Real-time interview advice providing system, real-time interview advice providing method and program

Abstract

Achieve pre-set interview goals during a real-time interview. [Solution] A real-time interview advice providing system that analyzes the meaning of the utterances in voice data during an interview that is taking place in real time, and generates and provides interview advice to achieve predetermined interview goals sets interview goals according to the type of interview, acquires the voice data during the interview during the interview that is taking place in real time, analyzes the meaning of the utterances in the acquired voice data during the interview that is taking place in real time, generates interview advice to achieve the interview goals based on the analysis of the meaning of the utterances during the interview that is taking place in real time, and provides the interview advice to the interviewer during the interview that is taking place in real time.

Description

[Technical Field]

[0001] The present invention relates to a technique that is effective in providing interview advice necessary for achieving a predetermined interview goal during an interview that is progressing in real time. [Background technology]

[0002] In recent years, techniques related to interviews conducted by companies and organizations to evaluate job applicants for employment and personnel evaluations of in-house personnel have been attracting attention. For example, Patent Document 1 provides a technology that analyzes the amount of speech of the interviewer and the amount of speech of the interviewee and provides at least one of advice and a warning to the interviewer during the interview. In the technology described in Patent Document 1, the advice and warning are related to the amount of speech, with advice such as "Try to reduce your speech volume" and warning such as "You're speaking too much." Furthermore, Patent Document 2 provides a technology that analyzes the voice of an interviewer who is interviewing an interviewee and provides advice to the interviewer. In the technology described in Patent Document 2, the advice is related to the facial expression, line of sight, and nod of the interviewer, and is such as "It seems that you are able to sufficiently show trust and other feelings through your facial expression. Continue to interact with your subordinates with a positive facial expression and strive to build relationships," and "It seems that you are able to interact with your subordinates with a positive facial expression. However, there are also many negative facial expressions such as a blank expression, sadness, or anger. Try to make more positive facial expressions." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-108346 [Patent Document 2] Japanese Patent Publication No. 2023-054558 Summary of the Invention [Problem to be solved by the invention]

[0004] Companies and organizations conduct interviews with job seekers, external personnel, internal personnel, etc. However, these interviews have the problem that it is difficult to achieve the interview goals that have been set in advance for the interview, since a third party does not objectively analyze the interview during the interview. Therefore, there is a need for a technology that provides interviewers with interview advice for achieving predetermined interview goals during an interview that is progressing in real time. However, the technologies described in Patent Documents 1 and 2 only provide advice or warnings regarding the interviewer's statements and actions, such as the amount of speech, facial expressions, eye contact, and nodding, and are unable to provide interview advice to help achieve the interview goals. Therefore, the inventor focused on a system that analyzes the content of speech data during an interview that is progressing in real time, generates interview advice to achieve predetermined interview goals, and provides the interview advice.

[0005] In consideration of these problems, the present invention aims to provide a real-time interview advice providing system, a real-time interview advice providing method, and a program that enable predetermined interview goals to be achieved during an interview that is progressing in real time. [Means for solving the problem]

[0006] The present invention provides a real-time interview advice providing system that analyzes the meaning of speech content of voice data during an interview that is progressing in real time, and generates and provides interview advice for achieving a predetermined interview goal, an interview goal setting unit that sets interview goals according to the type of interview; a voice data acquisition unit that acquires the voice data during the interview during the interview that is proceeding in real time; a speech content analysis unit that analyzes the meaning of speech content of the acquired voice data during the interview that is progressing in real time; an interview advice generating unit that generates interview advice for achieving the interview goal based on the analysis result of the meaning of the utterance content during the interview that is progressing in real time; an interview advice providing unit that provides the interview advice to the interviewee during the interview that is proceeding in real time; To provide a real-time interview advice providing system comprising:

[0007] According to the present invention, interview advice for achieving an interview goal is generated based on the analysis result of voice data during an interview, and the interview advice is provided to the interviewer. As a result, during the interview that is proceeding in real time, the interviewer receives interview advice necessary for achieving the interview goal, and by correcting and changing the content of the interview in response to this interview advice, the interviewer can achieve the interview goal that has been set in advance during the interview that is proceeding in real time.

