CN-122025198-A - Method, device, computer equipment, readable storage medium and program product for generating monitoring and early warning report of public health event

CN122025198ACN 122025198 ACN122025198 ACN 122025198ACN-122025198-A

Abstract

The application relates to a method, a device, computer equipment, a computer readable storage medium and a computer program product for generating a monitoring and early warning report of public health events, which relate to the field of public health monitoring and can improve the detection and early warning efficiency of public health events. The method comprises the steps of obtaining a monitoring and early-warning request aiming at a public health event, wherein the monitoring and early-warning request indicates a monitoring and early-warning target aiming at the public health event, responding to the monitoring and early-warning request, obtaining a plurality of subtasks related to the monitoring and early-warning target, determining a plurality of agents, wherein each agent corresponds to a corresponding subtask, obtaining multi-source heterogeneous data of each subtask through the plurality of agents in parallel, determining a subtask result corresponding to the subtask according to the multi-source heterogeneous data of the subtask corresponding to the agent aiming at each agent, and generating a monitoring and early-warning report based on each subtask result.

Inventors

ZHOU LU
CHEN YIPING
XIAO QINGYU
LIU HENGSHEN
YANG KAIXIN
GUO BOWEN
MIAO YIBO
LUO JUNYU
CHEN ZIRU
LI YIXUE

Assignees

广州国家实验室

Dates

Publication Date: 20260512
Application Date: 20260115

Claims (10)

1. A method for generating a monitoring and early warning report of a public health event, the method comprising: Acquiring a monitoring and early-warning request aiming at a public health event, wherein the monitoring and early-warning request indicates a monitoring and early-warning target aiming at the public health event; Responding to the monitoring and early warning request, acquiring a plurality of subtasks related to the monitoring and early warning target, and determining a plurality of intelligent agents, wherein each intelligent agent corresponds to the corresponding subtask; Acquiring the multi-source heterogeneous data of each of a plurality of subtasks in parallel through a plurality of agents; aiming at each intelligent agent, determining a subtask result corresponding to the subtask by the intelligent agent according to the multi-source heterogeneous data of the subtask corresponding to the intelligent agent; And generating a monitoring and early warning report based on the subtask results.
2. The method of claim 1, wherein the obtaining a plurality of sub-tasks related to the monitoring and pre-warning target in response to the monitoring and pre-warning request comprises: Responding to the monitoring and early warning request, and carrying out ambiguity verification on the monitoring and early warning request; generating a clarification question aiming at the fuzzy information under the condition that the fuzzy verification result indicates that the monitoring and early warning request contains the fuzzy information; And determining a plurality of subtasks related to the monitoring and early warning target according to feedback information of the user on the clarification question and the monitoring and early warning request.
3. The method of claim 1, wherein the obtaining, by a plurality of the agents, the multi-source heterogeneous data for each of the plurality of the subtasks in parallel, comprises: respectively acquiring a plurality of data acquisition tools corresponding to the intelligent agents from a preset tool library through a plurality of tool calling interfaces of the intelligent agents in parallel; And acquiring the multi-source heterogeneous data of each of the plurality of subtasks by using a plurality of data acquisition tools, wherein the multi-source heterogeneous data comprises at least one of epidemiological data, public health data and literature abstract data.
4. The method of claim 1, wherein the plurality of agents comprises a first agent, a second agent, and a third agent; The determining, by the agent, a subtask result corresponding to the subtask according to the multi-source heterogeneous data of the subtask corresponding to the agent, including: The first agent performs epidemiological characteristic analysis according to epidemiological data of the subtasks corresponding to the first agent to obtain a first subtask result; the second intelligent agent performs pathogen evolution characteristic analysis according to public health data of the subtasks corresponding to the second intelligent agent to obtain a second subtask result; the third agent performs public health risk analysis according to the document abstract data of the subtask corresponding to the third agent to obtain a third subtask result; And obtaining a plurality of subtask results according to the first subtask result, the second subtask result and the third subtask result.
5. The method of claim 4, wherein generating a monitoring and early warning report based on each of the subtask results comprises: the method comprises the steps of obtaining a preset monitoring early warning report template, wherein the monitoring early warning report template comprises an epidemiological characteristic plate, a pathogen evolution plate and a public health risk plate; Determining an explanatory text corresponding to the public health risk based on a third subtask result of public health risk analysis; Adding the first subtask result to the epidemiological feature board; adding the second subtask result to the pathogen evolution panel; Adding the third subtask result and the explanatory text corresponding to the public health risk plate; And obtaining the monitoring and early warning report based on the added epidemiological characteristic plate, pathogen evolution plate and public health risk plate.
6. The method of claim 1, wherein generating a monitoring and early warning report based on each of the subtask results, further comprises: in the process of generating the monitoring early warning report, acquiring data source information corresponding to the multi-source heterogeneous data by the intelligent agent; And generating a monitoring and early warning report based on the subtask result and the data source information.
7. The method of claim 6, wherein generating a monitoring and early warning report based on the subtask results and the data source information comprises: Determining a tracing evidence chain of the multi-source heterogeneous data based on the data source information; and adding the trace source evidence chain and the reference information corresponding to the trace source evidence chain into the monitoring and early warning report.
8. The method according to any one of claims 1 to 7, wherein the multi-source heterogeneous data is in the form of structured, the structured multi-source heterogeneous data being determined by: Determining a monitoring area and a monitoring period based on the monitoring early warning request by the intelligent agent, and determining a target time scale and a target geographic scale based on the monitoring area and the monitoring period; Respectively normalizing the time attribute and the space attribute of the multi-source heterogeneous data to the target time scale and the target geographic scale to obtain multi-source heterogeneous data with aligned time-space dimensions; and generating the structured multi-source heterogeneous data based on the multi-source heterogeneous data with the aligned space-time dimensions.
9. A monitoring and early warning report generating device for public health events, the device comprising: The monitoring and early warning triggering module is used for acquiring a monitoring and early warning request aiming at a public health event, wherein the monitoring and early warning request indicates a monitoring and early warning target aiming at the public health event; the task decomposition module is used for responding to the monitoring and early warning request, acquiring a plurality of subtasks related to the monitoring and early warning target and determining a plurality of agents, wherein each agent corresponds to the corresponding subtask; The heterogeneous data acquisition module is used for acquiring the multi-source heterogeneous data of each of the subtasks in parallel through a plurality of agents; The task analysis module is used for determining a subtask result corresponding to the subtask according to the multi-source heterogeneous data of the subtask corresponding to the intelligent agent by the intelligent agent aiming at each intelligent agent; and the report generation module is used for generating a monitoring and early warning report based on the subtask results.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any one of claims 1 to 8.

