Process scheduling arrangement method and device, equipment, program product and storage medium

Abstract

The invention discloses a process scheduling arrangement method and device, equipment, a program product and a storage medium. The method comprises the steps of obtaining first dialogue information of a user; determining a number of a first step in a flow according to the first dialogue information, and obtaining content of the first step according to the number of the first step; and executing the content of the first step to obtain a first execution result.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a process scheduling and choreography method and apparatus, equipment, program product, and storage medium. Background Art

[0002] At present, the solutions for process scheduling and orchestration usually adopt the International Terminating (IT) system, or obtain the execution process steps through the trained language model, or implement the process orchestration through the agent architecture solution. However, the current solutions have low scalability, low compatibility, low automation and low accuracy. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a process scheduling and choreography method and device, equipment, program product, and storage medium.

[0004] The process scheduling and choreography method provided by the present application comprises:

[0005] Get the user's first conversation information;

[0006] Determine the number of the first step in the process according to the first dialogue information, and obtain the content of the first step according to the number of the first step;

[0007] Execute the content of the first step to obtain the first execution result.

[0008] The process scheduling and arranging device provided by the present application comprises:

[0009] A multi-round dialogue module is used to obtain the user's first dialogue information;

[0010] A process scheduling module, used to determine the number of the first step in the process according to the first dialogue information, and obtain the content of the first step according to the number of the first step; and send the content of the first step to the step execution module;

[0011] The step execution module is used to execute the first content and obtain a first execution result.

[0012] The process scheduling and choreography device provided in the present application includes: a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the above-mentioned process scheduling and choreography method.

[0013] A computer program product provided by the present application includes: a computer program, and the computer program implements the above method when executed by a processor.

[0014] The computer-readable storage medium provided in the present application is used to store a computer program, and the computer program enables a computer to execute the above method.

[0015] In the technical solution of the present application, the user's first dialogue information is obtained; the number of the first step in the process is determined according to the first dialogue information, and the content of the first step is obtained according to the number of the first step; the content of the first step is executed to obtain the first execution result. In this way, by separating the acquisition of the step number and the execution of the step content, which are executed by different modules, a single module can only work in a single way, which can achieve the degree of automation of process arrangement and the accuracy of complex process arrangement jump. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a schematic diagram of the process scheduling method provided in the embodiment of the present application. Figure 1 ;

[0017] Figure 2 This is a schematic diagram of the process scheduling method provided in the embodiment of the present application. Figure 2 ;

[0018] Figure 3 is a schematic diagram of a multi-round dialogue module provided in an embodiment of the present application;

[0019] Figure 4 It is a schematic diagram of a process scheduling agent module provided in an embodiment of the present application;

[0020] Figure 5 It is a schematic diagram of the step execution agent module provided in the embodiment of the present application;

[0021] Figure 6 It is a logic flow chart of the main functions of the step execution agent module provided in the embodiment of the present application;

[0022] Figure 7 This is an example diagram of message interaction between a process scheduling agent and a step execution agent provided in an embodiment of the present application;

[0023] Figure 8 It is a schematic diagram of the structure of the process scheduling and arranging device provided in an embodiment of the present application;

[0024] Fig. 9 It is a schematic structural diagram of a process scheduling and orchestration device provided in an embodiment of the present application;

[0025] Fig.10 It is a schematic structural diagram of the chip of an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0028] It should also be pointed out that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0029] It should also be noted that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three kinds of relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. It should also be understood that the "indication" mentioned in the embodiments of the present application can be a direct indication, an indirect indication, or an indication of an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association relationship between A and B. It should also be understood that the "correspondence" mentioned in the embodiments of the present application can mean that there is a direct or indirect correspondence relationship between the two, or it can mean that there is an association relationship between the two, or it can mean a relationship between indication and being indicated, configuration and being configured, etc.

[0030] Currently, common technical solutions for process scheduling and orchestration are mainly divided into three categories.

[0031] The first type of solution is to solidify the process scheduling and flow involved in the system through IT system orchestration, unify the input parameters of the process scheduling function, make different branch judgments based on the function output of each step, and thus execute different branch flows, until the execution of the process function is completed and the execution results are uniformly output.

[0032] The second solution is to organize the process corpus involved in different sub-professions, use the process corpus to pre-train the large language model, then ask questions to the large language model, and use the output of the large language model to obtain the process steps that should be executed in different scenarios.

[0033] The third solution is to use an agent architecture solution, which uses a single agent to orchestrate and transfer the process. This method tightly couples the process jump with the selection of process step descriptions, which requires high capabilities of large models, and the accuracy of step jumps cannot be guaranteed. At the same time, changes in a single step description may affect the overall process jump. At the same time, due to the high degree of functional coupling, the feasibility of unit testing process jumps and step selection is low.

[0034] The above solution 1 implements process scheduling and jumping through IT system orchestration. When a new process scenario needs to be accessed, the original engineering code needs to be modified and adapted, which leads to low scalability of the project, low compatibility under different scenarios, and low code reusability.

[0035] The above-mentioned solution 2 uses process corpora of different scenarios to pre-train the language model, and then obtains the description of the process scheduling process by asking the language model questions. This solution has the following problems. In the current context, for example, in the scenarios of home broadband integrated adjustment or home broadband complaints, the process step descriptions involved in different scenarios involve dozens of execution steps, and the logic in a single step is also relatively complex. Therefore, it requires high professional background knowledge of the corpus provider. It is difficult to provide high-quality corpora in such scenarios, and it is difficult to obtain corpora for pre-training the language model. At the same time, it depends on the output results of the language model, and on-site personnel are required to perform different operations according to the steps, resulting in a low degree of automation of the overall process.

