Extracting the first target work order general processing steps from the general work order task processing workflow, and according to the obtained general workflow, the system determines the general standard processing steps that should be included; The first target work order common processing steps can be understood as the common processing steps for work orders of the same target work order task type; It should be noted that in this specification, the difference between the second target work order general processing step and the first target work order general processing step is that the processing process involved in the target work order general processing step is different. In the processing process determined by the work order task processing workflow, the target work order general processing step is called the first target work order general processing step, and in the processing process of extracting work order parameter field information, the target work order general processing step is called the second target work order general processing step; For example: common processing steps for target work orders such as preliminary review, problem classification, implementation of problem solutions, etc.

[0049] S3006: determining work order parameter shortage information based on the reference task work order template and the work order material information, and creating a first shortage information interaction processing step for the user based on the work order parameter shortage information; Specifically, use the reference task work order template to extract the necessary general information parameter types, such as work order subject, description, priority, submitter information, timestamp, attachments, etc., compare the new work order user input content in the work order material information to see if it contains all the general information parameter types, and identify the missing key general information parameter types (such as equipment model, specific description of the fault, etc.). The content information of these key general information parameter types is also the work order parameter missing information.

[0050] An interactive processing step (i.e., the first shortage information interactive processing step) is created based on the work order parameter shortage information, so that the work order processing large model can interact with the user according to the second shortage information interactive processing step, and the work order processing large model obtains the missing information through the second shortage information interactive processing step. In actual application, the second shortage information interactive processing step: the work order processing large model can output questions for obtaining shortage information to the user through the target agent service, and the user can input the work order parameter shortage information in response to the question.

[0051] It should be noted that in this specification, the difference between the second shortage information interaction processing step and the first shortage information interaction processing step is that the processing stages involved in the shortage information interaction processing step are different. The shortage information interaction processing step in the processing stage determined by the work order task processing workflow is called the first shortage information interaction processing step, and the shortage information interaction processing step in the processing stage of extracting work order parameter field information is called the second shortage information interaction processing step; S3008: Determine a first work order user preference item processing step for the user work order style portrait; Exemplarily, the (first or second) work order user preference item processing step instructs the work order processing big model to analyze the user's work order style portrait, so as to parse the user's work order style portrait, parse the user's previous work order submission style, including the preferred communication method, common problem type, work order description style, etc., determine the user's personalized processing steps according to the user's work order style portrait, and determine the personalized processing steps as the first work order user preference item processing steps, such as specific notification methods, priority processing, etc. The (first or second) work order user preference item processing step can be understood as obtaining and marking the user's work order user preference items. The work order user preference items are also used as a kind of work order parameter field information. After setting the work order user preference item processing step, the work order processing big model will extract the user preference work order configuration parameters through the work order processing big model based on the user's historical work orders.

[0052] It should be noted that in this specification, the difference between the second work order user preference item processing step and the first work order user preference item processing step is that the processing stages involved in the shortage information interaction processing step are different. The work order user preference item processing step in the processing stage determined by the work order task processing workflow is called the first work order user preference item processing step, and the work order user preference item processing step in the processing stage of extracting work order parameter field information is called the second work order user preference item processing step; Optionally, the (first or second) work order user preference item processing step indicates pre-parsing the user preference configuration based on the user's work order creation history, and creating a user work order style profile of the user based on the user preference configuration, such as the user's commonly used priority settings, common subject types, expected response time, etc.

[0053] S3010: Generate a large model work order task processing workflow based on the first target work order general processing steps, the first shortage information interaction processing steps and the first work order user preference item processing steps.

[0054] By integrating the general processing steps of the first target work order, the first shortage information interaction processing steps and the first work order user preference item processing steps, a personalized and efficient large model work order task processing workflow is generated. The large model work order task processing workflow ensures that each step meets the user's specific needs and historical performance, thereby improving processing efficiency and user satisfaction.

[0055] In one or more embodiments of the present specification, the above method generally not only improves the automation level and efficiency of work order processing, but also ensures that the personalized needs of each user are met, and enhances the customer's service experience and satisfaction. The large model work order task processing workflow generated by the method combines the intelligent application of historical data, the optimization of user interaction and the provision of personalized services, and realizes intelligence to ensure that the work order system can process general information, make up for missing data, and adjust according to the personalized needs of users, thereby improving the efficiency of work order processing and user satisfaction.

