Interview method and device based on AI auxiliary interview scene and terminal equipment
A technology of scenarios and questions, applied to devices and terminal equipment, in the field of interview methods based on AI-assisted interview scenarios, can solve problems such as inaccurate score determination, unstable and reliable analysis of interview results, and lack of scoring ability, so as to improve the accuracy rate Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0054] Such asfigure 1 As shown, the embodiment of the present invention provides an interview method based on an AI-assisted interview scenario. By providing an appropriate scoring model to assist the interview, the method includes but is not limited to the following steps:
[0055] S101. Obtain voice content expressed by an interviewer, and convert the voice content into text content.
[0056] The implementation of the above step S101 can use a front-end system; wherein, the front-end system can be implemented by a PC terminal or a mobile phone terminal. The front-end system realizes the conversion from voice content to text content through automatic speech recognition (Automatic Speech Recognition, ASR) technology.
[0057] In one embodiment, the obtained text content can use text recognition technology, such as natural language processing (Natural Language Processing, NLP) technology, to identify errors in the text content, such as semantic, grammatical or / and logical err...
Embodiment 2
[0098] Such as figure 2 As shown, the embodiment of the present invention provides an interview method based on an AI-assisted interview scenario, and shows the detailed implementation process of step S105 in the first embodiment. When starting the similar question engine in step S105, obtain the question template according to the processing result of the similar question engine, and select a scoring model to score the interviewer's answer, which may include:
[0099] S10511. When starting the similar query engine, invoke the trained matching neural network model in the similar engine, and convert the key information into word vectors through the matching neural network model.
[0100] In the above step S10511, the key information in the text content based on the interviewer's expression is converted into a word vector, and the word vector is used for matching to obtain an accurate matching range.
[0101] In one embodiment, considering that the interviewer may temporarily e...
Embodiment 3
[0134] Such as Figure 4 As shown, the embodiment of the present invention provides an interview method based on an AI-assisted interview scenario, and shows the detailed implementation process of step S105 in the first embodiment. In step S105, when the similar question engine is not started, the question template is obtained according to the key information, and the scoring model is selected to score the interviewer's answer, which may include:
[0135] S10521. When the similar question engine is not started, match the question template in the question database according to the question ID in the key information.
[0136] S10522. Call the scoring model corresponding to the successfully matched question template, and score the interviewer's answer according to the scoring model.
[0137] In the above step S10521 and step S10522, if the similar question engine is not activated, it means that in the current interview scene, random questions from the interviewer will not appear...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com