CN-122025080-A - Auxiliary diagnosis method, device, equipment and storage medium based on multiple intelligent agents

CN122025080ACN 122025080 ACN122025080 ACN 122025080ACN-122025080-A

Abstract

The application discloses an auxiliary diagnosis method, device, equipment and storage medium based on multiple intelligent agents, wherein the method comprises the steps of obtaining illness state information of a user; based on the illness state information, a plurality of target intelligent agent modules are determined from the multi-intelligent agent system to diagnose the illness state information, and an auxiliary diagnosis result is obtained. The application can select and call a plurality of different intelligent agent modules to complete the diagnosis of the user by combining the illness state information of the user, so as to improve the diagnosis efficiency or effect of the patient.

Inventors

XIAO YUETING
YANG GUANG
ZHENG CHAO
MAO XINSHENG

Assignees

数坤科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20251231

Claims (12)

1. An auxiliary diagnosis method based on multiple intelligent agents, which is characterized by being applied to a multiple intelligent agent system, wherein the multiple intelligent agent system comprises a plurality of intelligent agent modules, and the method comprises the following steps: acquiring illness state information of a user; And determining a plurality of target intelligent agent modules from the multi-intelligent agent system to diagnose the illness state information based on the illness state information, and obtaining an auxiliary diagnosis result of the user.
2. The method of claim 1, wherein determining, from the multi-agent system, a plurality of target agent modules to diagnose the condition information based on the condition information comprises: And sequentially determining a plurality of target intelligent agent modules from the multi-intelligent agent system based on the illness state information so as to sequentially diagnose the illness state information.
3. The method of claim 2, wherein sequentially determining a plurality of target agent modules from the multi-agent system based on the condition information to sequentially diagnose the condition information comprises: Determining a first target intelligent agent module from the multi-intelligent agent system based on the illness state information, and diagnosing through the first target intelligent agent module to obtain first auxiliary diagnosis information; Determining a second target intelligent agent module from the multi-intelligent agent system based on the first auxiliary diagnosis information and the illness state information, and diagnosing through the second target intelligent agent module to obtain second auxiliary diagnosis information; A third target agent module is determined from the multi-agent system based on the first auxiliary diagnostic information, the second auxiliary diagnostic information, and the condition information, or an auxiliary diagnostic result of the user is determined based on the first auxiliary diagnostic information, the second auxiliary diagnostic information, and the condition information.
4. The method of claim 3, wherein the determining a second target agent module from the multi-agent system based on the first auxiliary diagnostic information and the condition information comprises: A second target agent module is determined from the multi-agent system based on the first auxiliary diagnostic information and the condition information, and based on a reference agent module determined by a preset diagnostic procedure.
5. The method of claim 1, wherein the agent module comprises an agent detection module and an agent diagnostic module; The determining, from the multi-agent system, a plurality of target agent modules to diagnose the condition information includes: Performing auxiliary detection on the user through an intelligent agent detection module in the intelligent agent module to obtain auxiliary detection information of the user; and diagnosing the auxiliary detection information and the illness state information through an agent diagnosis module in the agent module to obtain auxiliary diagnosis information of the user, so as to determine an auxiliary diagnosis result of the user.
6. The method of claim 1, wherein the multi-agent system comprises a plurality of agent modules of different modalities for diagnosing information of different modalities, wherein the modalities comprise at least one of text, audio, and images.
7. The method of claim 1, wherein obtaining the auxiliary diagnostic result of the user comprises fusing the auxiliary diagnostic information obtained by each target agent module to obtain fused diagnostic information; performing rationality verification on the fusion diagnosis information through a trained verification agent module; And outputting an initial diagnosis report containing auxiliary diagnosis results based on the fused diagnosis information under the condition that the rationality verification of the fused diagnosis information is passed.
8. The method of claim 7, wherein the method further comprises: and writing logic adjustment to the content in the initial diagnosis report to obtain a target diagnosis report.
9. The method according to any one of claims 1-8, further comprising: And displaying the prompt information of the target intelligent agent modules on the terminal equipment of the user so as to guide the user to visit.
10. An auxiliary diagnostic device based on multiple agents, which is applied to a multiple agent system, wherein the multiple agent system comprises multiple agent modules, the device comprising: the acquisition module is used for acquiring illness state information of a user; And the auxiliary diagnosis module is used for determining a plurality of target intelligent agent modules from the multi-intelligent agent system to diagnose the illness state information based on the illness state information, and obtaining an auxiliary diagnosis result of the user.
11. A computer device, the computer device comprising: one or more processors; Memory, and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the multi-agent based auxiliary diagnostic method of any one of claims 1 to 9.
12. A computer-readable storage medium, having stored thereon a computer program, the computer program being loaded by a processor to perform the multi-agent based auxiliary diagnostic method of any one of claims 1 to 9.