[0056] See also Figure 5 , Figure 5 This is a flow chart of extracting work order parameter field information proposed in this specification. The following methods can be used to extract work order parameter field information from the work order material information using the work order processing large model according to the work order task processing workflow: S4002: Generate a work order workflow processing prompt word based on the work order task processing workflow, and input the work order workflow processing prompt word and the work order material information into the task work order processing large model; The work order workflow processing prompt word is task description information used to instruct the work order processing large model to perform task work order generation processing on the work order material information according to one or more target work order processing steps of the work order task processing workflow; Optionally, the work order workflow processing prompt word may be a preset prompt word work order workflow processing template, and the work order workflow processing prompt word is generated by writing the work order task processing workflow into the prompt word work order workflow processing template; In a feasible implementation, the work order processing large model can be obtained by training the model for the task work order generation scenario based on the basic large (language) model. The basic large (language) model (LLM) is an artificial intelligence content generation model designed to understand and generate human language. The basic large model is trained on a large amount of data and can perform a wide range of tasks, including text summarization, translation, sentiment analysis, etc.

[0057] Optionally, the basic big model may be the Tongyi Qianwen big model, the Bailing big model, the GPT system big model, etc.; In some embodiments, a trained basic big model can be obtained, and the basic big model can be adapted to the task work order generation scenario to obtain the task work order generation big model. Usually, the basic big model is directly applied to process the work order in the task work order generation scenario, which is difficult to adapt to the new task work order generation scenario. Based on this, the basic big model is first obtained to create an initial task work order generation big model, and sample data is obtained in the new task work order creation scenario. Since the basic big model is usually a trained AIGC model with content generation capabilities, based on this, this specification only needs to adapt it to the task work order generation scenario. Specifically, the sample data can be used to perform model fine-tuning training on the initial task work order generation big model. After the model fine-tuning training is completed, the task work order generation big model adapted to the task work order generation scenario is obtained.

[0058] For example, the following is an example of a model training process for generating a large model from a task work order: 1. Obtain sample training data of sample users in the task work order creation scenario. The sample training data includes sample work order material information and sample work order task processing workflow; use the expert service to annotate the sample training data with work order parameter field information labels and task work order labels; The sample work order material information is the work order material information in the model training stage, and the sample work order task processing workflow is the work order task processing workflow determined by the work order material information of the sample user in the model training stage; 2. Use the basic big model to create the initial task work order in the task work order creation scenario to generate a big model; 3. Using sample training data, generate sample work order workflow processing prompt words based on the sample work order task processing workflow, input the sample work order workflow processing prompt words and sample work order material information into the initial task work order processing large model for at least one round of model training, in each round of model training, parse at least one sample work order processing step of the sample work order task processing workflow through the initial work order processing large model, extract sample work order parameter field information from the sample work order material information based on the sample work order processing step, and use the sample work order parameter field information to perform work order generation processing in the work platform to obtain a sample task work order, calculate the parameter extraction loss based on the sample work order parameter field information and the work order parameter field information label using the model loss calculation formula, and calculate the work order creation loss based on the sample task work order and the task work order label, comprehensively determine the model comprehensive calculation loss based on the parameter extraction loss and the work order creation loss, and use the model comprehensive calculation loss to adjust the model parameters of the initial task work order processing large model until the initial task work order processing large model meets the model end training conditions, Optionally, the model loss calculation formula can be a fit using one or more of the hinge loss function, contrast loss function, Euclidean distance loss function, cross entropy loss function, etc. in the relevant technology.

[0059] Optionally, the model training termination condition of the model may include, for example, the value of the loss function is less than or equal to a preset loss function threshold, the number of iterations reaches a preset number threshold, etc. The specific model training termination condition can be determined based on actual conditions and is not specifically limited here.

[0060] S4004: parse at least one target work order processing step of the work order task processing workflow through the work order processing large model, extract work order parameter field information from the work order material information based on the target work order processing step, and use the work order parameter field information to perform work order generation processing in the work platform to obtain a target task work order.

[0061] In a feasible implementation manner, the target work order processing step includes at least one of a second target work order general processing step, a second shortage information interaction processing step, and a second work order user preference item processing step. The following method can be used to extract the work order parameter field information from the work order material information by executing the target work order processing step through the work order processing big model: B2: if the target work order processing step is a second target work order general processing step, extracting target work order general parameters from the work order material information through the work order processing large model; At least one target work order processing step of the work order task processing workflow is sequentially executed through the work order processing big model. When the work order process is in the second target work order general processing step, the work order processing big model will automatically identify and extract key target work order general parameters from the work order material information.