[0036] The main problem with the above solution three is that under the single-agent solution, the coupling degree between step jump and step description is high, which makes it difficult to ensure accuracy and the feasibility of unit testing the module is low.

[0037] Therefore, how to improve the automation and scalability of process scheduling and orchestration becomes a problem that needs to be considered in process scheduling and orchestration. To this end, the following technical solutions of the embodiments of the present application are proposed.

[0038] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined arbitrarily with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0039] Figure 1This is a schematic diagram of the process scheduling method provided in the embodiment of the present application. Figure 1 ,like Figure 1 As shown, the process scheduling and choreography method includes the following steps:

[0040] Step 101: Obtain the user's first conversation information.

[0041] Step 102: Determine the number of the first step in the process according to the first dialogue information, and obtain the content of the first step according to the number of the first step.

[0042] Step 103: Execute the content of the first step to obtain a first execution result.

[0043] In some embodiments, the method is applied to a process scheduling and choreography device, which includes three modules, namely a multi-round dialogue module, a process scheduling module, and a step execution module. The multi-round dialogue module can obtain the user's first dialogue information, the process scheduling module determines the number of the first step in the process according to the first dialogue information, and obtains the content of the first step according to the number of the first step, and the step execution module executes the content of the first step to obtain the first execution result. The process scheduling module and the step execution module are separated, and the work responsibilities of a single module are single. The number of prompt tokens required for the large question model in different scenarios is controllable, which improves the accuracy of complex process choreography jumps.

[0044] In some implementations, after the process scheduling module obtains the content of the first step, the content of the first step is sent to the step execution module.

[0045] It should be noted that the embodiment of the present application is described by taking a process including two steps as an example, namely the first step and the second step. In actual applications, the required steps are determined according to actual conditions. For example, more steps may be included, and the implementation method of more steps is the same as that of step two.

[0046] In some embodiments, after obtaining the user's first conversation information, the method further includes: determining the scene information of the first conversation based on the first conversation information; determining first parameter information required for the scene information of the first conversation based on the first conversation information, the first parameter information being used to execute the content of the first step.

[0047] In some embodiments, the multi-round dialogue module mainly includes two submodules, namely, a user intention mapping submodule and an intention parameter confirmation submodule. The user intention mapping submodule is used to determine the scene information of the first dialogue according to the first dialogue information, and the intention parameter confirmation submodule is used to determine the first parameter information required for the scene information of the first dialogue according to the first dialogue information, wherein the first parameter information is used to execute the content of the first step. Among them, the first scene information can be used to determine the corresponding prompt information, and different scenes correspond to different prompt information. It should be noted that the first parameter information is used to execute the content of all steps of the process, that is, it is not only used to execute the content of the first step, but also used to execute the content of the second step.

[0048] In some implementations, the function of the multi-round dialogue module is to complete the mapping of user questions to scenarios, and to supplement the application programming interface (API) parameter content involved in different scenarios based on the user dialogue content. In this way, the required parameters can be obtained in time when accessing a new scenario, solving the problem of scalability.

[0049] In some embodiments, the number of the first step in the process is determined based on the first dialogue information, and the content of the first step is obtained based on the number of the first step, including: determining the first prompt information based on the first dialogue information, the first prompt information including the process step jump logic and the calling order of the tools in each step; determining the number of the first step in the process based on the first prompt information, and obtaining the content of the first step based on the number of the first step.

[0050] In some embodiments, the scene information can be determined according to the dialogue information, and there are different prompt information for each scene information. Exemplarily, the first prompt information in the embodiment of the present application is the key prompt content, that is, the process description prompt template. The process prompt template needs to clearly describe the jump logic between different steps. At the same time, the call sequence of the API needs to be clearly described within the description of a single step, and it is necessary to clearly describe how the call results of multiple APIs affect the logic of step jump. That is, there is a different template for each scene. After the first prompt information corresponding to the first dialogue information is determined, the number of the first step is determined according to the first prompt information, and the content of the first step is obtained according to the number of the first step. Among them, the first step is the step at the beginning of the process. The initial step of each process is the first step. The content of the first step is related to the scene information, and then the next step is determined according to the step execution result and the step jump condition.

[0051] In some implementations, the first prompt information is determined based on the scene information of the first conversation, the number of the first step in the process is determined based on the first prompt information, and the content of the first step is obtained based on the number of the first step.

[0052] In some embodiments, the process scheduling module determines the first prompt information based on the first dialogue information, determines the number of the first step in the process based on the first prompt information, and can obtain the content of the first step based on the number of the first step, and send the content of the first step to the step execution module.

[0053] In some embodiments, the process scheduling module includes a next step content acquisition sub-module, which determines the first prompt information based on the first dialogue information, and the first prompt information includes the process step jump logic and the calling order of the tools in each step; determines the number of the first step in the process based on the first prompt information, and acquires the content of the first step based on the number of the first step.

[0054] In some implementations, the process generally involves two types of step description examples, namely, process jump step description and process end step description. The process description prompt template is mainly composed of these two types of step descriptions.

[0055] For example, the process jump step description example is as follows:

[0056] Step 3: Determine whether the "oltid and PONID" in the resource query tool are consistent with the "oltip and R / F / S / P" in the optical modem self-discovery tool.

[0057] The first step is to call the resource query tool, input the parameters "broadband account" and "onusn", and obtain the oltid and poind field data of the tool call result.

