A method for generating enterprise information tags based on enterprise profiles

By normalizing the subject and organizing the time window of multi-source enterprise profile data, and combining candidate tag template matching and relationship consistency analysis, interpretable enterprise information tags are generated. This solves the problem of insufficient accuracy and interpretability of tag generation in existing technologies, and realizes an accurate portrayal of the phased changes of technology-based SMEs.

CN122199007BActive Publication Date: 2026-11-10NANCHANG TRANSPORTATION COLLEGE
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202610660507.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-05-14
Publication Date
2026-11-10
Estimated Expiration
2046-05-14

AI Technical Summary

Technical Problem

Existing technologies rely heavily on single-point-of-time fields and static rules when generating information tags for technology-based SMEs. This makes it difficult to accurately depict the phased changes in the enterprise's status, easily misjudging short-term fluctuations as long-term characteristics. Furthermore, the lack of utilization of upstream and downstream collaboration and industrial chain relationships leads to high tag conflict rates and insufficient interpretability and reference value.

Method used

By acquiring multi-source enterprise profile data, performing subject normalization processing and time window organization, extracting stable results of time windows, conducting candidate label template matching and relationship consistency analysis, and generating interpretable enterprise information label results, including subject alignment, time-series profile fragment set, candidate label set, joint calculation of direct evidence and relationship evidence, and conflict resolution.

Benefits of technology

It improves the accuracy of label judgment, distinguishes between short-term occasional fluctuations and real phased labels across time windows, enhances the interpretability and reference value of labels, avoids interference from multiple labels from the same company and different companies with the same name, and ensures the accuracy and dynamism of label output.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122199007B_ABST
    Figure CN122199007B_ABST
Patent Text Reader

Abstract

This invention relates to the field of tag generation technology, and in particular to a method for generating enterprise information tags based on enterprise profiles. The method includes: acquiring multi-source enterprise profile data, and performing subject normalization processing on the multi-source enterprise profile data to obtain enterprise subject alignment results; performing time window processing on the associated multi-source data based on the enterprise subject alignment results to obtain a set of enterprise time-series profile segments; performing candidate tag template matching on the set of enterprise time-series profile segments to obtain a set of candidate tags and direct evidence results; and extracting time window stability results from the set of enterprise time-series profile segments. This invention, by extracting time window stability results from the set of enterprise time-series profile segments, obtains the continuous representation of candidate tags over continuous time windows, thereby distinguishing between temporary tags formed by short-term, occasional fluctuations and genuine, stage-specific tags that persist across multiple time windows.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • User portrait label generation method and system based on time-aligned transfer model

    CN119989032A

  • Enterprise management method and management platform based on dynamic portraits

    CN121352630A

  • Matching management method and management system between enterprises based on knowledge graph

    CN121563273A