CN112837033A - Robot system and method for realizing leaderless group interview - Google Patents
Robot system and method for realizing leaderless group interview Download PDFInfo
- Publication number
- CN112837033A CN112837033A CN202110155701.2A CN202110155701A CN112837033A CN 112837033 A CN112837033 A CN 112837033A CN 202110155701 A CN202110155701 A CN 202110155701A CN 112837033 A CN112837033 A CN 112837033A
- Authority
- CN
- China
- Prior art keywords
- module
- robot
- interview
- leaderless
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims abstract description 4
- 230000006399 behavior Effects 0.000 claims description 25
- 230000014509 gene expression Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 8
- 230000008451 emotion Effects 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 230000002996 emotional effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 2
- 230000001815 facial effect Effects 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims description 2
- 230000033764 rhythmic process Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/15—Conference systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a robot system and a method for realizing leaderless group interview, the leaderless group interview system comprises a video conference system, the video conference system comprises a client and a robot, the client comprises an ID login module, a camera, a microphone and a loudspeaker module, the robot comprises an interview starting module, an ID recognition module, a voice recognition module, a semantic understanding module, a behavior analysis module, an inference analysis module and a decision module, the microphone and the loudspeaker module are used for providing normal voice communication and enabling the robot to collect voice information of each interviewee, the leaderless group interview is realized based on the technologies of natural language understanding, analysis, inference, decision making, multi-mode analysis and the like, the objectionality and the impartiality caused by personal factors and bias are eliminated, the leaderless group interview is migrated from 'off-line' to 'on-line', the labor cost is reduced.
Description
Technical Field
The invention relates to the technical field of natural language processing, in particular to a robot system and a method for realizing leaderless group interview.
Background
The relative maturity of technologies such as voice recognition, face recognition, semantic understanding, emotion recognition, multi-modal analysis, conversation behavior analysis and the like provides basic technology accumulation for the intelligent decision-making robot.
The leaderless group interview is more and more emphasized, is an important method and way for many enterprises to choose talents, and becomes a possible trend along with the push of on-line recruitment and the push of recruitment robots to realize the on-line leaderless group interview.
Disclosure of Invention
The present invention is directed to a robotic system and method for achieving a leaderless team interview that solves the problems set forth above in the background.
In order to achieve the purpose, the invention provides the following technical scheme:
a robot system for achieving leaderless group interviewing comprises a leaderless group interviewing system, wherein the leaderless group interviewing system comprises a video conference system, the video conference system comprises a client and a robot, the client comprises an ID login module, a camera, a microphone and a loudspeaker module, and the robot comprises an interviewing starting module, an ID recognition module, a voice recognition module, a semantic understanding module, a behavior analysis module, an inference analysis module and a decision module.
As a further scheme of the invention: the robot is used for starting interviews, collecting interviewer information, analyzing, reasoning and deciding interviewer behaviors and information and comprehensively judging the interviewers, different roles are respectively assigned to the robot and other interviewers, the robot is based on natural language understanding, multi-mode analyzing, understanding and reasoning technologies, the robot collects information in real time, judges, analyzes and infers the information in real time and assigns roles of an organizer and an observer, other persons are presenters, the presenters express themselves and assign roles of the interviewers through various languages, tone, expressions and the like and observe colors in the discussion process, the scoring is carried out according to the expressions of the interviewers in the discussion process, and the final recording or non-recording decision is made by comprehensively considering all aspects of behaviors.
As a still further scheme of the invention: the camera is used for the robot to collect expressions and emotional expressions of various interviewers.
As a still further scheme of the invention: the microphone and speaker module is used for providing normal voice communication and enabling the robot to collect voice information of each interviewer, wherein the voice information comprises information such as characters, voice tones and the like which are analyzed subsequently.
As a still further scheme of the invention: and the ID login module is used for facilitating the interviewer to join the video conference system.
As a still further scheme of the invention: the interview starting module is used for starting a conference by the robot, and the ID identification module is used for identifying ID information of the interviewer, so that the interviewer is allowed to join the video conference system, and the interviewer is distinguished and identified.
As a still further scheme of the invention: the voice recognition module is used for recognizing the voice information of the interviewer, and the semantic understanding module is used for understanding the semantics expressed by the interviewer.
As a still further scheme of the invention: the behavior analysis module is used for analyzing the behavior of the interviewer, the reasoning analysis module is used for reasoning after analyzing the voice recognition analysis of the interviewer and the behavior of the interviewer, and the decision module is used for making a rating decision after analyzing and reasoning.
Compared with the prior art, the invention has the beneficial effects that:
based on technologies such as natural language understanding, analysis, reasoning, decision making, multi-modal analysis and the like, the leaderless group interview is realized, the objectionality and the unfairness caused by personal factors and prejudices are eliminated, the leaderless group interview is transferred from off-line to on-line, and the labor cost is reduced.