[0058] The second step is to call the optical modem self-discovery tool, input the parameters as "broadband account" and "onus sn", and obtain the oltip and r / f / s / p field data of the tool call result.

[0059] The third step is the final step, result processing. If the oltid of the resource query is consistent with the oltip discovered by the optical modem, and the ponid of the resource query is consistent with the r / f / s / p discovered by the optical modem, then execute step 7. If the oltid of the resource query is inconsistent with the oltip discovered by the optical modem, or the ponid of the resource query is inconsistent with the r / f / s / p discovered by the optical modem, then execute step 6.

[0060] Exemplarily, the process end step description is as follows:

[0061] step6:

[0062] Diagnosis result: The online address of the optical modem does not match the address to which the work order was issued.

[0063] Recommended solution: It is recommended to change the address in the construction APP to the online address of the optical modem (for the detailed address, see the detailed data of the optical modem self-discovery query).

[0064] The process ends.

[0065] In some implementations, executing the content of the first step to obtain a first execution result includes: acquiring a first tool according to the content of the first step and the first prompt information; and executing the content of the first step using the first tool to obtain the first execution result.

[0066] In some implementations, after receiving the content of the first step, the step execution module executes the content of the first step, obtains the first tool according to the content of the first step and the first prompt information, and executes the content of the first step using the first tool to obtain a first execution result.

[0067] In some embodiments, the step execution module includes an execution tool list acquisition submodule and an execution submodule, wherein the execution tool list acquisition submodule acquires the first tool according to the content of the first step and the first prompt information, and the execution submodule uses the first tool to execute the content of the first step and obtains the first execution result.

[0068] In some embodiments, the execution tool list acquisition submodule obtains a list of all tools to be called based on the complete step description content and the question language model, that is, the first tool. It should be noted that the first tool includes a tool for executing the content of the first step and a tool for executing the content of the second step. The execution submodule selects the first parameter information based on the content description of the first step, and obtains the specific value required for the first parameter call based on the selected first parameter and the first scenario information, thereby implementing the execution of the step. Exemplarily, the execution submodule selects an API based on the content description of the first step, obtains the content of the specific values ​​of the parameters required for the API call based on the selected API required parameters and the user's original question scenario, and completes the execution and call of the API based on the API URL and parameter fields.

[0069] In some embodiments, the step execution module specifically executes the following steps: obtain the content of the first step, obtain the tool name and number of tools to be called according to the step description, facilitate calling the tool list, traverse the tool name list to call, and then determine whether the calling of all tools has been completed. If not, continue to call API selection, API parameter selection, execute API call, record tool execution results, if the calling of all tools has been executed, select the next step according to the step description and the processing results of each tool, and send the next step number to the process scheduling module.

[0070] In some implementations, the step execution module mainly involves a template for obtaining a tool list and a template for obtaining the next step execution number and a thinking process.

[0071] For example, the template for obtaining the tool list is as follows:

[0072] Please delete the thought process or Trought content first. The rest of the content contains the calling instructions for one or more tools with specific names and the processing logic for the results returned by these tools. Please compile a tool list based on the calling instructions.

[0073] Each element in the list is the name of a tool with a specific name that you analyzed.

[0074] The description may contain some result processing logic. If you think it also contains some implicit tool calls, then these implicit tools are not counted.

[0075] After your understanding and statistics of the description, you should get a number. Please tell me this number.

[0076] The description is:

[0077] {}

[0078] Please return in the following format:

[0079] ['Tool Name 1', 'Tool Name 2']

[0080] Exemplarily, the example of obtaining the next step execution number and the thinking process template is as follows:

[0081] Based on the content in the step description, the judgment logic therein, and the return results of the tool, give the thinking process and give the number of the next step selected. Please be careful not to assume the specific content of the next step and only give the number of the next step.

[0082] Contents of step description:

[0083] {}

[0084] The tool returns the following results:

[0085] {}

[0086] Special attention:

[0087] The choice must be made based on the given judgment logic. Do not make any assumptions, and do not use other data that is not clearly stated in the judgment logic in the original data to assist in the judgment.

[0088] Be sure to strictly use the data selected by the given logic to make judgments. Do not perform any retrospective operations and do not use other data.

[0089] When it comes to string comparison logic, please strictly compare the strings and do not perform any semantic matching. If the content is different, it is considered not to be a match. Only when the content is completely the same can it be judged to be a match.

[0090] In some embodiments, after executing the content of the first step, the method further includes: obtaining the number of the second step in the process according to the first prompt information, the first execution result and the content of the first step; obtaining the content of the second step according to the number of the second step, executing the content of the second step, and obtaining the second execution result.

[0091] In some embodiments, after executing the content of the first step, the step execution module obtains the number of the next step in the process based on the first prompt information, the first execution result and the content of the first step. In this embodiment, taking the second step as an example, the number of the second step is obtained, and the number of the second step is sent to the process scheduling module. The process scheduling module determines the content of the second step based on the number of the second step, and sends the content of the second step to the step execution module. The step execution module executes the content of the second step to obtain the second execution result.

[0092] In some embodiments, the step execution module obtains the number of the second step based on the first prompt information, the first execution result, and the content of the first step, and sends the number of the second step to the process scheduling module. After the process scheduling module obtains the content of the second step based on the number of the second step, it sends the content of the second step to the step execution module, and then the step execution module executes the content of the second step to obtain a result. The specific execution process is shown in the first step and will not be repeated here.