[0008] Although the present invention is categorized as a system, the same effects and advantages can be obtained even when it is a method or a program. [Effects of the Invention]

[0009] According to the present invention, it is possible to achieve a predetermined interview goal during an interview that is progressing in real time. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an overview of a real-time interview advice providing system 1. FIG. [Figure 2] 1 is a diagram showing the functional configuration of a real-time interview advice providing system 1. FIG. [Figure 3] 10 is a flowchart showing a first interview goal setting process executed by the computer 10. FIG. [Figure 4] 10 is a flowchart showing a second interview goal setting process executed by the computer 10. FIG. [Figure 5]FIG. 10 is a flowchart showing a taboo phrase setting process executed by the computer 10. [Figure 6] FIG. 2 is a flowchart showing a first learning process executed by the computer 10. [Figure 7] FIG. 10 is a flowchart showing a second learning process executed by the computer 10. [Figure 8] FIG. 10 is a flowchart showing an interview advice providing process executed by the computer 10. [Figure 9] FIG. 10 is a flowchart showing an alert process executed by the computer 10. [Figure 10] FIG. 10 is a flowchart showing a process of providing minutes executed by the computer 10. [Figure 11] FIG. 10 is a flowchart showing a voice data providing process executed by the computer 10. [Figure 12] FIG. 10 is a flowchart showing an evaluation providing process executed by the computer 10. [Figure 13] FIG. 10 is a flowchart showing a report providing process executed by the computer 10. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention (hereinafter referred to as "embodiments") will be described in detail with reference to the accompanying drawings. In the following drawings, the same elements are designated by the same numbers or symbols throughout the description of the embodiments.

[0012] [Outline of the Real-time Interview Advice Providing System 1] 1 is a schematic diagram for explaining an overview of the real-time interview advice providing system 1. Components of the real-time interview advice providing system 1 will be described based on FIG. The real-time interview advice providing system 1 is a system that comprises at least a computer 10 having a server function, and that analyzes the meaning of the content of speech data during an interview that is proceeding in real time, and generates and provides interview advice for achieving a predetermined interview goal. In this embodiment, the real-time interview advice providing system 1 includes, in addition to the computer 10, an information terminal 3 used by the person conducting the interview (hereinafter also referred to as the interviewer). In addition, in the following description, the person being interviewed will also be referred to as the interviewee.

[0013] The information terminal 3 is a terminal device used by the interviewee, and may be, for example, a mobile phone, a smartphone, a tablet terminal, a personal computer, a laptop computer, or a wearable terminal such as a smart watch, smart glasses, or an HMD (Head Mounted Display). The information terminal 3 can be designed appropriately depending on the number of interviewees.

[0014] The computer 10 has a server function and may be realized, for example, by a single computer, or may be realized by multiple computers, such as a cloud computer. In this specification, a cloud computer may refer to either a computer that uses any computer in a scalable manner to perform a specific function, or a computer that includes multiple functional modules to realize a system and uses the functions in any combination.

[0015] In addition, the real-time interview advice providing system 1 may include other terminals and devices in addition to the above-mentioned information terminal 3 and computer 10, and the number, type and functions thereof are not particularly limited and can be designed as appropriate.

[0016] This section provides an overview of the processing steps that the real-time interview advice providing system 1 takes when analyzing the meaning of speech content in voice data during an interview that is taking place in real time, and generating and providing interview advice to achieve predetermined interview goals.

[0017] The computer 10 sets an interview goal according to the type of interview (step S1). The computer 10 may accept the type of interview via the information terminal 3 and set interview goals based on a template corresponding to the accepted type of interview, or may use AI (Artificial Intelligence) to set interview goals corresponding to the accepted type of interview, or may accept the interview goals themselves directly, or may set interview goals based on evaluation information obtained from an external database or held by the computer 10 itself.