Drawings
FIG. 1 is a system block diagram of a robotic system and method for implementing a leaderless team interview.
Fig. 2 is a schematic diagram of a video conferencing system implementing a robotic system and method for a leaderless team interview.
Fig. 3 is a schematic diagram of robot information processing in the robot system and method for implementing the leaderless team interview.
FIG. 4 is a schematic diagram of a trained inference model in a robotic system and method for performing a leaderless team interview.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 4, in the embodiment of the present invention, a robot system and a method for implementing a leaderless group interview include a leaderless group interview system, where the leaderless group interview system includes a video conference system, the video conference system includes a client and a robot, the client includes an ID login module, a camera, a microphone and a speaker module, the robot includes an interview starting module, an ID recognition module, a voice recognition module, a semantic understanding module, a behavior analysis module, an inference analysis module and a decision module, the robot is configured to start an interview, collect interviewer information, analyze, infer and decide interviewer behaviors and comprehensively evaluate the interviewer, the robot and other interviewers are respectively assigned different roles, and the robot understands, analyzes, decides, and/or analyzes based on natural language, multiple-mode analysis, understanding, and the like, The robot collects information in real time, judges, analyzes and infers the information in real time, assigns roles of an organizer and an observer, presents the representative through various languages, tone, expressions and the like, assigns roles of interviewers, observes the colors during discussion, scores the expressions of the interviewers in discussion and makes a decision on whether to record or not by comprehensively considering various behaviors, the camera is used for the robot to collect the expressions and emotional expressions of the interviewers, the microphone and loudspeaker modules are used for providing normal voice communication and enabling the robot to collect the voice information of the interviewers, wherein the voice information comprises information of subsequent analysis into characters, voice tones and the like, the ID login module is used for facilitating the interviewers to join a video conference system, and the interview starting module is used for the robot to start a conference, the system comprises an ID recognition module, a voice recognition module, a semantic understanding module, a behavior analysis module, an inference analysis module and a decision-making module, wherein the ID recognition module is used for recognizing ID information of an interviewee so that the interviewee is allowed to join a video conference system and distinguishing and recognizing the interviewee;
a method for realizing leaderless group interview comprises the following steps:
the method comprises the following steps: firstly, initializing and establishing a conference room, and then enabling a client to normally enter a system;
step two: the client enters the system in a dialing mode;
step three: when all the clients enter the system and the equipment detection is finished and normal, the robot can start an interview; the way that the robot starts the interview includes:
5) the method comprises the following steps that a plurality of articles or topics are preset manually in advance, and the robot randomly selects the articles or topics as analysis subjects of a leaderless group interview;
6) training a generative model according to a large number of articles by the robot, and generating a theme by the generative model each time;
7) the robot appoints one of the interviewers, and the interviewer determines a theme;
8) no topic, and all interviewees can play freely;
step four: the robot firstly needs to analyze the information data of each person, and scores or classifies the information data according to the information data of each person according to a certain rule, wherein the dimensionality comprises language information, extraspeech behaviors, expression behaviors, information quantity, knowledge plane, coherence, information contact degree, tone, expression and the like;
step five: scoring each interviewer according to the context of the multiple interviewers, wherein the dimensionality comprises the upper and lower bearing degrees, the information correspondence degree, the speaking time, the information co-occurrence of the interviewers, the personal contribution degree, the interaction condition with other interviewers and the like;
step six: finally, the scoring result of each interviewer is an individual performance score and a performance score of the individual in a team, and the individual performance score and the performance score can be adjusted through a weight value.
In the third step, the robot distinguishes each interviewer through the access ID of each person, the information of each interviewer is expressed through voice and images, the voice is translated into text and tones, the images are translated into corresponding emotions and behaviors, the emotion and the behavior are all time sequence data, and the voice and the images can be aligned according to time sequence through an information alignment technology to generate three kinds of information: text, voice including pitch and rhythm, image including expression, facial language and body language;
in the third step, the robot needs to simulate and acquire training data for many times to train the inference model, specifically: firstly, manually marking an output intermediate state and a final state, continuously collecting training data in a real interview scene, and training and optimizing a model on line to improve the decision reasoning level;
based on technologies such as natural language understanding, analysis, reasoning, decision making, multi-modal analysis and the like, the leaderless group interview is realized, the objectionality and the unfairness caused by personal factors and prejudices are eliminated, the leaderless group interview is transferred from off-line to on-line, and the labor cost is reduced.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention can be made without departing from the spirit and scope of the invention.