[0093] In some embodiments, the step execution module includes a tool call result processing and next step selection sub-module, which obtains the number of the second step in the process according to the first prompt information, the first execution result and the content of the first step; sends the number of the second step to the process scheduling module; the execution sub-module obtains the content of the second step according to the number of the second step, executes the content of the second step, and obtains the second execution result.

[0094] In some embodiments, the step execution module specifically executes the following steps: obtain the content of the first step, obtain the tool name and the number of tools to be called according to the step description, facilitate calling the tool list, traverse the tool name list for calling, and then determine whether the calling of all tools has been completed. If not, continue to call API selection, API parameter selection, execute API call, record tool execution results, if the calling of all tools has been executed, select the second step number according to the step description and the processing results of each tool, and send the second step number to the process scheduling module.

[0095] In some implementations, selecting the content of the next step in the process scheduling module also involves a prompt template, which mainly selects the complete step content corresponding to the step according to a given step number.

[0096] For example, the following is an example of this prompt template:

[0097] You are an expert in business logic analysis. I have a business process with many problems. Please extract the original complete fragment of a step from the business logic based on my business logic and the questions provided. The business logic is as follows:

[0098] Step 1: Query the user status under the PON port and call the "Query user status under the same PON port" tool;

[0099] If the value of "User Status" in the tool return result is not empty, execute step 4; otherwise, execute step 3;

[0100] step4:

[0101] Diagnosis result: Total number of users under PON port: {Total number of users}, Current number of online users: {Number of online users}

[0102] Recommended: None

[0103] The process ends.

[0104] step3:

[0105] Diagnostic result: Unable to diagnose this type of group disorder.

[0106] Recommended solution: It is recommended to transfer the case to the comprehensive coordination seat for processing.

[0107] The process ends.

[0108] The above is the entire business logic.

[0109] Sample output:

[0110] Question is an input question that must be answered.

[0111] Please extract the original complete fragment of the corresponding step from the business logic based on the step number given in the question or the step number to be executed mentioned in the question. Please ignore the other content in the question and do not modify any content of the extracted step fragment.

[0112] Example 1:

[0113] Question:

[0114] step1.

[0115] Answer:

[0116] Step 1: Query the user status under the PON port and call the "Query user status under the same PON port" tool;

[0117] If the value of "User Status" in the tool return result is not empty, execute step 4; otherwise, execute step 3;

[0118] Example 2:

[0119] Question:

[0120] Thinking process: In the result of querying the user status under the same pon port, the value of "user status" in the tool return result is not empty. The number of the next step selected is: step4.

[0121] Answer:

[0122] step4:

[0123] Diagnosis result: Total number of users under PON port: {Total number of users}, Current number of online users: {Number of online users}

[0124] Recommended: None

[0125] The process ends.

[0126] Note: Please extract the original complete fragment of the corresponding step from the business logic based on the step number given in the question or the step number to be executed mentioned in the question. Please ignore other content in the question and do not modify any content of the extracted step fragment.

[0127] Current issues:

[0128] Question:{question}

[0129] Answer:

[0130] In some embodiments, the method also includes: determining whether the content of the first step and / or the content of the second step includes process end information; if the content of the first step and / or the content of the second step includes process end information, determining whether to present the first execution result and / or the second execution result based on the process end information.

[0131] In some embodiments, the process scheduling module further includes a process end step content processing submodule, which determines whether the content of the first step and / or the content of the second step contains process end information; if the content of the first step and / or the content of the second step contains process end information, it determines whether to present the first execution result and / or the second execution result according to the process end information. That is, it is necessary to determine whether to present the execution result for each step. In addition, the relevant data presented by the result is summarized and uniformly returned to the user.

[0132] The technical solution of the embodiment of the present application obtains the first dialogue information of the user; determines the number of the first step in the process according to the first dialogue information, and obtains the content of the first step according to the number of the first step; executes the content of the first step to obtain the first execution result. In this way, by separating the acquisition of the step number and the execution of the step content, which are executed by different modules, a single module can only work in a single way, which can achieve the degree of automation of process arrangement and the accuracy of complex process arrangement jump.

[0133] The technical solution of the embodiment of the present application is illustrated below with reference to specific application examples.

[0134] The above-mentioned solution 1 implements process scheduling and jumping through IT system orchestration. When a new process scenario needs to be accessed, the original engineering code needs to be modified and adapted, which leads to low scalability of the project, low compatibility under different scenarios, and low code reusability.

[0135] The above-mentioned solution 2 uses process corpora of different scenarios to pre-train the language model, and then obtains the description of the process scheduling process by asking questions to the language model. This solution has the following problems:

[0136] In the current context, for example, in the scenarios of home broadband integrated adjustment or home broadband complaints, the process steps involved in different scenarios involve dozens of execution steps, and the logic in a single step is also relatively complex, so the professional background knowledge of the person providing the corpus is high. It is difficult to provide high-quality corpus in such scenarios, and it is difficult to obtain corpus for pre-training of large language models. At the same time, it depends on the output results of the large language model, and it is also necessary for on-site personnel to perform different operations step by step, resulting in a low degree of automation of the overall process.

[0137] The main problem with the above-mentioned solution three is that in the single-agent solution, the coupling degree between step jump and step description is high, which makes it difficult to ensure accuracy and the feasibility of unit testing of modules is low. Based on this, the anti-interference method provided in the embodiment of the present application is further explained.