[0018] The computer 10 acquires voice data during the interview, which is proceeding in real time (step S2). The computer 10 acquires voice data from a sound collection device such as a microphone installed at the location where the interview is held, or from the information terminal 3.

[0019] During the interview that is proceeding in real time, the computer 10 analyzes the meaning of the utterances in the acquired voice data (step S3). The computer 10 analyzes the meaning of the interviewer's statements, the tone of voice, the tempo and content of the conversation in the audio data, and the meaning of the interviewee's statements, the tone of voice, the tempo and content of the conversation using a predetermined algorithm or AI.

[0020] During the interview that is progressing in real time, the computer 10 generates interview advice for achieving the interview goal based on the analysis result of the meaning of the utterance content (step S4). The computer 10 generates interview advice based on the analysis results of the voice data.

[0021] The computer 10 provides interview advice to the interviewee during the interview that is proceeding in real time (step S5). The computer 10 outputs the generated interview advice to the information terminal 3, and causes the information terminal 3 to display the interview advice.

[0022] The above is an overview of the real-time interview advice providing system 1. According to this real-time interview advice providing system 1, it is possible to achieve a preset interview goal during an interview that is progressing in real time.

[0023] [Device configuration] 2 is a block diagram showing the configuration of the real-time interview advice providing system 1. The device configuration of the real-time interview advice providing system 1 will be described with reference to FIG. The real-time interview advice providing system 1 is a system that analyzes the meaning of the content of speech in voice data during an interview that is progressing in real time, and generates and provides interview advice to achieve a predetermined interview goal, and is composed of at least a computer 10. In this embodiment, the real-time interview advice providing system 1 is composed of an information terminal 3 in addition to the computer 10, as described above. The real-time interview advice providing system 1 is a system in which a computer 10 is connected to an information terminal 3 so as to be capable of data communication via a network 8 such as a public line network or an intranet. The real-time interview advice providing system 1 may include other terminals and devices in addition to the information terminal 3 and the computer 10, and the number, type and functions of the other terminals and devices can be designed as appropriate. As mentioned above, the number of information terminals 3 can be designed as appropriate depending on the number of interviewees.

[0024] The information terminal 3 is the above-mentioned terminal device used by the interviewing party. The information terminal 3 has a CPU (Central Processing Unit), GPU (Graphics Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), etc. as a terminal control unit, and has devices, etc. that enable communication with other terminals, devices, etc. as a communication unit. The information terminal 3 includes, as an input / output unit, various devices for receiving predetermined inputs and executing input / output of various data.

[0025] The computer 10 has a server function and may be realized, for example, by a single computer, or may be realized by multiple computers, such as a cloud computer. The computer 10 has a control unit including a CPU, GPU, RAM, ROM, etc., and a communication unit including a device for enabling communication with other terminals and devices, an audio data acquisition unit for acquiring audio data during an interview that is progressing in real time, and an interview advice provision unit for providing interview advice to the interviewee during an interview that is progressing in real time. The computer 10 includes a data storage unit such as a hard disk, semiconductor memory, recording medium, or memory card as a memory unit. The computer 10 includes, as processing units, various devices that perform various processes, an interview goal setting unit that sets interview goals according to the type of interview, a statement content analysis unit that analyzes the meaning of the statement content of the acquired audio data during the interview that is progressing in real time, and an interview advice generation unit that generates interview advice for achieving the interview goals based on the analysis results of the meaning of the statement content during the interview that is progressing in real time.

[0026] In computer 10, the control unit loads a specified program and works in cooperation with the communication unit to realize an interview type reception module, a template output module, a template reception module, an evaluation information acquisition module, a taboo phrase reception module, an internal data acquisition module, an audio data acquisition module, an advice provision module, an alert module, a minutes provision module, an audio data provision module, an evaluation provision module, and a report provision module. In addition, in the computer 10, the control unit reads a predetermined program, thereby realizing a storage module in cooperation with the storage unit. In addition, in computer 10, the control unit reads a specified program and works in cooperation with the processing unit to realize a template selection module, an interview goal setting module, an evaluation information analysis module, a taboo phrase setting module, a recovery plan setting module, a learning module, a model generation module, an audio data acquisition module, a statement content analysis module, an advice generation module, a taboo phrase judgment module, a minutes generation module, an end judgment module, an evaluation generation module, a summary module, an extraction module, and a report generation module.