[0062] For example, the target work order common parameters may be the incident type, urgency, impact scope, etc.

[0063] B4: If the target work order processing step is the second shortage information interaction processing step, the target agent object is called through the work order processing large model to output shortage task information prompts to the user, the user supplementary data input by the user for the shortage task information prompts is obtained, and the work order shortage task parameters are extracted based on the user supplementary data; At least one target work order processing step of the work order task processing workflow is sequentially executed through the work order processing big model. When the work order process is in the second shortage information interaction processing step, the target agent object is called through the work order processing big model to output a shortage task information prompt to the user, and the shortage task information prompt is used to remind the user that the missing information for work order creation needs to be supplemented; After the user responds to the prompt of the target intelligent object, he / she enters the user's supplementary data. The user's supplementary data will be processed by the work order processing large model, and the required work order missing task parameters will be extracted from the user's supplementary data. These work order missing task parameters supplement and complete the content of the work order, making subsequent processing more accurate.

[0064] B6: If the target work order processing step is the second work order user preference item processing step, obtain the user's historical work orders of the user, and extract the user preference work order configuration parameters through the work order processing large model based on the user's historical work orders.

[0065] At least one target work order processing step of the work order task processing workflow is sequentially executed by the work order processing big model. When the work order process is in the second work order user preference item processing step, the user's historical work orders are analyzed by the work order processing big model. By analyzing the user's historical work order data, the big model identifies the user's preferences, such as commonly used processing priorities, preferred communication methods, etc. Then, the user's preferred work order configuration parameters are extracted from the historical work order data; In one or more embodiments of this specification, the above-mentioned processing flow not only improves the efficiency of work order processing, but also improves user satisfaction, and can ensure the personalization and timely feedback of task work order services. Through this intelligent processing method, enterprises can better manage a large number of work order requirements, while reducing the burden of manual operations and enhancing the reliability and response speed of the work order processing system.

[0066] The following will be combined Figure 6 , the task work order generation device provided in the embodiment of this specification is introduced in detail. It should be noted that, Figure 6 The task work order generation device shown is used to execute this instruction Figure 1~Figure 5 For the convenience of explanation, only the part related to the embodiment of this specification is shown. For the specific technical details not disclosed, please refer to this specification. Figure 1~Figure 5 The embodiment shown.

[0067] See also Figure 6 , which shows a schematic diagram of the structure of the task work order generation device of an embodiment of the present specification. The task work order generation device 1 can be implemented as all or part of the device through software, hardware or a combination of both. According to some embodiments, the task work order generation device 1 includes a request processing module 11, a work order generation module 12 and an information output module 13, which are specifically used to: The request processing module 11 is used to respond to the work order automatic generation request input by the user to the target agent object, obtain the input work order material information, and determine the work order task processing workflow for the user based on the work order material information; A work order generation module 12 is used to extract work order parameter field information from the work order material information according to the work order task processing workflow using a work order processing large model, and to perform work order generation processing using the work order parameter field information in a work platform to obtain a target task work order; The information output module 13 is used to output the target task work order and work order creation prompt information to the user based on the target intelligent agent object.

[0068] Optional, such as Figure 7 As shown, the request processing module 11 includes: A determination unit 111 is used to extract user work order requirement information from the work order material information, and determine a target work order task type based on the user work order requirement information; The generating unit 112 is configured to generate a work order task processing workflow for the user based on the target work order task type.

[0069] Optionally, the generating unit 112 is configured to: A general work order task processing workflow corresponding to the target work order task type is obtained, and a work order task processing workflow for the user is obtained based on the general work order task processing workflow.

[0070] Optionally, the generating unit 112 is used to: obtain a reference task work order template corresponding to the target work order task type; Determine a first target work order general processing step from the general work order task processing workflow; Determine work order parameter shortage information based on the reference task work order template and the work order material information, and create a first shortage information interaction processing step for the user based on the work order parameter shortage information; Determine a first work order user preference item processing step for the user work order style portrait; A large model work order task processing workflow is generated based on the first target work order general processing steps, the first shortage information interaction processing steps and the first work order user preference item processing steps.