[0138] In view of the problems existing in the above solutions, the technical problems mainly solved by the embodiments of the present application include:

[0139] Solve the problem of low scalability and compatibility of the current solution in the process scheduling process when accessing new scenarios. Solve the problem of low accuracy of the current solution in handling complex process orchestration, that is, the large number of steps involved in the process steps and the low accuracy caused by the complexity of the execution process of a single step. Solve the problem of low degree of automation of process orchestration in the current language large model solution. Based on the multi-agent solution, decouple the input and output of different processing modules to solve the problem of low feasibility of unit testing of the current large model processing process scheduling solution. The specific description is as follows:

[0140] The embodiment of the present application is based on the ReAct thinking mode of the agent, and designs two types of agents to cooperate with each other according to the characteristics of the process scheduling and orchestration requirements, namely the process scheduling agent and the step execution agent.

[0141] Figure 2 This is a schematic diagram of the process scheduling method provided by the embodiment of the present application Figure 2 .like Figure 2 As shown, the method comprises the following steps:

[0142] Step 201: Map user questions to scenarios.

[0143] Step 202: Complete the user question parameters.

[0144] Step 203: Determine whether the message comes from the user. If so, initialize the next step number to step 1. Otherwise, use the most recent message as the next step number content (think).

[0145] Step 204: The process scheduling agent selects the next step content (think).

[0146] Step 205: Determine whether the step contains the end of the process.

[0147] If the process end information is included, execute step 209; otherwise, execute steps 206 to 209.

[0148] Step 206: The process scheduling agent sends the next step content description to the step execution agent (action).

[0149] Step 207: Step execution agent internal processing.

[0150] Step 208: The step execution agent sends the thinking process and the next step number to the process scheduling agent.

[0151] Step 209: The process scheduling agent is executed and the process ends and the description of the step is returned.

[0152] The process designed in the embodiment of the present application is mainly divided into two parts, namely the user dialogue part and the agent interaction part. Steps 201 and 202 are the user dialogue part. The main function of the user dialogue part is to complete the mapping of user questions to scenarios and supplement the API parameter content involved in different scenarios according to the user dialogue content. Steps 203 to 209 are the agent interaction part. The main function of the agent interaction part is to complete the execution of the process prompt through the mutual cooperation of the process scheduling agent and the step execution agent, and output the final result of the process execution.

[0153] The key prompt content involved in this proposal is the process description prompt template. The process prompt template needs to clearly describe: the jump logic between different steps; at the same time, the call sequence of multiple APIs needs to be clearly described within the description of a single step, and it is necessary to clearly describe how the call results of multiple APIs affect the logic of step jumps.

[0154] The following are description examples of two types of steps involved in the process, namely process jump step description and process end step description. The process description prompt template is mainly composed of these two types of step descriptions.

[0155] The following is an example of describing the process jump step:

[0156] Step 3: Determine whether the "oltid and PONID" in the resource query tool are consistent with the "oltip and R / F / S / P" in the optical modem self-discovery tool.

[0157] The first step is to call the resource query tool, input the parameters "broadband account" and "onusn", and obtain the oltid and PONID field data of the tool call result.

[0158] The second step is to call the optical modem self-discovery tool, input the parameters as "broadband account" and "onus sn", and obtain the oltip and R / F / S / P field data of the tool call result.

[0159] The third step is the final step, result processing. If the oltid of the resource query is consistent with the oltip discovered by the optical modem, and the ponid of the resource query is consistent with the r / f / s / p discovered by the optical modem, then execute step 7. If the oltid of the resource query is inconsistent with the oltip discovered by the optical modem, or the ponid of the resource query is inconsistent with the r / f / s / p discovered by the optical modem, then execute step 6.

[0160] The following is an example of the description of the process end step:

[0161] step6:

[0162] Diagnosis result: The online address of the optical modem does not match the address to which the work order was issued.

[0163] Recommended solution: It is recommended to change the address in the construction APP to the online address of the optical modem (for the detailed address, see the detailed data of the optical modem self-discovery query).

[0164] The process ends.

[0165] The above are examples of two types of step description content in the process description prompt template.

[0166] Selecting the content of the next step description in the process scheduling agent involves the prompt template. This prompt template mainly selects the complete step content corresponding to the step according to the given step number.

[0167] An example of this prompt template is as follows:

[0168] You are an expert in business logic analysis. I have a business process with many problems. Please extract the original complete fragment of a step from the business logic based on my business logic and the questions provided. The business logic is as follows:

[0169] Step 1: Query the user status under the PON port and call the "Query user status under the same PON port" tool;

[0170] If the value of "User Status" in the tool return result is not empty, execute step 4; otherwise, execute step 3;

[0171] step4:

[0172] Diagnosis result: Total number of users under PON port: {Total number of users}, Current number of online users: {Number of online users}

[0173] Recommended: None

[0174] The process ends.

[0175] step3:

[0176] Diagnostic result: Unable to diagnose this type of group disorder.

[0177] Recommended solution: It is recommended to transfer the case to the comprehensive coordination seat for processing.

[0178] The process ends.

[0179] The above is the entire business logic.

[0180] Sample output:

[0181] Question is an input question that must be answered.

[0182] Please extract the original complete fragment of the corresponding step from the business logic based on the step number given in the question or the step number to be executed mentioned in the question. Please ignore the other content in the question and do not modify any content of the extracted step fragment.

[0183] Example 1:

[0184] Question:

[0185] step1.

[0186] Answer:

[0187] Step 1: Query the user status under the PON port and call the "Query user status under the same PON port" tool;

[0188] If the value of "User Status" in the tool return result is not empty, execute step 4; otherwise, execute step 3;

[0189] Example 2:

[0190] Question:

[0191] Thinking process: In the result of querying the user status under the same pon port, the value of "user status" in the tool return result is not empty. The number of the next step selected is: step4.