Description

Auxiliary diagnosis method, device, equipment and storage medium based on multiple intelligent agents Technical Field The application relates to the technical field of medical diagnosis, in particular to an auxiliary diagnosis method, device and equipment based on multiple intelligent agents and a storage medium. Background Hospital informatization comprehensively applies information science and computer technology to medical science and medical and health care industry management, and realizes medical modernization by carrying out technical improvement on the traditional medical and health care industry. However, in the process of diagnosing by the user, there is often a process of diagnosing according to a fixed procedure set in each hospital, for example, a procedure generally including inquiry, examination, review, secondary examination, and the like, resulting in low diagnosis efficiency for the patient. Disclosure of Invention The application provides an auxiliary diagnosis method, device, equipment and storage medium based on multiple intelligent agents, which can assist a user to diagnose at least partially, thereby improving the diagnosis efficiency of a patient. In a first aspect, the present application provides a multi-agent-based auxiliary diagnosis method, applied to a multi-agent system, where the multi-agent system includes a plurality of agent modules, the method includes: acquiring illness state information of a user; And determining a plurality of target intelligent agent modules from the multi-intelligent agent system to diagnose the illness state information based on the illness state information, and obtaining an auxiliary diagnosis result of the user. In one embodiment of the present application, the determining, from the multi-agent system, a plurality of target agent modules to diagnose the condition information based on the condition information includes: And sequentially determining a plurality of target intelligent agent modules from the multi-intelligent agent system based on the illness state information so as to sequentially diagnose the illness state information. In one embodiment of the present application, the sequentially determining a plurality of target agent modules from the multi-agent system based on the condition information to sequentially diagnose the condition information includes: Determining a first target intelligent agent module from the multi-intelligent agent system based on the illness state information, and diagnosing through the first target intelligent agent module to obtain first auxiliary diagnosis information; Determining a second target intelligent agent module from the multi-intelligent agent system based on the first auxiliary diagnosis information and the illness state information, and diagnosing through the second target intelligent agent module to obtain second auxiliary diagnosis information; A third target agent module is determined from the multi-agent system based on the first auxiliary diagnostic information, the second auxiliary diagnostic information, and the condition information, or an auxiliary diagnostic result of the user is determined based on the first auxiliary diagnostic information, the second auxiliary diagnostic information, and the condition information. In one embodiment of the present application, the determining a second target agent module from the multi-agent system based on the first auxiliary diagnostic information and the condition information includes: A second target agent module is determined from the multi-agent system based on the first auxiliary diagnostic information and the condition information, and based on a reference agent module determined by a preset diagnostic procedure. In one embodiment of the application, the agent module includes an agent detection module and an agent diagnostic module; The determining, from the multi-agent system, a plurality of target agent modules to diagnose the condition information includes: performing auxiliary detection on the user through an intelligent agent detection module in the multi-intelligent agent system to obtain auxiliary detection information of the user; And diagnosing the auxiliary detection information and the illness state information through an intelligent agent diagnosis module in the multi-intelligent agent system to obtain auxiliary diagnosis information of the user, so as to determine an auxiliary diagnosis result of the user. In one embodiment of the application, the multi-agent system comprises a plurality of agent modules of different modalities for diagnosing information of different modalities, wherein the modalities comprise at least one of text, audio and images. In one embodiment of the application, the obtaining of the auxiliary diagnosis result of the user includes fusing the auxiliary diagnosis information obtained through each target intelligent agent module to obtain fused diagnosis information; performing rationality verification on the fu