CN-120106078-B - Automatic event handling method, device and system based on semantic analysis

CN120106078BCN 120106078 BCN120106078 BCN 120106078BCN-120106078-B

Abstract

The invention provides an event automatic handling method, device and system based on semantic analysis, which relate to the technical field of semantic analysis and comprise the steps of acquiring reported information; the method comprises the steps of determining semantic complete characteristics, event emergency characteristics and reporting time characteristics based on reporting information, determining recall priority parameters based on the semantic complete characteristics and the event emergency characteristics, determining correction strategies according to the magnitude relation between the semantic complete characteristics and a complete threshold value, determining coarse ranking priority parameters based on the correction strategies and the recall priority parameters, determining target priority parameters based on the coarse ranking priority parameters and the reporting time characteristics, and determining event handling sequences based on the target priority parameters. The method introduces comprehensive judgment on the semantic integrity and accuracy of the reported information, and makes up the defect that the related technology only depends on emergency degree assessment, thereby improving the accuracy and comprehensiveness of information processing.

Inventors

MENG CHAO
DING CHUNLEI
LI SHUHUA
JIN JINFEI
LI QIANWEN

Assignees

浙江物芯数科信息产业有限公司

Dates

Publication Date: 20260505
Application Date: 20250226

Claims (9)

1. An automatic event handling method based on semantic analysis, comprising: acquiring reporting information; Determining semantic complete characteristics, event emergency characteristics and reporting time characteristics based on the reporting information; Determining recall priority parameters based on the semantic integrity features and the event emergency features; Determining a correction strategy according to the size relation between the semantic integral features and the integral threshold; determining coarse prioritization parameters based on the correction strategy and the recall prioritization parameters; determining a target priority parameter based on the coarse prioritization parameter and the reporting time feature; Determining an event handling sequence based on the target priority parameter; The determining a target priority parameter based on the coarse prioritization parameter and the reporting time feature includes: determining a time interval based on the difference between the reported time characteristic and the current time; Determining an event treatment plan period based on the coarse prioritization parameters, wherein the event treatment plan period includes a low interval period, an intermediate interval period, and a high interval period; determining a time adjustment factor based on a ratio of the time interval to the event treatment plan period; The target priority parameter is determined based on the coarse prioritization parameter and the time adjustment factor.
2. The automatic event handling method based on semantic analysis according to claim 1, wherein the determining a correction strategy according to the magnitude relation between the semantic integrity features and the integrity threshold value comprises: responsive to the semantic integrity feature being less than the integrity threshold; Based on the reported information, acquiring supplementary information according to a large language model; Determining a first correction parameter based on the supplemental information; Determining the coarse prioritization parameters based on the first correction parameters and the recall prioritization parameters; Responding to the situation that the semantic integrity feature is larger than or equal to the integrity threshold value; Based on the reported information, acquiring subjective judgment information according to a large language model; Determining a second correction parameter based on the subjective judgment information; And determining the coarse prioritization parameter based on the second correction parameter and the recall prioritization parameter.
3. The automatic event handling method based on semantic analysis according to claim 2, wherein the supplementary information includes time information, location information and event information; the determining a first correction parameter based on the supplemental information includes: determining a time difference factor based on the difference between the time information and the reported time characteristic; determining a location score factor according to a preset location list map based on the location information; Determining an event score factor according to a preset event list map based on the event information; determining the first correction parameter based on the time difference factor, the location score factor, and the event score factor, wherein, In the formula, As a first correction parameter, As a time difference factor, As a point score factor, As a factor of the score of an event, Respectively, their corresponding weight values.
4. The automatic event handling method based on semantic analysis according to claim 2, wherein the subjective judgment information includes an aging score factor and an influence score factor; the determining a second correction parameter based on the subjective judgment information includes: And determining the second correction parameter based on the average of the aging score factor and the influence score factor.
5. The automatic event handling method based on semantic analysis according to claim 1, wherein determining semantic integrity features based on the reported information comprises: Based on the reported information, acquiring coding information according to a coding model; Acquiring decoding information according to a decoding model associated with the coding model based on the coding information; determining semantic similarity based on the decoding information and the encoding information; Based on a preset language standard structure, determining semantic integrity according to the reported information; And determining the semantic integrity features according to the semantic similarity and the semantic integrity.
6. The automatic event handling method based on semantic analysis according to claim 5, wherein the preset language standard structure comprises a time field, a person field, a place field and an event field; the determining the semantic integrity based on the preset language standard structure according to the report information comprises the following steps: Extracting keywords based on the reported information; Judging matching degree sets of the keywords in a time field, a character field, a place field and an event field respectively; and determining the semantic integrity based on the matching degree set.
7. The automatic event handling method based on semantic analysis according to claim 1, wherein determining an event emergency feature based on the reported information comprises: constructing an event handling knowledge graph based on the historical reporting information and the historical handling result; Based on the reporting information, determining associated reporting information matched with the event handling knowledge graph according to the event handling knowledge graph; Determining an association treatment result based on the association reporting information; The event emergency feature is determined based on the associated treatment results.
8. An automatic event handling device based on semantic analysis, characterized in that it applies a method for automatic event handling based on semantic analysis according to any one of claims 1 to 7, comprising: The acquisition module is used for acquiring the reported information; The analysis module is used for determining semantic complete characteristics, event emergency characteristics and reporting time characteristics based on the reporting information, determining recall priority parameters based on the semantic complete characteristics and the event emergency characteristics, determining correction strategies according to the magnitude relation between the semantic complete characteristics and a complete threshold value, determining coarse priority parameters based on the correction strategies and the recall priority parameters, determining target priority parameters based on the coarse priority parameters and the reporting time characteristics, and determining time intervals based on the difference between the reporting time characteristics and the current time, determining event treatment plan periods based on the coarse priority parameters, wherein the event treatment plan periods comprise low interval periods, middle interval periods and high interval periods, determining time adjustment factors based on the ratio of the time intervals to the event treatment plan periods, and determining the target priority parameters based on the coarse priority parameters and the time adjustment factors; A handling module for determining an event handling sequence based on the target priority parameter.
9. An automatic event handling system based on semantic analysis, comprising a processor and a memory communicatively coupled to the processor, the memory storing instructions executable by the processor, the instructions when executed by the processor implementing the steps of an automatic event handling method based on semantic analysis as claimed in any one of claims 1 to 7.

