Multi-agent medical intelligent diagnosis method and system based on inference tree structure, electronic equipment and storage medium

Abstract

The invention discloses a multi-agent medical intelligent diagnosis method and system based on an inference tree structure, electronic equipment and a storage medium. The method comprises the steps that a large language model is commanded to simulate multiple specialist physician roles through preset cue words; defining an inference tree structure, and requiring each agent to output a diagnosis result according to the structure; each agent analyzes the medical examination data of the corresponding field to generate a diagnosis result based on an inference tree structure; designing a multi-agent cross validation mechanism, and updating an inference tree through pairwise discussion of agents; and fusing the reasoning trees of all agents, and outputting final diagnosis including a diagnosis conclusion, a reasoning process and clinical evidence. According to the method, medical examination data in different fields are analyzed by utilizing a multi-agent method based on an inference tree structure, so that the diagnosis performance of a complex medical scene is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical intelligent diagnosis, and specifically relates to a multi-agent medical intelligent diagnosis method, system, electronic equipment and storage medium based on an inference tree structure. Background Art

[0002] Medical diagnosis aims to infer and determine a patient's possible illness based on their medical examination data, making it one of the most critical steps in clinical decision-making. With the development of large-scale pre-trained language models (LLMs), medical diagnosis is gradually incorporating intelligent methods. These models leverage their powerful language understanding and reasoning capabilities to assist doctors in disease diagnosis and treatment decisions.

[0003] Most existing large-model-based medical diagnostic methods focus on data processing of a single modality or a single task. For example, some methods focus on inputting medical images into multimodal models to generate corresponding imaging reports and preliminary diagnoses. Such methods usually assume that the input data comes from a single source and the scope of the problem is clear, making it difficult to cope with the multi-dimensionality and high complexity of real-world diagnostic tasks. In real clinical scenarios, patients often have multiple symptoms and a variety of examination methods, which may include multiple medical data such as blood tests, biochemical indicators, imaging examinations, and pathological examinations. Different specialties have different focuses on the same data. This makes medical diagnosis no longer a single judgment task, but an interdisciplinary and cross-modal comprehensive reasoning process. Existing methods find it difficult to effectively integrate and globally reason about multiple types of heterogeneous examination results while ensuring diagnostic accuracy.

[0004] Therefore, there is an urgent need to propose a solution for complex medical diagnostic tasks that can introduce a multi-agent collaborative mechanism, professionally interpret various types of medical examination data, and improve the interpretability and comprehensiveness of the diagnosis through a structured reasoning process, so as to be closer to the diagnosis and treatment needs in real medical practice. Summary of the Invention

[0005] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the existing technology and provide a multi-agent medical intelligent diagnosis method, system, electronic device and storage medium based on an inference tree structure, so as to improve the diagnostic effect in complex medical scenarios through a multi-agent structured interaction method.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a multi-agent medical intelligent diagnosis method based on an inference tree structure, comprising the following steps:

[0008] Use preset prompt words to command the large language model to simulate multiple specialist roles;

[0009] Define the inference tree structure and require each agent to output the diagnosis results according to the structure;

[0010] Each agent analyzes the medical examination data in the corresponding field and generates a diagnosis result based on the inference tree structure;

[0011] Design a multi-agent cross-validation mechanism to update the inference tree through pairwise discussion between agents;

[0012] The reasoning trees of all agents are integrated to output the final diagnosis including the diagnosis conclusion, reasoning process and clinical evidence.

[0013] As a preferred technical solution, the preset prompt word is "You are a doctor who is good at {professional field}. Please give a diagnosis based on the following medical examination data and output it in the form of a tree structure, including the diagnosis results, reasoning process and corresponding clinical medical evidence."

[0014] As a preferred technical solution, the inference tree has a three-layer structure, which is used to represent the diagnostic process of each agent. The inference tree is represented by a triple (c, r, e), where c represents the clinical diagnosis conclusion given by the agent, r represents the reasoning process supporting the diagnosis, and e represents the key clinical medical evidence cited in the diagnosis.

[0015] Each agent A i Generate an inference tree T based on medical examination data D i The process is expressed as:

[0016] T i =LLM(Prompt i ,D)

[0017] Among them, LLM is a large model that outputs diagnostic reasoning by inputting prompt words and patient medical data.