Description

Method, device, computer equipment, readable storage medium and program product for generating monitoring and early warning report of public health event Technical Field The present application relates to the technical field of public health monitoring, and in particular, to a method, an apparatus, a computer device, a computer readable storage medium and a computer program product for generating a monitoring and early warning report of a public health event. Background With the development of the global public health system, the method aims at continuous monitoring and risk prognosis of pathogens such as influenza virus, SARS-CoV-2, RSV and the like, and has important significance for public health decision and virus response. In the conventional technology, production of monitoring reports for pathogens mainly depends on manual or semi-automatic scripting tools, specifically, researchers need to manually acquire monitoring data, and combine professional knowledge to perform trend judgment and text writing. However, since the data acquisition and processing flows in the above manner are mainly performed serially or manually, the data aggregation efficiency is low, and thus the report generation efficiency is very low. Disclosure of Invention In view of the foregoing, it is desirable to provide a method, apparatus, computer device, computer readable storage medium, and computer program product for generating a monitoring and early warning report of a public health event. In a first aspect, the present application provides a method for generating a monitoring and early warning report of a public health event, including: Responding to the monitoring and early warning request, acquiring a plurality of subtasks related to the monitoring and early warning target and determining a plurality of intelligent agents, wherein each intelligent agent corresponds to the corresponding subtask; Acquiring the multi-source heterogeneous data of each of a plurality of subtasks in parallel through a plurality of agents; aiming at each intelligent agent, determining a subtask result corresponding to the subtask by the intelligent agent according to the multi-source heterogeneous data of the subtask corresponding to the intelligent agent; And generating a monitoring and early warning report based on the subtask results. In one embodiment, the responding to the monitoring and early warning request, acquiring a plurality of subtasks related to the monitoring and early warning target, includes: Responding to the monitoring and early warning request, and carrying out ambiguity verification on the monitoring and early warning request; generating a clarification question aiming at the fuzzy information under the condition that the fuzzy verification result indicates that the monitoring and early warning request contains the fuzzy information; And determining a plurality of subtasks related to the monitoring and early warning target according to feedback information of the user on the clarification question and the monitoring and early warning request. In one embodiment, the obtaining, by the plurality of agents, the multi-source heterogeneous data of each of the plurality of subtasks in parallel includes: respectively acquiring a plurality of data acquisition tools corresponding to the intelligent agents from a preset tool library through a plurality of tool calling interfaces of the intelligent agents in parallel; And acquiring the multi-source heterogeneous data of each of the plurality of subtasks by using a plurality of data acquisition tools, wherein the multi-source heterogeneous data comprises at least one of epidemiological data, public health data and literature abstract data. In one embodiment, before the determining, by the agent, the subtask result corresponding to the subtask according to the multi-source heterogeneous data of the subtask corresponding to the agent, the method further includes: Determining a monitoring area and a monitoring period based on the monitoring early warning request by the intelligent agent, and determining a target time scale and a target geographic scale based on the monitoring area and the monitoring period; Respectively normalizing the time attribute and the space attribute of the multi-source heterogeneous data to the target time scale and the target geographic scale to obtain multi-source heterogeneous data with aligned time-space dimensions; and generating structured multi-source heterogeneous data based on the multi-source heterogeneous data with the aligned space-time dimensions. In one embodiment, the plurality of agents includes a first agent, a second agent, and a third agent; The determining, by the agent, a subtask result corresponding to the subtask according to the multi-source heterogeneous data of the subtask corresponding to the agent, including: The first agent performs epidemiological characteristic analysis according to epidemiological data of the subtasks corresponding to