[0071] Optionally, the work order generating module 12 is used to: Generate a work order workflow processing prompt word based on the work order task processing workflow, and input the work order workflow processing prompt word and the work order material information into the task work order processing large model; At least one target work order processing step of the work order task processing workflow is parsed through the work order processing large model, and work order parameter field information is extracted from the work order material information based on the target work order processing step.

[0072] Optionally, the target work order processing step includes at least one of a second target work order general processing step, a second shortage information interaction processing step, and a second work order user preference item processing step, and the work order generating module 12 is used to: If the target work order processing step is a second target work order general processing step, extracting target work order general parameters from the work order material information through the work order processing large model; If the target work order processing step is the second shortage information interaction processing step, the target agent object is called through the work order processing large model to output shortage task information prompts to the user, the user supplementary data input by the user for the shortage task information prompts is obtained, and the work order shortage task parameters are extracted based on the user supplementary data; If the target work order processing step is the second work order user preference item processing step, the user history work orders of the user are obtained, and the user preference work order configuration parameters are extracted through the work order processing large model based on the user history work orders.

[0073] Optionally, the work order generating module 12 is used to: Get the work order creation interface of the work platform; A work order creation request is generated based on the work order creation interface and the work order parameter field information, and a target task work order is created in the work platform based on the work order creation request using the work order parameter field information.

[0074] It should be noted that the task work order generation device provided in the above embodiment only uses the division of the above functional modules as an example when executing the task work order generation method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the task work order generation device provided in the above embodiment and the task work order generation method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0075] The serial numbers of the embodiments of this specification are for description only and do not represent the advantages or disadvantages of the embodiments.

[0076] In one or more embodiments of the present specification, the electronic device responds to the work order automatic generation request input by the user to the target intelligent agent object, determines the work order task processing workflow based on the acquired work order material information, uses the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow, and uses the work order parameter field information in the work platform to generate the target task work order, and then outputs the target task work order and the work order creation prompt information to the user based on the target intelligent agent object, thereby avoiding the limitation of manually creating work order tasks, and can realize the automation and intelligence of work order processing according to the work order task processing workflow based on the work order processing large model, significantly improve the efficiency and accuracy of work order creation and processing, can adapt to the changes in business needs for work order task processing, and improve user satisfaction and operation experience. The task work order generation method can not only improve employee work efficiency, but also optimize resource allocation, and enhance overall service quality and management efficiency.

[0077] The present specification also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figure 1~Figure 5 The task work order generation method of the embodiment shown in the figure can be found in the specific execution process. Figure 1~Figure 5 The specific description of the illustrated embodiment will not be repeated here.

[0078] The present specification also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor as described above. Figure 1~Figure 5 The task work order generation method of the embodiment shown in the figure can be found in the specific execution process. Figure 1~Figure 5 The specific description of the illustrated embodiment will not be repeated here.

[0079] Please refer to Figure 8 , which shows a block diagram of the structure of an electronic device provided by an exemplary embodiment of this specification. The electronic device in this specification may include one or more of the following components: a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, the memory 120, the input device 130, and the output device 140 may be connected via the bus 150.

[0080] The processor 110 may include one or more processing cores. The processor 110 uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions and processes data of the electronic device 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120. Optionally, the processor 110 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 110 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 110, but may be implemented separately through a communication chip.

[0081] The memory 120 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 120 includes a non-transitory computer-readable storage medium. The memory 120 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The operating system may be an Android system, including a system deeply developed based on the Android system, an IOS system developed by Apple, including a system deeply developed based on the IOS system or other systems. The data storage area may also store data created by the electronic device during use, such as a phone book, audio and video data, chat record data, etc.

[0082] See also Fig. 9As shown, the memory 120 can be divided into an operating system space and a user space. The operating system runs in the operating system space, and native and third-party applications run in the user space. In order to ensure that different third-party applications can achieve good operating results, the operating system allocates corresponding system resources to different third-party applications. However, different application scenarios in the same third-party application also have different requirements for system resources. For example, in the local resource loading scenario, the third-party application has higher requirements for disk reading speed; in the animation rendering scenario, the third-party application has higher requirements for GPU performance. The operating system and third-party applications are independent of each other, and the operating system often cannot perceive the current application scenario of the third-party application in a timely manner, resulting in the operating system being unable to perform targeted system resource adaptation according to the specific application scenario of the third-party application.

[0083] In order for the operating system to distinguish the specific application scenarios of third-party applications, it is necessary to open up data communication between third-party applications and the operating system so that the operating system can obtain the current scenario information of third-party applications at any time, and then perform targeted system resource adaptation based on the current scenario.