[0018] As a preferred technical solution, the inference tree structure output by the large model is a three-layer structure, representing the diagnosis result, the inference process, and the clinical evidence. Each inference path meets the requirements of logical consistency and evidence sufficiency and is defined by the following function:

[0019] Path(t)={t1→t2→t3|t∈T i}

[0020] Among them, t1, t2, and t3 correspond to the root node, intermediate node, and leaf node in the inference tree respectively.

[0021] As a preferred technical solution, the cross-validation mechanism is specifically as follows:

[0022] Allow any two agents A i With A j A two-way cross-discussion is conducted between the two parties on their respective reasoning paths to determine whether there are conflicts, redundancies or reasoning gaps. The cross-validation function is defined as:

[0023] Review(T i ,T j )→△T i ,△T j

[0024] where △T i and △T j Indicates the update operation of the tree structure after the discussion, which includes the rationality of the conclusion, evidence coverage, and logical consistency.

[0025] As a preferred technical solution, after building the multi-agent workflow, the patient's medical examination data D is input into the system, and the system will connect all agents A i Output inference tree T i Fusion is performed to finally form a unified multi-agent integrated reasoning tree T final , including the main diagnostic conclusions, supporting reasoning paths, and all the clinical medical evidence relied upon. The system completes the diagnosis summary through the following integrated functions:

[0026] T final =Merge(T1,T2,...,T n )

[0027] This enables comprehensive diagnosis of complex diseases.

[0028] In a second aspect, the present invention provides a multi-agent medical intelligent diagnosis system based on an inference tree structure, which is applied to the multi-agent medical intelligent diagnosis method based on an inference tree structure, including a role simulation module, an inference tree construction module, a data analysis module, a cross-validation module, and a fusion output module;

[0029] The role simulation module is used to command the large language model to simulate multiple specialist doctor roles through preset prompt words;

[0030] The inference tree construction module is used to define the inference tree structure and requires each agent to output the diagnosis result according to the structure;

[0031] The data analysis module is used by each agent to analyze the medical examination data in the corresponding field and generate a diagnosis result based on the inference tree structure;

[0032] The cross-validation module is used to design a multi-agent cross-validation mechanism to update the inference tree through pairwise discussion between agents;

[0033] The fusion output module is used to fuse the reasoning trees of all intelligent agents and output the final diagnosis including the diagnosis conclusion, reasoning process and clinical evidence.

[0034] In a third aspect, the present invention provides an electronic device, comprising:

[0035] at least one processor; and,

[0036] a memory communicatively connected to the at least one processor; wherein,

[0037] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the multi-agent medical intelligent diagnosis method based on the inference tree structure.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the multi-agent medical intelligent diagnosis method based on an inference tree structure.

[0039] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0040] 1. This invention utilizes a multi-agent collaborative mechanism, where agents representing different specialist roles divide the work of processing medical data in their respective fields, avoiding the limitations of a single model in processing multimodal information. Through a cross-validation mechanism, agents discuss and revise the inference tree in pairs, effectively identifying and resolving diagnostic conflicts or insufficient evidence, significantly reducing the risk of misdiagnosis and missed diagnoses. Furthermore, the inference tree structure mandates that all diagnostic conclusions be linked to clinical evidence to ensure the credibility of the results.

[0041] 2. This invention uses a three-layer inference tree structure (diagnostic conclusion - reasoning process - clinical evidence) to intuitively display diagnostic logic, allowing doctors to clearly trace the basis for each judgment step. During the cross-validation process, the system dynamically marks conflicting or redundant nodes in the reasoning path and records the reasons for correction, forming a transparent and auditable decision chain. This structured output method significantly improves the interpretability of diagnostic results. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1This is a flow chart of a multi-agent medical intelligent diagnosis method based on an inference tree structure according to an embodiment of the present invention;

[0044] Figure 2 This is a block diagram of a multi-agent medical intelligent diagnosis system based on an inference tree structure according to an embodiment of the present invention.