Claims (10)
1. A robotic system for enabling a leaderless panel interview, comprising a leaderless panel interview system, characterized by: the leaderless group interview system comprises a video conference system, the video conference system comprises a client and a robot, the client comprises an ID login module, a camera, a microphone and a loudspeaker module, and the robot comprises an interview starting module, an ID recognition module, a voice recognition module, a semantic understanding module, a behavior analysis module, an inference analysis module and a decision-making module.
2. The robotic system and method of enabling a leaderless team interview according to claim 1 wherein: the robot is used for starting interviews, collecting interviewer information, analyzing, reasoning and deciding interviewer behaviors and information and comprehensively judging the interviewers, different roles are respectively assigned to the robot and other interviewers, the robot is based on natural language understanding, multi-mode analyzing, understanding and reasoning technologies, the robot collects information in real time, judges, analyzes and infers the information in real time and assigns roles of an organizer and an observer, other persons are presenters, the presenters express themselves and assign roles of the interviewers through various languages, tone, expressions and the like and observe colors in the discussion process, the scoring is carried out according to the expressions of the interviewers in the discussion process, and the final recording or non-recording decision is made by comprehensively considering all aspects of behaviors.
3. A robotic system for enabling a leaderless team interview according to claim 1 wherein: the camera is used for the robot to collect expressions and emotional expressions of various interviewers.
4. A robotic system for enabling a leaderless team interview according to claim 1 wherein: the microphone and speaker module is used for providing normal voice communication and enabling the robot to collect voice information of each interviewer, wherein the voice information comprises information such as characters, voice tones and the like which are analyzed subsequently.
5. A robotic system for enabling a leaderless team interview according to claim 1 wherein: and the ID login module is used for facilitating the interviewer to join the video conference system.
6. A robotic system for enabling a leaderless team interview according to claim 1 wherein: the interview starting module is used for starting a conference by the robot, and the ID identification module is used for identifying ID information of the interviewer, so that the interviewer is allowed to join the video conference system, and the interviewer is distinguished and identified.
7. A robotic system for enabling a leaderless team interview according to claim 1 wherein: the voice recognition module is used for recognizing the voice information of the interviewer, and the semantic understanding module is used for understanding the semantics expressed by the interviewer.
8. A robotic system for enabling a leaderless team interview according to claim 1 wherein: the behavior analysis module is used for analyzing the behavior of the interviewer, the reasoning analysis module is used for reasoning after analyzing the voice recognition analysis of the interviewer and the behavior of the interviewer, and the decision module is used for making a rating decision after analyzing and reasoning.
9. A method of implementing a leaderless panel interview, comprising: the method comprises the following steps:
the method comprises the following steps: firstly, initializing and establishing a conference room, and then enabling a client to normally enter a system;
step two: the client enters the system in a dialing mode;
step three: when all the clients enter the system and the equipment detection is finished and normal, the robot can start an interview; the way that the robot starts the interview includes:
1) the method comprises the following steps that a plurality of articles or topics are preset manually in advance, and the robot randomly selects the articles or topics as analysis subjects of a leaderless group interview;
2) training a generative model according to a large number of articles by the robot, and generating a theme by the generative model each time;
3) the robot appoints one of the interviewers, and the interviewer determines a theme;
4) no topic, and all interviewees can play freely;
step four: the robot firstly needs to analyze the information data of each person, and scores or classifies the information data according to the information data of each person according to a certain rule, wherein the dimensionality comprises language information, extraspeech behaviors, expression behaviors, information quantity, knowledge plane, coherence, information contact degree, tone, expression and the like;
step five: scoring each interviewer according to the context of the multiple interviewers, wherein the dimensionality comprises the upper and lower bearing degrees, the information correspondence degree, the speaking time, the information co-occurrence of the interviewers, the personal contribution degree, the interaction condition with other interviewers and the like;
step six: finally, the scoring result of each interviewer is an individual performance score and a performance score of the individual in a team, and the individual performance score and the performance score can be adjusted through a weight value.
