Intelligent inquiry method, device and equipment, medium and program product

Abstract

The invention discloses an intelligent inquiry method, device and equipment, a medium and a program product, and the method comprises the following steps: splitting a target task into a plurality of subtasks through a preset task splitting algorithm, the target task being a received task demand input by a target user; performing task arrangement on the sub-tasks according to a preset task arrangement algorithm to realize data transmission among the sub-tasks; main agents and coordination agents corresponding to the subtasks are determined, the main agents are used for task division, and the coordination agents are used for executing the corresponding subtasks; according to the task arrangement result, from the first sub-task, the task is executed through cooperation of the coordination agent and the knowledge base, and an execution result of the target task is obtained; and feeding back the execution result to the target user. According to the method, automation of all links in the intelligent question-answering process is achieved, manual participation is reduced, and meanwhile the efficiency and accuracy of the intelligent question-answering system are improved by disassembling and executing the target task.

Description

Technical Field

[0001] The present invention relates to the field of Internet medical technology, and in particular to an intelligent diagnosis method, device, equipment, medium and program product. Background Art

[0002] With the development and popularization of mobile terminals, more and more people choose to use mobile terminals such as mobile phones to consult doctors, and doctors can also use fragmented time to answer patients' questions, which improves the efficiency of patients' medical treatment and enables doctors to provide medical services more efficiently. However, in the existing technology, manual operation is often required to complete the entire consultation process. For example: when a user initiates a consultation request, the customer service staff needs to first screen a suitable doctor, then notify the doctor to handle the consultation request, and then the doctor will answer according to the user's needs, and finally the customer service staff will feedback the consultation results to the user. This consultation method has the following disadvantages:

[0003] (1) The consultation process involves multiple roles, and each role requires separate allocation of manpower, resulting in a waste of human resources;

[0004] (2) Customer service staff acts as intermediaries, increasing communication costs;

[0005] (3) Due to the involvement of customer service personnel, the entire consultation process takes a long time and the user experience is poor;

[0006] (4) Customer service staff need to connect with a large number of doctors and patients at the same time, and the quality of service cannot be guaranteed.

[0007] Therefore, how to improve the level of intelligence is an urgent problem to be solved. Summary of the invention

[0008] In order to solve the above problems, the embodiments of the present application provide an intelligent medical consultation method, device, equipment, medium and program product.

[0009] The embodiments of the present application provide an intelligent medical consultation method, apparatus, device, medium and program product.

[0010] In a first aspect, the present invention provides an intelligent medical consultation method, comprising the following steps:

[0011] Splitting the target task into multiple subtasks through a preset task splitting algorithm, wherein the target task refers to the task requirements received from the target user input;

[0012] According to a preset task scheduling algorithm, the subtasks are scheduled to realize data transmission between the subtasks;

[0013] Determine the main agent and the coordination agent corresponding to each subtask, the main control agent is used to divide the tasks, and the coordination agent is used to execute the corresponding subtasks;

[0014] According to the task arrangement result, starting from the first subtask, the execution result of the target task is obtained by coordinating the intelligent agent and the knowledge base to perform the task, wherein the knowledge base includes the business knowledge related to the subtask;

[0015] The execution result is fed back to the target user.

[0016] In some embodiments, the target task is split into multiple subtasks using a preset task splitting algorithm, specifically including:

[0017] Determine the target task based on the task requirements input by the target user;

[0018] According to the preset task splitting algorithm, determine the task assignment order and effective service period, and generate a task planning plan;

[0019] According to the task planning scheme, the target task is divided into multiple subtasks.

[0020] In some embodiments, the subtasks are scheduled according to a preset task scheduling algorithm to achieve data transmission between the subtasks, specifically including:

[0021] Determine the dependencies between subtasks;

[0022] According to the preset task scheduling algorithm and dependency relationships, the execution order of each subtask is determined to realize data transfer between subtasks.

[0023] In some embodiments, the step of obtaining the execution result of the target task by coordinating the intelligent agent and the knowledge base to execute the task starting from the first subtask according to the task scheduling result includes:

[0024] According to the task arrangement results, determine the workflow and the first subtask;

[0025] Through the coordination agent corresponding to the first subtask, the corresponding knowledge base is called;

[0026] performing tasks according to the knowledge base;

[0027] According to the described workflow, starting from the first subtask, the tasks are executed in sequence to determine the execution result of the target task.