[0045] Figure 3 2 is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0047] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0048] See also Figure 1 In one embodiment of the present application, a multi-agent medical intelligent diagnosis method based on an inference tree structure is provided, comprising the following steps:

[0049] Step S1: Use preset prompt words to instruct the large language model to simulate multiple specialist roles, specifically:

[0050] Set the preset prompt word Prompt i Input into the large model LLM to simulate different specialist doctor roles i , each Agent i Responsible for different medical professional directions, including Prompt i ="You are a doctor specializing in {professional field}. Please provide a diagnosis based on the following medical examination data and output it in a tree structure, including the diagnosis result, reasoning process, and corresponding clinical medical evidence."

[0051] The Agent set is represented as:

[0052] A={A1,A2,...,A n}

[0053] Where n is the number of agents.

[0054] Step S2: Define the inference tree structure and require each agent to output the diagnosis results according to the structure, specifically:

[0055] The reasoning tree structure is a three-layer tree structure used to represent the diagnostic process of each agent. The structure can be abstracted as a triple (c, r, e), where c represents the clinical diagnosis conclusion given by the agent, r represents the reasoning process supporting the diagnosis, and e represents the key clinical medical evidence cited in the diagnosis. i Generate an inference tree T based on medical examination data D i The process can be expressed as:

[0056] T i =LLM(Prompt i ,D)

[0057] Among them, LLM is a large model that outputs diagnostic reasoning by inputting prompt words and patient medical data.

[0058] Step S3: Each agent analyzes the medical examination data in the corresponding field and generates a diagnosis result based on the inference tree structure, specifically:

[0059] The inference tree structure output by the large model is a three-layer structure, representing the diagnosis result, the reasoning process, and the clinical evidence. Each reasoning path meets the requirements of logical consistency and evidence sufficiency and is defined by the following function:

[0060] Path(t)={t1→t2→t3|t∈T i}

[0061] Among them, t1, t2, and t3 correspond to the root node, intermediate node, and leaf node in the inference tree respectively.

[0062] Step S4: Design a multi-agent cross-validation mechanism to update the inference tree through pairwise discussion among agents. Specifically:

[0063] The cross-validation mechanism allows any two agents A i With A j A two-way cross-discussion is conducted between the two parties on their respective reasoning paths to determine whether there are conflicts, redundancies or reasoning gaps. The cross-validation function is defined as:

[0064] Review(T i ,T j )→△T i ,△T j

[0065] where △T i and △Tj Indicates the update operations performed on the tree structure after the discussion, including the rationality of the conclusion, evidence coverage, logical consistency, etc.

[0066] More specifically, the verification mechanism is as follows: when two agents review the diagnostic nodes of the inference trees Ti and Tj based on their own medical knowledge, if they find mutually exclusive diagnostic results (such as diabetes and hypoglycemia), they activate the conflict marker and update the inference tree.

[0067] Step S5: Integrate the reasoning tree of all agents and output the final diagnosis including the diagnosis conclusion, reasoning process and clinical evidence, specifically:

[0068] After building the multi-agent workflow, the patient’s medical examination data D is input into the system, and the system will send all agents A i Output inference tree T i Fusion is performed to finally form a unified multi-agent integrated reasoning tree T final , including the main diagnostic conclusions, supporting reasoning paths, and all the clinical medical evidence relied upon. The system completes the diagnosis summary through the following integrated functions:

[0069] T final =Merge(T1,T2,...,T n )

[0070] This enables comprehensive diagnosis of complex diseases.

[0071] More specifically, after completing a multi-agent collaborative diagnosis, the system performs a structured fusion of the inference trees output by all agents to generate a unified multi-agent integrated inference tree. First, the nodes of each inference tree are aligned layer by layer according to the diagnostic hierarchy (e.g., symptoms → pathological mechanism → disease diagnosis → treatment plan). Then, all sub-nodes (symptoms, examination indicators, and reasoning basis) under the same diagnostic node (e.g., "diabetes") are merged to form a comprehensive evidence pool.

[0072] It should be noted that, for the sake of convenience, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited to the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously.