[0084] Taking the Android operating system as an example, the programs and data stored in the memory 120 are as follows: Fig.10As shown, the memory 120 may store a Linux kernel layer 320, a system runtime library layer 340, an application framework layer 360 and an application layer 380, wherein the Linux kernel layer 320, the system runtime library layer 340 and the application framework layer 360 belong to the operating system space, and the application layer 380 belongs to the user space. The Linux kernel layer 320 provides underlying drivers for various hardware of electronic devices, such as display drivers, audio drivers, camera drivers, Bluetooth drivers, Wi-Fi drivers, power management, etc. The system runtime library layer 340 provides the main feature support for the Android system through some C / C++ libraries. For example, the SQLite library provides database support, the OpenGL / ES library provides 3D drawing support, and the Webkit library provides browser kernel support, etc. The system runtime library layer 340 also provides an Android runtime library (Android runtime), which mainly provides some core libraries that allow developers to use Java language to write Android applications. The application framework layer 360 provides various APIs that may be used when building applications. Developers can also use these APIs to build their own applications, such as activity management, window management, view management, notification management, content provider, package management, call management, resource management, and location management. At least one application runs in the application layer 380. These applications can be native applications that come with the operating system, such as contact applications, text messaging applications, clock applications, camera applications, etc.; they can also be third-party applications developed by third-party developers, such as game applications, instant messaging applications, photo beautification applications, etc.

[0085] Taking the operating system as an IOS system as an example, the programs and data stored in the memory 120 are as follows: Fig.11As shown, the IOS system includes: a core operating system layer 420 (Core OS layer), a core service layer 440 (Core Services layer), a media layer 460 (Media layer), and a touchable layer 480 (Cocoa Touch Layer). The core operating system layer 420 includes the operating system kernel, drivers, and underlying program frameworks. These underlying program frameworks provide functions closer to the hardware for use by the program frameworks located in the core service layer 440. The core service layer 440 provides system services and / or program frameworks required by applications, such as the foundation framework, account framework, advertising framework, data storage framework, network connection framework, geographic location framework, motion framework, etc. The media layer 460 provides audio-visual interfaces for applications, such as graphics and image-related interfaces, audio technology-related interfaces, video technology-related interfaces, and wireless playback (AirPlay) interfaces for audio and video transmission technologies. The touchable layer 480 provides various commonly used interface-related frameworks for application development, and the touchable layer 480 is responsible for the user's touch interaction operations on electronic devices. For example, local notification service, remote push service, advertising framework, game tool framework, message user interface (UI) framework, user interface UIKit framework, map framework, etc.

[0086] exist Fig.11 Among the frameworks shown, the frameworks related to most applications include but are not limited to: the basic framework in the core service layer 440 and the UIKit framework in the touchable layer 480. The basic framework provides many basic object classes and data types, provides the most basic system services for all applications, and has nothing to do with UI. The classes provided by the UIKit framework are basic UI class libraries for creating touch-based user interfaces. iOS applications can provide UIs based on the UIKit framework, so it provides the basic architecture of applications for building user interfaces, drawing, processing and user interaction events, responding to gestures, etc.

[0087] Among them, the method and principle of implementing data communication between third-party applications and the operating system in the IOS system can be referred to the Android system, and this manual will not go into details here.

[0088] Among them, the input device 130 is used to receive input instructions or data, and the input device 130 includes but is not limited to a keyboard, a mouse, a camera, a microphone or a touch device. The output device 140 is used to output instructions or data, and the output device 140 includes but is not limited to a display device and a speaker. In one example, the input device 130 and the output device 140 can be combined, and the input device 130 and the output device 140 are touch screen displays, which are used to receive touch operations on or near the user using any suitable object such as a finger or a touch pen, and to display the user interface of each application. The touch screen display is usually set on the front panel of the electronic device. The touch screen display can be designed as a full screen, a curved screen or a special-shaped screen. The touch screen display can also be designed as a combination of a full screen and a curved screen, or a combination of a special-shaped screen and a curved screen, which is not limited in the embodiments of this specification.

[0089] In addition, those skilled in the art will understand that the structure of the electronic device shown in the above drawings does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown, or combine certain components, or arrange the components differently. For example, the electronic device also includes radio frequency circuits, input units, sensors, audio circuits, wireless fidelity (WiFi) modules, power supplies, Bluetooth modules and other components, which will not be described in detail here.