[0028] In a second aspect, the present application also provides an intelligent medical consultation device, including:

[0029] A splitting module is used to split the target task into multiple subtasks by using a preset task splitting algorithm, wherein the target task refers to the task requirement received from the target user input;

[0030] The scheduling module is used to schedule the subtasks according to a preset task scheduling algorithm to achieve data transmission between the subtasks;

[0031] A determination module is used to determine the main agent and the coordination agent corresponding to each subtask, wherein the main control agent is used to divide the tasks, and the coordination agent is used to execute the corresponding subtasks;

[0032] An execution module is used to execute tasks according to the task arrangement results, starting from the first subtask, by coordinating the intelligent agent and the knowledge base to obtain the execution result of the target task, wherein the knowledge base includes business knowledge related to the subtask;

[0033] The feedback module is used to feed back the execution result to the target user.

[0034] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0035] Memory;

[0036] processor;

[0037] and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the above method.

[0038] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the above method.

[0039] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0040] The above technical solution provided by the embodiment of the present application can achieve the following beneficial effects: through the technical solution of the embodiment of the present application, the automatic splitting of the target task is realized, and the corresponding knowledge base is called by determining the main intelligent agent to perform the task. The automation of each link in the intelligent question-answering process is realized, which reduces manual participation and improves the efficiency and accuracy of the intelligent question-answering system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 A schematic diagram showing a process flow of an intelligent medical consultation method according to an embodiment of the present application is shown;

[0043] Figure 2 A schematic diagram showing a process flow of a task splitting method according to an embodiment of the present application is shown;

[0044] Figure 3 A schematic diagram showing a process flow of a task scheduling method according to an embodiment of the present application is shown;

[0045] Figure 4 A schematic diagram showing a flow chart of a method for generating an execution result according to an embodiment of the present application is shown;

[0046] Figure 5 A schematic diagram of the structure of an intelligent medical consultation device according to an embodiment of the present application is shown;

[0047] Figure 6 A schematic structural diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings.

[0049] Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0050] Embodiment 1

[0051] In view of the deficiencies in the related art, the present application provides an intelligent diagnosis method, such as Figure 1 As shown, the method comprises the following steps:

[0052] S10: Split the target task into multiple subtasks using a preset task splitting algorithm, wherein the target task refers to the task requirement received from the target user input.

[0053] In this embodiment, the subtasks are obtained through a preset task splitting algorithm, the target task is determined by obtaining the input data of the target user, and the target task is split into multiple subtasks according to the preset task splitting algorithm. Exemplarily, the preset task splitting algorithm can be one or more of a pre-configured divide-and-conquer algorithm, a network task workflow partitioning algorithm, Mapduce, and a ForkJoin framework.

[0054] S20: Arrange the subtasks according to a preset task arrangement algorithm to achieve data transmission between the subtasks.

[0055] In this embodiment, by determining the dependency relationship between each subtask, establishing a dependency graph of the task, and through a preset data transfer mechanism, ensuring that the output of the previous subtask can be used as the input of the next subtask, specifying the task scheduling strategy according to the priority and resource requirements of the task, and completing the task scheduling. Specifically, the task scheduling algorithm can be one or more of the benchmark algorithm, deep reinforcement learning algorithm, task decomposition and scheduling algorithm, and directed acyclic graph algorithm. Task scheduling can be implemented by combining concurrent programming tools with thenApply or thenAccept methods.

[0056] S30: Determine the main intelligent agent and the coordination intelligent agent corresponding to each subtask, the main control intelligent agent is used to divide the tasks, and the coordination intelligent agent is used to execute the corresponding subtasks.

[0057] In this embodiment, the main agent performs the division, and the coordination agent is used to perform the corresponding subtasks, and the communication and coordination with other agents are realized through the communication protocol. Specifically, when the target task is divided into multiple subtasks, the main agent divides the subtasks to the corresponding coordination agents, and these coordination agents respectively perform the corresponding subtasks.

