一种基于多模态大模型的面访问卷质控方法及系统
By combining multimodal large models with interview audio and questionnaire data, the efficiency and consistency verification issues of face-to-face interview data quality control were resolved, realizing an efficient and comprehensive quality control process and improving the authenticity and credibility of the data.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- INSTITUTE OF ETHNOLOGY & ANTHROPOLOGY CHINESE ACADEMY OF SOCIAL SCIENCES
- Filing Date
- 2026-03-12
- Publication Date
- 2026-07-17
AI Technical Summary
In existing questionnaire surveys, face-to-face questionnaires have low data quality control efficiency, cannot effectively verify the consistency between the interviewer's recorded answers and the interviewee's true intentions, and suffer from high labor costs, insufficient coverage and content depth.
A quality control method based on a multimodal large model is adopted. By simultaneously acquiring interview voice data and structured electronic questionnaire data, multimodal feature extraction and fusion analysis are performed to locate standardized voice answers, and consistency comparison is conducted to generate quality control output information.
It has automated and intelligentized the face-to-face survey quality control process, significantly improving efficiency, reducing labor costs, enabling full coverage of survey samples, identifying data distortion issues, and improving the authenticity and credibility of the data.
Smart Images
Figure CN121808052B_ABST