[0090] In the embodiments of this specification, the execution subject of each step may be the electronic device described above. Optionally, the execution subject of each step is the operating system of the electronic device. The operating system may be an Android system, an IOS system, or other operating systems, which is not limited in the embodiments of this specification.

[0091] The electronic device of the embodiment of this specification may also be equipped with a display device, which may be various devices capable of realizing display functions, such as cathode ray tube display (CR), light-emitting diode display (LED), electronic ink screen, liquid crystal display (LCD), plasma display panel (PDP), etc. The user may use the display device on the electronic device to view displayed text, images, videos and other information. The electronic device may be a smart phone, a tablet computer, a gaming device, an AR (Augmented Reality) device, a car, a data storage device, an audio playback device, a video playback device, a notebook, a desktop computing device, a wearable device such as an electronic watch, an electronic glasses, an electronic helmet, an electronic bracelet, an electronic necklace, electronic clothing and other devices.

[0092] exist Figure 8 In the electronic device shown, the processor 110 may be used to call an application stored in the memory 120 and specifically perform the following operations: In response to a work order automatic generation request input by a user to a target agent object, the input work order material information is obtained, and a work order task processing workflow for the user is determined based on the work order material information; Using the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow, and using the work order parameter field information to perform work order generation processing in the work platform to obtain the target task work order; The target task work order and work order creation prompt information are output to the user based on the target agent object.

[0093] In one embodiment, the processor 110 performs the following steps when determining the work order task processing workflow for the user based on the work order material information: Extracting user work order requirement information from the work order material information, and determining a target work order task type based on the user work order requirement information; A work order task processing workflow for the user is generated based on the target work order task type.

[0094] In one embodiment, the processor 110 performs the following steps when generating a work order task processing workflow for the user based on the target work order task type: A general work order task processing workflow corresponding to the target work order task type is obtained, and a work order task processing workflow for the user is obtained based on the general work order task processing workflow.

[0095] In one embodiment, the processor 110 further performs the following steps: obtaining a reference task work order template corresponding to the target work order task type, and performing the following steps after obtaining a work order task processing workflow for the user based on the general work order task processing workflow: Determine a first target work order general processing step from the general work order task processing workflow; Determine work order parameter shortage information based on the reference task work order template and the work order material information, and create a first shortage information interaction processing step for the user based on the work order parameter shortage information; Determine a first work order user preference item processing step for the user work order style portrait; A large model work order task processing workflow is generated based on the first target work order general processing steps, the first shortage information interaction processing steps and the first work order user preference item processing steps.

[0096] In one embodiment, the processor 110 performs the following steps when extracting the work order parameter field information from the work order material information according to the work order task processing workflow using the work order processing large model: Generate a work order workflow processing prompt word based on the work order task processing workflow, and input the work order workflow processing prompt word and the work order material information into the task work order processing large model; At least one target work order processing step of the work order task processing workflow is parsed through the work order processing large model, and work order parameter field information is extracted from the work order material information based on the target work order processing step.

[0097] In one embodiment, the target work order processing step includes at least one of a second target work order general processing step, a second shortage information interaction processing step, and a second work order user preference item processing step. The processor 110 extracts work order parameter field information from the work order material information based on the target work order processing step and performs the following steps: If the target work order processing step is a second target work order general processing step, extracting target work order general parameters from the work order material information through the work order processing large model; If the target work order processing step is the second shortage information interaction processing step, the target agent object is called through the work order processing large model to output shortage task information prompts to the user, the user supplementary data input by the user for the shortage task information prompts is obtained, and the work order shortage task parameters are extracted based on the user supplementary data; If the target work order processing step is the second work order user preference item processing step, the user history work orders of the user are obtained, and the user preference work order configuration parameters are extracted through the work order processing large model based on the user history work orders.

[0098] In one embodiment, the processor 110 performs the following steps when executing the work order generation process using the work order parameter field information in the work platform to obtain the target task work order: Get the work order creation interface of the work platform; A work order creation request is generated based on the work order creation interface and the work order parameter field information, and a target task work order is created in the work platform based on the work order creation request using the work order parameter field information.