[0192] Answer:

[0193] step4:

[0194] Diagnosis result: Total number of users under PON port: {Total number of users}, Current number of online users: {Number of online users}

[0195] Recommended: None

[0196] The process ends.

[0197] Note: Please extract the original complete fragment of the corresponding step from the business logic based on the step number given in the question or the step number to be executed mentioned in the question. Please ignore other content in the question and do not modify any content of the extracted step fragment.

[0198] Current issues:

[0199] Question:{question}

[0200] Answer:

[0201] The embodiment of the present application can be mainly divided into three modules, namely a multi-round dialogue module, a process scheduling agent module and a step execution agent module.

[0202] Figure 3 is a schematic diagram of a multi-round dialogue module provided in an embodiment of the present application, such as Figure 3 As shown, the multi-round dialogue module mainly includes two sub-modules, namely the user intention mapping sub-module and the intention parameter confirmation sub-module. The function of the user intention mapping sub-module is to map the user's question to the scenario supported by this system. If it is a scenario not supported by this system, the user will be given corresponding prompt content. The function of the intention parameter confirmation sub-module is to complete the parameter supplement required for the scenario through multiple rounds of dialogue with the user.

[0203] Figure 4 is a schematic diagram of a process scheduling agent module provided in an embodiment of the present application, such as Figure 4 As shown in the figure, the process scheduling agent module mainly includes the next step content acquisition submodule and the process end step content processing submodule. The next step content acquisition submodule extracts the complete description of the next step content from the process prompt template through the number content of the next step. The process end step content processing submodule decides whether to call the relevant API to obtain the presentation data based on the content description of the process end step, and completes the summary of the relevant data presented in the result and returns it to the user.

[0204] Figure 5 is a schematic diagram of the step execution agent module provided in the embodiment of the present application, such as Figure 5As shown, the step execution agent module mainly includes a submodule for obtaining the list of tools to be executed, a submodule for processing tool call results and selecting the next step, and an API execution submodule. The submodule for obtaining the list of tools to be executed obtains a list of all tools to be called based on the complete step description content and the question language model. The submodule for processing tool call results and selecting the next step obtains the number of the next step to be executed based on the summary of all tool execution results and the step description content. The API execution submodule mainly completes the selection of the API based on the content description of the current step, obtains the specific values ​​of the parameters required for the API call based on the selected API required parameters and the user's original problem scenario, and completes the execution and call of the API based on the API URL and parameter fields.

[0205] Figure 6 The steps provided in the embodiment of the present application are the main functional logic flow chart of the agent module, such as Figure 6 As shown, the execution steps of the step execution module agent module are as follows:

[0206] Step 601: Get the most recent message from the process scheduling agent as the content of the complete step description (think).

[0207] Step 602: Obtain the tool name and tool quantity (action) required to be called according to the step description.

[0208] Step 603: Traverse the tool name list and make calls.

[0209] Step 604: Determine whether all tool calls (actions) have been completed.

[0210] If the traversal is complete, execute step 609; otherwise, execute steps 605 to 609.

[0211] Step 605: Call API selection (action).

[0212] Step 606: API parameter selection (action).

[0213] Step 607: Execute API call (action).

[0214] Step 608: Record tool execution results (action).

[0215] Step 609: Process the results of each tool according to the step description and output the thinking process and the next step selected, and send a message to the process scheduling agent (action)

[0216] The step execution agent mainly involves obtaining prompt templates for the tool list and obtaining prompt templates for the next step execution number and thinking process.

[0217] The following is an example of a tool list acquisition prompt template:

[0218] Please delete the thought process or Trought content first. The rest of the content contains the calling instructions for one or more tools with specific names and the processing logic for the results returned by these tools. Please compile a tool list based on the calling instructions.

[0219] Each element in the list is the name of a tool with a specific name that you analyzed.

[0220] The description may contain some result processing logic. If you think it also contains some implicit tool calls, then these implicit tools are not counted.

[0221] After your understanding and statistics of the description, you should get a number. Please tell me this number.

[0222] The description is:

[0223] {}

[0224] Please return in the following format:

[0225] ['Tool Name 1', 'Tool Name 2']

[0226] The following is an example of the prompt template for getting the next step execution number and the thinking process:

[0227] Based on the content in the step description, the judgment logic therein, and the return results of the tool, give the thinking process and give the number of the next step selected. Please be careful not to assume the specific content of the next step and only give the number of the next step.

[0228] Contents of step description:

[0229] {}

[0230] The tool returns the following results:

[0231] {}

[0232] Special attention:

[0233] The choice must be made based on the given judgment logic. Do not make any assumptions, and do not use other data that is not clearly stated in the judgment logic in the original data to assist in the judgment.

[0234] Be sure to strictly use the data selected by the given logic to make judgments. Do not perform any retrospective operations and do not use other data.

[0235] When it comes to string comparison logic, please strictly compare the strings and do not perform any semantic matching. If the content is different, it is considered not to be a match. Only when the content is completely the same can it be judged to be a match.

[0236] Figure 7 is an example diagram of message interaction between a process scheduling agent and a step execution agent provided in an embodiment of the present application, such as Figure 7 As shown in the figure, the MainTainer role is the process scheduling agent, and the Director role is the step execution agent. The process scheduling agent sends a message to the step execution agent through RoleMaintainerAction, and the messages that the process scheduling agent pays attention to are divided into two parts, namely, the action from the user message, namely UserRequirement, and the action from the step execution agent message, namely FunctionCallAction.