10. A method of performing a leaderless panel interview according to claim 9 wherein: in the third step, the robot distinguishes each interviewer through the access ID of each person, the information of each interviewer is expressed through voice and images, the voice is translated into text and tones, the images are translated into corresponding emotions and behaviors, the emotion and the behavior are all time sequence data, and the voice and the images can be aligned according to time sequence through an information alignment technology to generate three kinds of information: text, voice including pitch and rhythm, image including expression, facial language and body language; in the third step, the robot needs to simulate and acquire training data for many times to train the inference model, specifically: the method comprises the steps of firstly, manually marking an output intermediate state and a final state, continuously collecting training data in a real interview scene, and training and optimizing a model on line so as to improve the decision reasoning level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155701.2A CN112837033A (en) | 2021-02-04 | 2021-02-04 | Robot system and method for realizing leaderless group interview |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155701.2A CN112837033A (en) | 2021-02-04 | 2021-02-04 | Robot system and method for realizing leaderless group interview |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112837033A true CN112837033A (en) | 2021-05-25 |
Family
ID=75932174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110155701.2A Pending CN112837033A (en) | 2021-02-04 | 2021-02-04 | Robot system and method for realizing leaderless group interview |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112837033A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218763A (en) * | 2013-03-26 | 2013-07-24 | 陈秀成 | Remote on-line interviewing method and system with high reliability |
| CN104202557A (en) * | 2014-08-26 | 2014-12-10 | 四川亿信信用评估有限公司 | Video online interviewing system |
| US20180018632A1 (en) * | 2016-07-14 | 2018-01-18 | Universal Entertainment Corporation | Interview system |
| CN107977822A (en) * | 2016-10-25 | 2018-05-01 | 周海杭 | A kind of online interview exam system |
| CN209057303U (en) * | 2018-11-08 | 2019-07-02 | 江西国泰利民信息科技有限公司 | A kind of speech recognition Remote Video Conference robot framework |
| CN110900623A (en) * | 2019-11-25 | 2020-03-24 | 广西秀牛科技有限公司 | Self-service interview robot |
| CN111126553A (en) * | 2019-12-25 | 2020-05-08 | 平安银行股份有限公司 | Intelligent robot interviewing method, equipment, storage medium and device |
-
2021
- 2021-02-04 CN CN202110155701.2A patent/CN112837033A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218763A (en) * | 2013-03-26 | 2013-07-24 | 陈秀成 | Remote on-line interviewing method and system with high reliability |
| CN104202557A (en) * | 2014-08-26 | 2014-12-10 | 四川亿信信用评估有限公司 | Video online interviewing system |
| US20180018632A1 (en) * | 2016-07-14 | 2018-01-18 | Universal Entertainment Corporation | Interview system |
| CN107977822A (en) * | 2016-10-25 | 2018-05-01 | 周海杭 | A kind of online interview exam system |
| CN209057303U (en) * | 2018-11-08 | 2019-07-02 | 江西国泰利民信息科技有限公司 | A kind of speech recognition Remote Video Conference robot framework |
| CN110900623A (en) * | 2019-11-25 | 2020-03-24 | 广西秀牛科技有限公司 | Self-service interview robot |
| CN111126553A (en) * | 2019-12-25 | 2020-05-08 | 平安银行股份有限公司 | Intelligent robot interviewing method, equipment, storage medium and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zadeh et al. | Social-iq: A question answering benchmark for artificial social intelligence | |
| Kollias | Abaw: Valence-arousal estimation, expression recognition, action unit detection & multi-task learning challenges | |
| Soldner et al. | Box of lies: Multimodal deception detection in dialogues | |
| US10110743B2 (en) | Automatic pattern recognition in conversations | |
| CN110175229B (en) | Method and system for on-line training based on natural language | |
| Ren | Affective information processing and recognizing human emotion | |
| Chowanda et al. | Erisa: Building emotionally realistic social game-agents companions | |
| Leite et al. | Semi-situated learning of verbal and nonverbal content for repeated human-robot interaction | |
| US11611554B2 (en) | System and method for assessing authenticity of a communication | |
| AbdElminaam et al. | HR-chat bot: Designing and building effective interview chat-bots for fake CV detection | |
| CN112884326A (en) | Video interview evaluation method and device based on multi-modal analysis and storage medium | |
| CN113076770A (en) | Intelligent figure portrait terminal based on dialect recognition | |
| Bai et al. | Automatic long-term deception detection in group interaction videos | |
| Huang et al. | Making virtual conversational agent aware of the addressee of users' utterances in multi-user conversation using nonverbal information | |
| Petrushin | Emotion recognition agents in real world | |
| CN112837033A (en) | Robot system and method for realizing leaderless group interview | |
| Wei et al. | Investigating the relationship between dialogue and exchange-level impression | |
| Rasipuram et al. | Online peer-to-peer discussions: A platform for automatic assessment of communication skill | |
| Fang et al. | Estimation of cohesion with feature categorization on small scale groups | |
| Tsihrintzis et al. | On improving visual-facial emotion recognition with audio-lingual and keyboard stroke pattern information | |
| Sen et al. | Dbates: Dataset for discerning benefits of audio, textual, and facial expression features in competitive debate speeches | |
| Shiota et al. | Development and application of leader identification model using multimodal information in multi-party conversations | |
| Randika et al. | A Multimodal Interviewee Evaluation Approach for Candidates Facing Video Interviews | |
| Svetleff et al. | Facial Expression of Emotion Assessment from Video in Adult Second Language Learners | |
| Barriere et al. | Opinions in interactions: New annotations of the SEMAINE database |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210525 |