[0058] S40: According to the task scheduling result, starting from the first subtask, the execution result of the target task is obtained by coordinating the intelligent agent and the knowledge base to cooperate in executing the task, wherein the knowledge base includes the business knowledge related to the subtask.

[0059] In this embodiment, the execution result of the target task is obtained by coordinating the agent and the knowledge base to perform the task. In a multi-agent system, agents need to collaborate to complete complex tasks, and this collaboration involves multiple aspects such as communication, coordination, and decision-making. For example, Tribe AI is a low-code tool designed to help users quickly build and coordinate multi-agent teams. By breaking down complex tasks and assigning them to agents who are good at different fields, each agent can focus on its own strengths, thereby achieving faster task execution. As the basis for the agent to perform tasks, the knowledge base stores information about the environment, tasks, and effects of actions. Through the knowledge base, the coordinating agent can obtain the required knowledge and reason to make reasonable decisions.

[0060] In the process of executing a task, the coordination agent first calls the knowledge base tool to retrieve relevant information from the knowledge base. Then the big model summarizes and outputs the execution results. Specifically, the coordination agent can also improve the execution steps by reflecting on the completed subtasks and learning from the mistakes, so as to improve the accuracy and efficiency of subsequent execution tasks. For example, the knowledge base can not only help a single agent to perform tasks, but also promote collaboration between agents.

[0061] S50: Feedback the execution result to the target user.

[0062] In the above scheme provided by the embodiment of the present application, the target task is first split into multiple subtasks through a preset task splitting algorithm, and then the subtasks are scheduled according to the preset task scheduling algorithm to achieve data transmission between the subtasks. Finally, according to the task scheduling results, starting from the first subtask, the execution result of the target task is obtained by coordinating the intelligent agent and the knowledge base to cooperate in executing the task, and the execution result is fed back to the target user. The automation of each link in the intelligent question-answering process is realized, while reducing manual participation, and by disassembling and executing the target task, the efficiency and accuracy of the intelligent question-answering system are improved.

[0063] like Figure 2 As shown, S10: split the target task into multiple subtasks using a preset task splitting algorithm, including the following steps:

[0064] S11: Determine the target task according to the task requirements input by the target user;

[0065] S12: Determine the task assignment order and effective service period according to the preset task splitting algorithm, and generate a task planning plan;

[0066] S13: According to the task planning scheme, the target task is divided into multiple subtasks.

[0067] In this embodiment, the target task can be determined according to the task requirement input by the target user. For example, when the target user inputs the task requirement, the target task can be directly determined.

[0068] In this embodiment, the task assignment order and the effective service period can be determined according to the preset task splitting algorithm, and the task planning scheme can be generated. For example, the task assignment order can be determined according to the preset task splitting algorithm, that is, the execution order of each subtask can be determined. At the same time, the effective service period of each subtask can also be determined according to the preset task splitting algorithm, that is, the time period in which each subtask can be executed can be determined. Furthermore, the task planning scheme can be generated according to the task assignment order and the effective service period.

[0069] In the embodiment of the present invention, the target task can be split into multiple subtasks according to the task planning scheme. For example, the target task can be split into multiple subtasks according to the task planning scheme, and each subtask is assigned to a different agent.

[0070] like Figure 3 As shown, S20: according to a preset task scheduling algorithm, the subtasks are scheduled to realize data transmission between the subtasks, including the following steps:

[0071] S21: Determine the dependencies between subtasks;

[0072] S22: According to the preset task scheduling algorithm and dependency relationship, the execution order of each subtask is determined to realize data transmission between each subtask.

[0073] Specifically, in order to ensure that the subtasks can be executed smoothly, it is necessary to first determine the dependencies between the subtasks, so that the execution order of the subtasks can be determined based on the dependencies.

[0074] For example, in the above example, the execution result of "Please help me analyze my recent physical condition" is the input of "Please tell me the cause of my physical discomfort", so there is a dependency relationship between the two subtasks. If a subtask does not have a dependency relationship, it can be directly set as the first subtask to be executed. Of course, in actual applications, other task scheduling algorithms can also be used to implement the scheduling of subtasks, as long as the scheduling of subtasks can be achieved, and they will not be described here one by one.