[0099] In one or more embodiments of the present specification, the electronic device responds to the work order automatic generation request input by the user to the target intelligent agent object, determines the work order task processing workflow based on the acquired work order material information, uses the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow, and uses the work order parameter field information in the work platform to generate the target task work order, and then outputs the target task work order and the work order creation prompt information to the user based on the target intelligent agent object, thereby avoiding the limitation of manually creating work order tasks, and can realize the automation and intelligence of work order processing according to the work order task processing workflow based on the work order processing large model, significantly improve the efficiency and accuracy of work order creation and processing, can adapt to the changes in business needs for work order task processing, and improve user satisfaction and operation experience. The task work order generation method can not only improve employee work efficiency, but also optimize resource allocation, and enhance overall service quality and management efficiency.

[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0101] The above disclosure is only the preferred embodiment of this specification, which certainly cannot be used to limit the scope of rights of this specification. Therefore, equivalent changes made according to the claims of this specification are still within the scope covered by this specification.

Claims

1. A method for generating a task work order, characterized in that: The method comprises: In response to a work order automatic generation request input by a user to a target agent object, the input work order material information is obtained, and a work order task processing workflow for the user is determined based on the work order material information; Using the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow, and using the work order parameter field information to perform work order generation processing in the work platform to obtain the target task work order; The target task work order and work order creation prompt information are output to the user based on the target agent object.

2. The method according to claim 1, characterized in that The determining of a work order task processing workflow for the user based on the work order material information includes: Extracting user work order requirement information from the work order material information, and determining a target work order task type based on the user work order requirement information; A work order task processing workflow for the user is generated based on the target work order task type.

3. The method according to claim 2, characterized in that The generating a work order task processing workflow for the user based on the target work order task type includes: A general work order task processing workflow corresponding to the target work order task type is obtained, and a work order task processing workflow for the user is obtained based on the general work order task processing workflow.

4. The method according to claim 3, characterized in that The method further includes: obtaining a reference task work order template corresponding to the target work order task type, The obtaining of the work order task processing workflow for the user based on the general work order task processing workflow includes: Determine a first target work order general processing step from the general work order task processing workflow; Determine work order parameter shortage information based on the reference task work order template and the work order material information, and create a first shortage information interaction processing step for the user based on the work order parameter shortage information; Determine a first work order user preference item processing step for the user work order style portrait; A large model work order task processing workflow is generated based on the first target work order general processing steps, the first shortage information interaction processing steps and the first work order user preference item processing steps.

5. The method according to claim 1, characterized in that The adopting of the work order processing large model to extract the work order parameter field information from the work order material information according to the work order task processing workflow includes: Generate a work order workflow processing prompt word based on the work order task processing workflow, and input the work order workflow processing prompt word and the work order material information into the task work order processing large model; At least one target work order processing step of the work order task processing workflow is parsed through the work order processing large model, and work order parameter field information is extracted from the work order material information based on the target work order processing step.

6. The method according to claim 5, characterized in that The target work order processing step includes at least one of a second target work order general processing step, a second shortage information interaction processing step, and a second work order user preference item processing step. The step of extracting work order parameter field information from the work order material information based on the target work order processing step includes: If the target work order processing step is the second target work order general processing step, extracting the target work order general parameters from the work order material information through the work order processing large model; If the target work order processing step is the second shortage information interaction processing step, the target agent object is called through the work order processing large model to output shortage task information prompts to the user, the user supplementary data input by the user for the shortage task information prompts is obtained, and the work order shortage task parameters are extracted based on the user supplementary data; If the target work order processing step is the second work order user preference item processing step, the user history work orders of the user are obtained, and the user preference work order configuration parameters are extracted through the work order processing large model based on the user history work orders.

7. The method according to claim 1, characterized in that The step of using the work order parameter field information to perform work order generation processing in the work platform to obtain a target task work order includes: Get the work order creation interface of the work platform; A work order creation request is generated based on the work order creation interface and the work order parameter field information, and a target task work order is created in the work platform based on the work order creation request using the work order parameter field information.

8. A task work order generating device, characterized in that: The device comprises: A request processing module, configured to respond to a work order automatic generation request input by a user to a target agent object, obtain the input work order material information, and determine a work order task processing workflow for the user based on the work order material information; A work order generation module, used to extract work order parameter field information from the work order material information according to the work order task processing workflow using a work order processing large model, and to perform work order generation processing using the work order parameter field information in a work platform to obtain a target task work order; An information output module is used to output the target task work order and work order creation prompt information to the user based on the target intelligent agent object.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps as claimed in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 7.

Images