[0073] Based on the same concept as the multi-agent medical intelligent diagnosis method based on the inference tree structure in the above-mentioned embodiment, the present invention also provides a multi-agent medical intelligent diagnosis system based on the inference tree structure, which can be used to execute the above-mentioned multi-agent medical intelligent diagnosis method based on the inference tree structure. For ease of explanation, the structural diagram of the embodiment of the multi-agent medical intelligent diagnosis system based on the inference tree structure only shows the parts related to the embodiment of the present invention. Those skilled in the art will understand that the illustrated structure does not constitute a limitation of the device, and it can include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0074] See also Figure 2 In another embodiment of the present application, a multi-agent medical intelligent diagnosis system 100 based on an inference tree structure is provided, the system comprising a role simulation module 101, an inference tree construction module 102, a data analysis module 103, a cross-validation module 104, and a fusion output module 105;

[0075] The role simulation module 101 is used to instruct the large language model to simulate multiple specialist doctor roles through preset prompt words;

[0076] The inference tree construction module 102 is used to define the inference tree structure and require each agent to output the diagnosis result according to the structure;

[0077] The data analysis module 103 is used by each agent to analyze the medical examination data in the corresponding field and generate a diagnosis result based on the inference tree structure;

[0078] The cross-validation module 104 is used to design a multi-agent cross-validation mechanism to update the inference tree through pairwise discussion between agents;

[0079] The fusion output module 105 is used to fuse the reasoning trees of all agents and output a final diagnosis including the diagnosis conclusion, reasoning process and clinical evidence.

[0080] It should be noted that the multi-agent medical intelligent diagnosis system based on the inference tree structure of the present invention corresponds one-to-one to the multi-agent medical intelligent diagnosis method based on the inference tree structure of the present invention. The technical features and beneficial effects described in the above-mentioned embodiment of the multi-agent medical intelligent diagnosis method based on the inference tree structure are all applicable to the embodiment of the multi-agent medical intelligent diagnosis based on the inference tree structure. For specific contents, please refer to the description in the embodiment of the method of the present invention. No further details will be given here. This is hereby declared.

[0081] In addition, in the implementation of the multi-agent medical intelligent diagnosis system based on the inference tree structure in the above embodiment, the logical division of each program module is only an example. In actual application, the above functions can be assigned to different program modules as needed, for example, for the configuration requirements of the corresponding hardware or the convenience of software implementation. That is, the internal structure of the multi-agent medical intelligent diagnosis system based on the inference tree structure is divided into different program modules to complete all or part of the functions described above.

[0082] See also Figure 3 In one embodiment, an electronic device for implementing a multi-agent medical intelligent diagnosis method based on an inference tree structure is provided. The electronic device 200 may include a first processor 201, a first memory 202 and a bus, and may also include a computer program stored in the first memory 202 and executable on the first processor 201, such as a multi-agent medical intelligent diagnosis program 203 based on an inference tree structure.

[0083] The first memory 202 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the first memory 202 may be an internal storage unit of the electronic device 200, such as a mobile hard disk of the electronic device 200. In other embodiments, the first memory 202 may also be an external storage device of the electronic device 200, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 200. Furthermore, the first memory 202 may include both an internal storage unit of the electronic device 200 and an external storage device. The first memory 202 can be used not only to store application software and various types of data installed in the electronic device 200, such as the code of the multi-agent medical intelligent diagnosis program 203 based on the inference tree structure, but also to temporarily store data that has been output or is about to be output.

[0084] In some embodiments, the first processor 201 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The first processor 201 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and lines, and executing or executing programs or modules stored in the first memory 202, as well as calling data stored in the first memory 202, to perform various functions of the electronic device 200 and process data.

[0085] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 200 , and the electronic device 200 may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0086] The multi-agent medical intelligent diagnosis program 203 based on the inference tree structure stored in the first memory 202 of the electronic device 200 is a combination of multiple instructions. When running in the first processor 201, it can achieve the following:

[0087] Use preset prompt words to command the large language model to simulate multiple specialist roles;

[0088] Define the inference tree structure and require each agent to output the diagnosis results according to the structure;

[0089] Each agent analyzes the medical examination data in the corresponding field and generates a diagnosis result based on the inference tree structure;

[0090] Design a multi-agent cross-validation mechanism to update the inference tree through pairwise discussion between agents;

[0091] The reasoning trees of all agents are integrated to output the final diagnosis including the diagnosis conclusion, reasoning process and clinical evidence.

[0092] Furthermore, if the modules / units integrated in the electronic device 200 are implemented as software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0093] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0094] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be considered as equivalent replacement methods and are included in the scope of protection of the present invention.