[0237] The technical solution of the embodiment of the present application, the division logic of multiple agents based on the ReAct thinking mode used in the embodiment of the present application, are respectively the process scheduling agent and the step execution agent, the internal logic of each agent and the message transmission method between agents are all within the scope of patent protection. The method of the agent asking questions to the large model involved in the embodiment of the present application, and the prompt content of the question to the large model are all within the scope of patent protection. The module division principle relied on by the embodiment of the present application, namely the multi-round dialogue module, the agent interaction module, and the functions and contents of the sub-modules involved in each module are all within the scope of patent protection. The embodiment of the present application solves the problem of low scalability and compatibility of the current solution when accessing new scenarios by configuring prompt templates in different scenarios. The embodiment of the present application splits the process scheduling agent and the step execution agent based on the ReAct thinking method. The job responsibilities of a single agent are single, and the number of prompt tokens required for the large model of questioning language in different scenarios is controllable, which greatly improves the accuracy of complex process orchestration jumps. The embodiment of the present application improves the automation level of process automatic arrangement and jump through agent message interaction and the thinking mode of think and action in react mode. The embodiment of the present application splits the process scheduling agent and the step execution agent based on ReAct thinking. The input and output of different agents are highly deterministic, which provides feasibility for unit testing of agent system functions.

[0238] In one application scenario, the AI+home broadband integrated adjustment assistant application faces a difficult problem: the processes in dozens of scenarios and 31 provinces are different. How to quickly complete the automatic intelligent scheduling and dispatch of the process through a large model and execute and return the final result to the user. The embodiment of this application relies on a large model intelligent body to implement the scheduling and circulation of the process, automatically call the interface to complete the process execution, and realize the rapid implementation and deployment of large model applications such as AI+home broadband integrated adjustment.

[0239] Figure 8 Schematic diagram of the structure of the process scheduling and arranging device provided in the embodiment of the present application. Figure 8 As shown, the process scheduling and arranging device includes:

[0240] The multi-round dialogue module 801 is used to obtain the first dialogue information of the user;

[0241] The process scheduling module 802 is used to determine the number of the first step in the process according to the first dialogue information, and obtain the content of the first step according to the number of the first step; and send the content of the first step to the step execution module 803;

[0242] The step execution module 803 is used to execute the first content and obtain a first execution result.

[0243] In some embodiments, the multi-round dialogue module 801 includes a user intention mapping submodule 8011 and an intention parameter confirmation submodule 8012; the user intention mapping submodule 8011 is used to determine the scene information of the first dialogue based on the first dialogue information; the intention parameter confirmation submodule 8012 is used to determine the first parameter information required for the scene information of the first dialogue based on the first dialogue information, and the first parameter information is used for the step execution module to execute the content of the first step.

[0244] In some embodiments, the process scheduling module 802 includes a next step content acquisition submodule 8021; the next step content acquisition submodule 8021 is used to determine the first prompt information based on the first dialogue information, the first prompt information includes the process step jump logic and the calling order of the tools in each step; determine the number of the first step in the process based on the first prompt information, and obtain the content of the first step based on the number of the first step.

[0245] In some embodiments, the step execution module 803 includes an execution tool list acquisition submodule 8031 ​​and an execution submodule 8032; the execution tool list acquisition submodule 8031 ​​is used to acquire the first tool according to the content of the first step and the first prompt information; the execution submodule 8032 is used to use the first tool to execute the content of the first step and obtain the first execution result.

[0246] In some embodiments, the step execution module 803 includes a tool call result processing and next step selection submodule 8033; the tool call result processing and next step selection submodule 8033 is used to obtain the number of the second step in the process according to the first prompt information, the first execution result and the content of the first step; and send the number of the second step to the process scheduling module; the execution submodule 8032 is used to obtain the content of the second step according to the number of the second step, execute the content of the second step, and obtain the second execution result.

[0247] In some embodiments, the process scheduling module 802 also includes a process end step content processing sub-module 8022; the process end step content processing sub-module 8022 is used to determine whether the content of the first step and / or the content of the second step has process end information; if the content of the first step and / or the content of the second step includes process end information, then determine whether to present the first execution result and / or the second execution result based on the process end information.

[0248] Those skilled in the art should understand that Figure 8 The implementation functions of each module in the process scheduling and orchestration device shown can be understood by referring to the relevant description of the aforementioned method. Figure 8 The functions of each module in the process scheduling and arranging device shown can be implemented by a program running on a processor, or by a specific logic circuit.

[0249] Fig. 9 It is a schematic structural diagram of a process scheduling and orchestration device 900 provided in an embodiment of the present application. Fig. 9 The process scheduling and orchestration device 900 shown includes a processor 910, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0250] Alternatively, if Fig. 9 As shown, the process scheduling and choreography device 900 may further include a memory 920. The processor 910 may call and run a computer program from the memory 920 to implement the method in the embodiment of the present application.

[0251] The memory 920 may be a separate device independent of the processor 910 , or may be integrated into the processor 910 .

[0252] Alternatively, if Fig. 9 As shown, the process scheduling and orchestration device 900 may further include a transceiver 930, and the processor 910 may control the transceiver 930 to communicate with other devices, specifically, may send information or data to other devices, or receive information or data sent by other devices.

[0253] The transceiver 930 may include a transmitter and a receiver. The transceiver 930 may further include an antenna, and the number of the antennas may be one or more.

[0254] The process scheduling and orchestration device 900 can implement the corresponding processes implemented by the process scheduling and orchestration device in each method of the embodiments of the present application. For the sake of brevity, they will not be described here.

