Sequence prediction method and device based on large language model and time knowledge graph

By constructing a temporal knowledge graph and using temporal random walks and a large language model to generate prompt templates, the problem of insufficient generalization ability of the temporal knowledge graph in complex scenarios is solved, and more accurate prediction of future events is achieved.

CN120670600APending Publication Date: 2025-09-19SHENZHEN PINGAN COMM TECH CO LTD
5 Cites 0 Cited by

Patent Information

Application Number
CN202510704210.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-28
Publication Date
2025-09-19

AI Technical Summary

Technical Problem

Existing temporal knowledge graph methods lack cross-domain and cross-time generalization capabilities when processing complex temporal relationship data. Especially in scenarios such as property insurance and intelligent diagnosis and treatment, traditional methods ignore the semantic information of events, resulting in insufficient prediction performance.

Method used

By constructing a temporal knowledge graph and applying the transition distribution formula of temporal random walk to generate paths with time information, the paths are analyzed to obtain temporal patterns and converted into temporal logic rules, and combined with a large language model to generate prompt templates to predict future events.

Benefits of technology

The cross-domain and cross-time generalization capabilities of the temporal knowledge graph are improved, and the generated results are more accurate and suitable for prediction tasks in different data sets and fields.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of knowledge maps, and discloses an event prediction method and device based on a time knowledge map and a large language model, and the method comprises the steps: carrying out the migration in a directed graph of the time knowledge map through employing a transition distribution formula of time random migration, and generating a path with time information; analyzing the path with the time information to obtain a time pattern of which the occurrence frequency is greater than or equal to a preset time threshold value, converting the time pattern into a time logic rule, and storing the time logic rule to obtain a time logic rule base; and selecting a time logic rule from the time logic rule base according to the current occurrence event to generate a large language model generation prompt template, and generating the prompt template according to the large language model generation prompt template to predict an event possibly occurring in the future. When the method is applied to time knowledge maps with complex data scales such as financial insurance and intelligent diagnosis and treatment, the cross-domain and cross-time generalization ability of the time knowledge maps of the type can be improved.
Need to check novelty before this filing date? Find Prior Art