AI interview evaluation report generation system and method based on competency model

CN121788087BActive Publication Date: 2026-11-03CAPITAL NORMAL UNIVERSITY +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202511938273.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-12-22
Publication Date
2026-11-03
Estimated Expiration
2045-12-22

AI Technical Summary

Technical Problem

Existing AI-powered interview assessment report generation systems rely on manual observation and fixed scoring sheets. The data collection process lacks temporal consistency of multi-source signals. Manual recording of verbal and non-verbal performances is susceptible to attentional bias and emotional interference. Rule-based scoring methods cannot capture candidates' behavioral characteristics in changes in tone of voice, subtle facial expressions, and reaction rhythm. This results in low correlation accuracy of assessment results across competency dimensions, and the reports are prone to descriptive imbalances and judgment biases, making it difficult to support the quantitative identification and reliable assessment of candidates' comprehensive behavioral characteristics.

Method used

A multimodal data synchronization module is used to calculate the time offset of image, voice and operational behavior signals during the candidate interview process to generate a multimodal synchronization dataset. Facial expression, tone change and reaction time parameters are extracted by the feature encoding module. The similarity coefficient is calculated by the behavior pattern screening module to filter out time window features below the threshold and generate a competency-related behavior feature set. Finally, the competency feature mapping module matches the behavior features with the competency dimension weights to generate competency assessment result data.

Benefits of technology

By constructing a time alignment mechanism for multi-source signals, dynamic synchronization of speech, images, and behavioral sequences is achieved, improving signal matching accuracy, generating quantifiable behavioral vectors, maintaining the continuity and consistency of semantic and emotional changes, and realizing adaptive matching of behavioral features and ability dimensions. Finally, the report output presents multi-dimensional evaluation results in a fusion of scores and textual descriptions, significantly enhancing the objectivity, interpretability, and reliability of the evaluation results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121788087B_ABST
    Figure CN121788087B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of artificial intelligence, in particular to an AI interview evaluation report generation system and method based on a competency model, which comprises a multi-modal data synchronization module, a feature coding module, a behavior pattern screening module, a competency feature mapping module and an evaluation result generation module.In the application, a multi-source signal time alignment mechanism is constructed to realize dynamic synchronization of voice images and behavior sequences, a time compensation and window division strategy is adopted to improve signal matching accuracy, so that the timing relationship between expression changes and tone fluctuations is stably presented, a quantifiable behavior vector is generated through multi-dimensional feature coding, the semantic and emotional changes are continuously consistent through similarity screening, the competency weight mapping is established in the feature fusion stage, the behavior features and the ability dimensions are adaptively matched, finally, the multi-dimensional evaluation results are output in the form of score and text description fusion, and the objectivity, interpretability and reliability of the evaluation results are enhanced.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Talent evaluation management method and system based on AI intelligence

    CN120338741A

  • One-stop talent screening method and system

    CN120806900A