Description

Automatic event handling method, device and system based on semantic analysis Technical Field The present invention relates to the field of semantic analysis technologies, and in particular, to a method, an apparatus, and a system for automatically handling events based on semantic analysis. Background With the development of society and the advancement of information technology, the demand for automatic disposal of various emergency events is increasing, such as natural disasters, public safety events, sudden technical failures, and the like. The rapid response and efficient handling of these events is critical in ensuring social stability. However, due to the diversity and complexity of the reported information, the receiving, analyzing and prioritizing of the events only depends on manual work, which has the problems of low efficiency and high risk of erroneous judgment. Therefore, automatic handling of events using artificial intelligence and semantic analysis techniques has become an important point of research and development. Related art when handling reporting events, simple keyword matching and preset rules are typically relied upon to determine the type and urgency of the event. This approach tends to be frustrating in the face of complex or ambiguous information and makes it difficult to accurately determine the priority of an event, resulting in response delays and mishandling. That is, most of the treatment methods in the related art only can determine the emergency degree of the event based on the report information, which cannot determine the accuracy and the integrity of the report information, and cannot adjust the event treatment strategy or the event treatment sequence according to the report time, which is easy to cause delay and improper treatment. Therefore, a method, apparatus and system for automatically handling events based on semantic analysis are needed. Disclosure of Invention The invention provides an event automatic handling method based on semantic analysis, which comprises the following steps: acquiring reporting information; Determining semantic complete characteristics, event emergency characteristics and reporting time characteristics based on the reporting information; determining recall priority parameters based on the semantic integrity features and the event emergency features; Determining a correction strategy according to the size relation between the semantic integral features and the integral threshold; determining coarse-ranking priority parameters based on the correction strategy and recall priority parameters; determining a target priority parameter based on the coarse priority parameter and the reporting time characteristic; Based on the target priority parameters, an event handling sequence is determined. Further, determining a correction strategy according to the magnitude relation between the semantic integrity features and the integrity threshold value comprises the following steps: Responsive to the semantic integrity feature being less than an integrity threshold; based on the reported information, acquiring supplementary information according to the large language model; determining a first correction parameter based on the supplemental information; determining coarse ranking priority parameters based on the first correction parameters and recall priority parameters; responding to the fact that the semantic integrity feature is larger than or equal to an integrity threshold value; based on the reported information, acquiring subjective judgment information according to the large language model; Determining a second correction parameter based on the subjective judgment information; And determining a coarse prioritization parameter based on the second correction parameter and the recall prioritization parameter. Further, the supplementary information includes time information, location information, and event information; determining a first correction parameter based on the supplemental information, comprising: determining a time difference factor based on the difference between the time information and the reported time characteristic; determining a location score factor according to a preset location list map based on the location information; Determining an event score factor according to a preset event list map based on the event information; determining a first correction parameter based on the time difference factor, the location score factor, and the event score factor, wherein, In the formula,As a first correction parameter,As a time difference factor,As a point score factor,As a factor of the score of an event,Respectively, their corresponding weight values. Further, the subjective judgment information comprises an aging score factor and an influence score factor; determining a second correction parameter based on the subjective judgment information, including: and determining a second correction parameter based on the average of the age score fa