[0027] Hereinafter, each process executed by the real-time interview advice providing system 1 will be described together with the process executed by each of the modules described above. In this specification, each module may execute its processing content as its own function, or may execute its processing content via a predetermined application.

[0028] [First Interview Goal Setting Process Executed by Computer 10] The first interview goal setting process executed by the computer 10 will be described with reference to Figure 3. The figure shows a flowchart of the first interview goal setting process executed by the computer 10. This first interview goal setting process is a detailed description of the interview goal setting process (step S1) that sets an interview goal according to the type of interview. The first interview goal setting process is a process that is executed before the interviewer conducts the interview.

[0029] The consultation type reception module receives the type of consultation (step S10). An interview is a face-to-face meeting between the person conducting the interview (interviewer) and the person being interviewed (interviewee). Types of interviews include recruitment interviews, personnel evaluation interviews, and one-on-one interviews. The information terminal 3 accepts input of data regarding the type of interview (type of interview, interviewer's identifier, interviewee's identifier, interview date and time, interview duration, etc.) from the interviewer via a specified UI (User Interface) such as a specified application or a specified website, and transmits the accepted data to the computer 10. The consultation type reception module receives this data and receives the type of consultation.

[0030] The template selection module selects a template set according to the type of interview (step S11). The template is a document in which interview goals corresponding to the type of interview are registered. The format of the template is not particularly limited as long as the interview goals are registered in the template, and the template may be, for example, a document in which the type of interview and one or more interview goals corresponding to the type of interview are described. The interview goal is the goal of the interview. For example, in the case of a recruitment interview, it is the achievement of necessary confirmations when hiring, such as whether the interviewee's abilities meet the standards and whether they match the company's culture. In the case of a personnel evaluation interview, it is the achievement of the interviewee's personnel evaluation, such as whether the intention of the evaluation was correctly conveyed and whether the interviewee is satisfied with the evaluation. In the case of a one-on-one interview, it is the promotion of the interviewee's growth and mutual understanding between the interviewer and interviewee, such as drawing out the subordinate's concerns and providing appropriate support. The template selection module selects one or more templates that correspond to the type of the received interview.

[0031] The template output module outputs a template set according to the type of interview (step S12). The template output module transmits the selected template to the information terminal 3. The information terminal 3 receives this template and displays it on its own display unit via a predetermined UI such as a predetermined application or a predetermined website. The template output module displays this template on the information terminal 3, thereby outputting a template set according to the type of interview.

[0032] The template reception module receives a template desired by the interviewing party (step S13). The information terminal 3 accepts a selection input such as a tap or click on a template that the interviewee desires from among the displayed templates, and transmits data indicating the accepted template to the computer 10. The template reception module receives this data and receives the template desired by the interviewing party.

[0033] The template selection module selects a template desired by the interviewing party (step S14). The template selection module selects a template corresponding to the received data indicating the template as the template desired by the interviewee, based on the received data.

[0034] The interview goal setting module sets the selected template as the interview goal (step S15). The interview goal setting module sets the interview goal registered in the selected template as the interview goal when the interviewer conducts an interview.

[0035] The above is the first interview goal setting process. In the first interview goal setting process, the interview goal is set by selecting a template, but the interview goal may be set by other methods. For example, the information terminal 3 may accept direct input of the interview goal from the interviewee and transmit it to the computer 10, which may then receive the interview goal and set it as the interview goal according to the type of interview. The computer 10 may also use AI to set the interview goal according to the type of interview received.