[0075] like Figure 4 As shown, S40: according to the task scheduling result, starting from the first subtask, the execution result of the target task is obtained by coordinating the intelligent agent and the knowledge base to perform the task, including the following steps:

[0076] S41: Determine the workflow and the first subtask based on the task scheduling result;

[0077] S42: calling the corresponding knowledge base through the coordination agent corresponding to the first subtask;

[0078] S43: Execute tasks based on the knowledge base;

[0079] S44: According to the workflow, starting from the first subtask, the tasks are executed in sequence to determine the execution result of the target task.

[0080] In this embodiment, the workflow and the first subtask can be determined according to the task scheduling result. For example, the workflow and the first subtask can be determined according to the task scheduling result. The workflow refers to the execution order of each subtask, and the first subtask refers to the first subtask to be executed.

[0081] In this embodiment, the corresponding knowledge base can be called through the main agent and the coordination agent corresponding to the first subtask. For example, the knowledge base of the corresponding field can be called through the main agent and the coordination agent corresponding to the first subtask. Since each coordination agent corresponds to a different knowledge base, that is, each knowledge base is used to perform a different task, by calling the corresponding knowledge base to perform the task, the execution efficiency and the accuracy of the execution result are improved.

[0082] Specifically, the task can be executed according to the knowledge base. First, the requirement information of the first subtask can be sent to the coordination agent corresponding to the first subtask, so that the coordination agent can query the knowledge base according to the requirement information to find the answer to solve the problem.

[0083] For example, according to the task arrangement result, a series of workflows can be obtained, such as: "Step 1: Execute subtask A; Step 2: Execute subtask B; ..." Then, it is only necessary to execute each subtask in sequence according to this workflow.

[0084] After the first subtask is executed, the execution result of the subtask can be obtained, and then the execution result can be used as the input of the second subtask to continue executing the second subtask, and so on, until the last subtask is executed. Finally, the execution results of all subtasks can be summarized to generate the final execution result. It should be pointed out that during the execution process, some subtasks may fail. At this time, different countermeasures can be taken according to the actual situation. For example, you can re-execute the subtask, or skip the subtask and directly execute the next subtask, etc.

[0085] For example, when the execution is completed, an execution result will be obtained, which can be a text message or a voice message, and the specific form is not limited. Subsequently, the execution result can be sent to the target user so that the user can understand the result of the consultation. Of course, the execution result can also be presented in a variety of ways according to the user's preferences or habits, such as text, pictures, videos, etc.

[0086] In some possible embodiments, in order to better display the execution results, optimization can be performed in the following ways: generating a visual report based on the execution results; and sending the visual report to the target user. The execution results can also be converted into a visual form, such as a chart, a table, etc., so that the user can more intuitively understand the results of the consultation. In addition, more information can be added according to the needs of the user, such as suggestions, reminders, etc., so as to make the visual report more rich and comprehensive.

[0087] Embodiment 2

[0088] The present application also provides an intelligent medical consultation device, such as Figure 5 As shown, the device comprises:

[0089] The splitting module 400 is used to split the target task into multiple subtasks by using a preset task splitting algorithm, wherein the target task refers to the task requirement received from the target user input;

[0090] The scheduling module 500 is used to schedule the subtasks according to a preset task scheduling algorithm to achieve data transmission between the subtasks;

[0091] Determination module 600, used to determine the main agent and coordination agent corresponding to each subtask, the main control agent is used to divide the task, and the coordination agent is used to execute the corresponding subtask;

[0092] An execution module 700 is used to execute tasks starting from the first subtask by coordinating the intelligent agent and the knowledge base to obtain the execution result of the target task according to the task arrangement result, wherein the knowledge base includes the business knowledge related to the subtask;

[0093] The feedback module 800 is used to feed back the execution result to the target user.

[0094] In some possible embodiments, the splitting module 400 is specifically used for:

[0095] Determine the target task based on the task requirements input by the target user;

[0096] According to the preset task splitting algorithm, determine the task assignment order and effective service period, and generate a task planning plan;

[0097] According to the task planning plan, the target task is divided into multiple subtasks.