Claims

1. A multi-agent medical intelligent diagnosis method based on an inference tree structure, characterized in that: The steps include: Use preset prompt words to command the large language model to simulate multiple specialist roles; Define the inference tree structure and require each agent to output the diagnosis results according to the structure; Each agent analyzes the medical examination data in the corresponding field and generates a diagnosis result based on the inference tree structure; Design a multi-agent cross-validation mechanism to update the inference tree through pairwise discussion between agents; The reasoning trees of all agents are integrated to output the final diagnosis including the diagnosis conclusion, reasoning process and clinical evidence.

2. The multi-agent medical intelligent diagnosis method based on the inference tree structure according to claim 1 is characterized in that: The preset prompt word is "You are a doctor who is good at {professional field}. Please give a diagnosis based on the following medical examination data and output it in the form of a tree structure, including the diagnosis results, reasoning process and corresponding clinical medical evidence." 3. The multi-agent medical intelligent diagnosis method based on the inference tree structure according to claim 1 is characterized in that: The inference tree has a three-layer structure, which is used to represent the diagnostic process of each agent. The inference tree is represented by a triple (c, r, e), where c represents the clinical diagnosis conclusion given by the agent, r represents the reasoning process supporting the diagnosis, and e represents the key clinical medical evidence cited in the diagnosis. Each agent A i Generate an inference tree T based on medical examination data D i The process is expressed as: T i =LLM(Prompt i ,D) Among them, LLM is a large model that outputs diagnostic reasoning by inputting prompt words and patient medical data.

4. The multi-agent medical intelligent diagnosis method based on the inference tree structure according to claim 1 is characterized in that: The inference tree structure output by the large model is a three-layer structure, representing the diagnosis result, the reasoning process, and the clinical evidence. Each reasoning path meets the requirements of logical consistency and evidence sufficiency and is defined by the following function: Path(t)={t1→t2→t3|t∈T i } Among them, t1, t2, and t3 correspond to the root node, intermediate node, and leaf node in the inference tree respectively.

5. The multi-agent medical intelligent diagnosis method based on the inference tree structure according to claim 1 is characterized in that: The cross-validation mechanism is specifically as follows: Allow any two agents A i With A j A two-way cross-discussion is conducted between the two parties on their respective reasoning paths to determine whether there are conflicts, redundancies or reasoning gaps. The cross-validation function is defined as: Review(T i ,T j )→△T i ,△T j where △T i and △T j Indicates the update operation of the tree structure after the discussion, which includes the rationality of the conclusion, evidence coverage, and logical consistency.

6. The multi-agent medical intelligent diagnosis method based on the inference tree structure according to claim 1 is characterized in that: After building the multi-agent workflow, the patient’s medical examination data D is input into the system, and the system will send all agents A i Output inference tree T i Fusion is performed to finally form a unified multi-agent integrated reasoning tree T final , including the main diagnostic conclusions, supporting reasoning paths, and all the clinical medical evidence relied upon. The system completes the diagnosis summary through the following integrated functions: T final =Merge(T1,T2,...,T n ) This enables comprehensive diagnosis of complex diseases.

7. A multi-agent medical intelligent diagnosis system based on an inference tree structure, characterized by: The multi-agent medical intelligent diagnosis method based on the inference tree structure applied to any one of claims 1-6 comprises a role simulation module, an inference tree construction module, a data analysis module, a cross-validation module and a fusion output module; The role simulation module is used to command the large language model to simulate multiple specialist doctor roles through preset prompt words; The inference tree construction module is used to define the inference tree structure and requires each agent to output the diagnosis result according to the structure; The data analysis module is used by each agent to analyze the medical examination data in the corresponding field and generate a diagnosis result based on the inference tree structure; The cross-validation module is used to design a multi-agent cross-validation mechanism to update the inference tree through pairwise discussion between agents; The fusion output module is used to fuse the reasoning trees of all intelligent agents and output the final diagnosis including the diagnosis conclusion, reasoning process and clinical evidence.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the multi-agent medical intelligent diagnosis method based on the inference tree structure as described in any one of claims 1-6.

9. A computer-readable storage medium storing a program, characterized in that: When the program is executed by a processor, the multi-agent medical intelligent diagnosis method based on the inference tree structure described in any one of claims 1 to 6 is implemented.

Images