[0255] Fig.10 It is a schematic structural diagram of the chip of an embodiment of the present application. Fig.10 The chip 1000 shown includes a processor 1010, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0256] Alternatively, if Fig.10 As shown, the chip 1000 may further include a memory 1020. The processor 1010 may call and run a computer program from the memory 1020 to implement the method in the embodiment of the present application.

[0257] The memory 1020 may be a separate device independent of the processor 1010 , or may be integrated into the processor 1010 .

[0258] Optionally, the chip 1000 may further include an input interface 1030. The processor 1010 may control the input interface 1030 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0259] Optionally, the chip 1000 may further include an output interface 1040. The processor 1010 may control the output interface 1040 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0260] The chip can implement the corresponding processes implemented by the process scheduling and orchestration device in each method of the embodiments of the present application. For the sake of brevity, they will not be described here.

[0261] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0262] It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and performed. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, and other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0263] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0264] It should be understood that the above-mentioned memory is exemplary but not restrictive. For example, the memory in the embodiments of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.

[0265] An embodiment of the present application also provides a computer program product, including a computer program.

[0266] When the computer program is executed by the processor, it implements the corresponding processes implemented by the process scheduling and orchestration device in each method of the embodiments of the present application. For the sake of brevity, it will not be repeated here.

[0267] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0268] The computer program enables the computer to execute the corresponding processes implemented by the process scheduling and orchestration device in each method of the embodiments of the present application. For the sake of brevity, it will not be repeated here.

[0269] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0270] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0271] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0272] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0273] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0274] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0275] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A process scheduling and arranging method, characterized in that: The method comprises: Get the user's first conversation information; Determine the number of the first step in the process according to the first dialogue information, and obtain the content of the first step according to the number of the first step; Execute the content of the first step to obtain a first execution result.

2. The method according to claim 1, characterized in that After obtaining the first conversation information of the user, the method further includes: Determining scene information of the first dialogue according to the first dialogue information; First parameter information required for scene information of the first dialogue is determined according to the first dialogue information, and the first parameter information is used to execute the content of the first step.

3. The method according to claim 2, characterized in that The determining the number of the first step in the process according to the first dialogue information, and acquiring the content of the first step according to the number of the first step includes: Determining first prompt information according to the first dialogue information, wherein the first prompt information includes process step jump logic and a calling sequence of tools in each step; The number of the first step in the process is determined according to the first prompt information, and the content of the first step is obtained according to the number of the first step.

4. The method according to claim 3, characterized in that: The executing the content of the first step to obtain a first execution result includes: Acquire a first tool according to the content of the first step and the first prompt information; The first tool is used to execute the content of the first step and obtain a first execution result.

5. The method according to claim 4, characterized in that After executing the first step, the method further includes: Acquire the number of the second step in the process according to the first prompt information, the first execution result and the content of the first step; The content of the second step is obtained according to the number of the second step, and the content of the second step is executed to obtain a second execution result.

6. The method according to claim 5, characterized in that The method further comprises: Determine whether the content of the first step and / or the content of the second step contains process end information; If the content of the first step and / or the content of the second step includes process end information, it is determined whether to present the first execution result and / or the second execution result according to the process end information.

7. A process scheduling and arranging device, characterized in that: The device comprises: A multi-round dialogue module is used to obtain the user's first dialogue information; a process scheduling module, configured to determine the number of the first step in the process according to the first dialogue information, and obtain the content of the first step according to the number of the first step; and send the content of the first step to the step execution module; The step execution module is used to execute the first content and obtain a first execution result.

8. The device according to claim 7, characterized in that The multi-round dialogue module includes a user intention mapping submodule and an intention parameter confirmation submodule; the device also includes: The user intention mapping submodule is used to determine the scenario information of the first dialogue according to the first dialogue information; The intention parameter confirmation submodule is used to determine the first parameter information required for the scene information of the first dialogue according to the first dialogue information, and the first parameter information is used by the step execution module to execute the content of the first step.

9. The device according to claim 8, characterized in that The process scheduling module includes a next step content acquisition submodule; the device also includes: The next step content acquisition submodule is used to determine the first prompt information based on the first dialogue information, the first prompt information including the process step jump logic and the calling order of the tools in each step; determine the number of the first step in the process based on the first prompt information, and acquire the content of the first step based on the number of the first step.

10. The device according to claim 9, characterized in that The step execution module includes an execution tool list acquisition submodule and an execution submodule; the device also includes: The execution tool list acquisition submodule is used to acquire the first tool according to the content of the first step and the first prompt information; The execution submodule is used to execute the content of the first step using the first tool and obtain a first execution result.

11. The device according to claim 10, characterized in that The step execution module also includes a tool call result processing and next step selection submodule; the device also includes: The tool call result processing and next step selection submodule is used to obtain the number of the second step in the process according to the first prompt information, the first execution result and the content of the first step; and send the number of the second step to the process scheduling module; The execution submodule is used to obtain the content of the second step according to the number of the second step, execute the content of the second step, and obtain a second execution result.

12. The device according to claim 11, characterized in that The process scheduling module also includes a process end step content processing submodule; the device includes: The process end step content processing submodule is used to determine whether the content of the first step and / or the content of the second step contains process end information; if the content of the first step and / or the content of the second step includes process end information, then determine whether to present the first execution result and / or the second execution result based on the process end information.

13. A process scheduling and arranging device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 6.

14. A computer program product, characterized in that include: A computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

15. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program causes a computer to execute the method according to any one of claims 1 to 6.

Images