[0098] In some possible embodiments, the orchestration module 500 is specifically used to:

[0099] Determine the dependencies between subtasks;

[0100] According to the preset task scheduling algorithm and dependency relationships, the execution order of each subtask is determined to realize data transfer between subtasks.

[0101] In some possible embodiments, the execution module 700 is specifically used to:

[0102] According to the task arrangement results, determine the workflow and the first subtask;

[0103] Through the coordination agent corresponding to the first subtask, the corresponding knowledge base is called;

[0104] Perform tasks based on the knowledge base;

[0105] According to the workflow, starting from the first subtask, execute the tasks in sequence to determine the execution result of the target task.

[0106] Embodiment 3

[0107] The present application also provides an electronic device, such as Figure 6 As shown, including:

[0108] Memory;

[0109] Processor; and

[0110] Computer programs;

[0111] Among them, the computer program is stored in the memory and is configured to be executed by the processor to implement the technical solution of any of the above-mentioned method embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

[0112] Optionally, the memory can be independent or integrated with the processor. When the memory is a device independent of the processor, the electronic device further includes: a bus for connecting the memory and the processor.

[0113] Embodiment 4

[0114] An embodiment of the present application further provides a computer-readable storage medium, characterized in that a computer program is stored thereon, and the computer program is executed by a processor to implement the technical solution of any of the above method embodiments.

[0115] Embodiment 5

[0116] An embodiment of the present application also provides a computer program product, characterized in that it includes a computer program, and when the computer program is executed by a processor, the technical solution of any of the above method embodiments is implemented.

[0117] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0118] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0119] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0120] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0121] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent medical consultation method, characterized in that: The steps include: Splitting the target task into multiple subtasks through a preset task splitting algorithm, wherein the target task refers to the task requirements received from the target user input; According to a preset task scheduling algorithm, the subtasks are scheduled to realize data transmission between the subtasks; Determine the main agent and the coordination agent corresponding to each subtask, the main control agent is used to divide the tasks, and the coordination agent is used to execute the corresponding subtasks; According to the task arrangement result, starting from the first subtask, the execution result of the target task is obtained by coordinating the intelligent agent and the knowledge base to perform the task, wherein the knowledge base includes the business knowledge related to the subtask; The execution result is fed back to the target user.

2. The method according to claim 1, characterized in that The target task is split into multiple subtasks by a preset task splitting algorithm, specifically including: Determine the target task based on the task requirements input by the target user; According to the preset task splitting algorithm, determine the task assignment order and effective service period, and generate a task planning plan; According to the task planning scheme, the target task is divided into multiple subtasks.

3. The method according to claim 2, characterized in that The subtasks are arranged according to a preset task arrangement algorithm to realize data transmission between the subtasks, specifically including: Determine the dependencies between subtasks; According to the preset task scheduling algorithm and dependency relationships, the execution order of each subtask is determined to realize data transfer between subtasks.

4. The method according to claim 3, characterized in that According to the task arrangement result, starting from the first subtask, the execution result of the target task is obtained by coordinating the intelligent agent and the knowledge base to perform the task, including: According to the task arrangement results, determine the workflow and the first subtask; Through the coordination agent corresponding to the first subtask, the corresponding knowledge base is called; performing tasks according to the knowledge base; According to the described workflow, starting from the first subtask, the tasks are executed in sequence to determine the execution result of the target task.

5. An intelligent medical consultation device, characterized in that: include: A splitting module is used to split the target task into multiple subtasks by using a preset task splitting algorithm, wherein the target task refers to the task requirement received from the target user input; The scheduling module is used to schedule the subtasks according to a preset task scheduling algorithm to achieve data transmission between the subtasks; A determination module is used to determine the main agent and the coordination agent corresponding to each subtask, wherein the main control agent is used to divide the tasks, and the coordination agent is used to execute the corresponding subtasks; An execution module is used to execute tasks according to the task arrangement results, starting from the first subtask, by coordinating the intelligent agent and the knowledge base to obtain the execution result of the target task, wherein the knowledge base includes business knowledge related to the subtask; The feedback module is used to feed back the execution result to the target user.

6. An electronic device, characterized in that: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 4 when being executed by a processor.

Images