[0036] [Second Interview Goal Setting Process Executed by Computer 10] The second interview goal setting process executed by the computer 10 will be described with reference to Figure 4. This figure shows a flowchart of the second interview goal setting process executed by the computer 10. This second interview goal setting process is a detailed version of the interview goal setting process (step S1) that is different from the first interview goal setting process. The second interview goal setting process is a process that is executed before the interviewer conducts the interview. Note that detailed explanations of processes similar to those described above will be omitted.

[0037] The consultation type reception module receives the type of consultation (step S20). The process of step S20 is similar to the process of step S10 described above.

[0038] The evaluation information acquisition module acquires evaluation information (step S21). The evaluation information is data relating to the evaluation of the interviewee, such as surveys, job information, work history, and personnel evaluation history. The evaluation information acquisition module acquires evaluation information from an external database (not shown), etc. If the computer 10 itself holds evaluation information in advance, the evaluation information may be acquired from the held evaluation information.

[0039] The evaluation information analysis module analyzes the evaluation information (step S22). The evaluation information analysis module analyzes the acquired evaluation information using a predetermined algorithm. For example, the evaluation information analysis module analyzes the personality, abilities, motivation, work experience, etc. of the interviewee based on the evaluation information.

[0040] The interview goal setting module sets an interview goal according to the type of interview and the evaluation information (step S23). The interview goal setting module sets interview goals based on the type of interview received and the acquired evaluation information. The interview goal setting module uses a predetermined algorithm or the like to set interview goals based on the type of interview and the evaluation information. When setting an interview goal in the process of step S15 described above, the interview goal setting module may set an interview goal based on the selected template and the acquired evaluation information. The interview goal setting module may also set interview goals based on the type of interview received and the analysis results of the evaluation information. The interview goal setting module uses a predetermined algorithm or the like to set interview goals based on the type of interview and the analysis results of the evaluation information.

[0041] This completes the second interview goal setting process.

[0042] The computer 10 executes the first or second interview goal setting process described above to set an interview goal for the interviewer when conducting an interview with the interviewee. The computer 10 executes the interview advice providing process described below using the set interview goal.

[0043] [Prohibited phrase setting process executed by computer 10] The taboo phrase setting process executed by the computer 10 will be described with reference to Fig. 5. The figure shows a flowchart of the taboo phrase setting process executed by the computer 10. This taboo phrase setting process is executed before the interviewer conducts an interview with the interviewee.

[0044] The taboo phrase receiving module receives input of taboo phrases (step S30). Taboo words are phrases that the interviewer must not say to the interviewee, such as statements about the person's registered domicile or living environment, statements about assets, statements that are limited to a specific gender, statements about political party support, statements about religious views, statements about family structure, statements that are legally questionable, and statements that are ethically questionable. The information terminal 3 receives input of data related to taboo phrases from the interviewee via a predetermined UI such as a predetermined application or a predetermined website, and transmits the received data to the computer 10. The taboo phrase receiving module receives this data and accepts input of taboo phrases.

[0045] It should be noted that instead of accepting input of taboo phrases, if the computer 10 itself holds taboo phrases in advance, the computer 10 may execute the process described below using the taboo phrases it holds. The computer 10 may also be configured to accept input of taboo phrases from a person other than the interviewee. In this case, the input of taboo phrases may be accepted via a terminal device or the like used by the person in question.

[0046] The taboo phrase setting module sets taboo phrases (step S31). The taboo phrase setting module sets the received taboo phrase as a taboo phrase that the interviewee must not utter during the interview.

[0047] The recovery plan setting module sets a recovery plan (step S32). The recovery plan is a way of responding after the interviewee utters a taboo phrase during the interview, such as a way of apologizing, a way of explaining, or a way of changing the topic. The recovery plan setting module sets a recovery plan for each taboo phrase that has been set. The recovery plan setting module sets one or more recovery plans for each taboo phrase. The recovery plan setting module may set a pre-set recovery plan for each taboo phrase, may accept input of a recovery plan in accordance with input of the taboo phrase and set the accepted recovery plan for each taboo phrase, or may set a recovery plan for each taboo phrase by some other method.

[0048] This completes the taboo phrase setting process. The computer 10 executes the alert process, which will be described later, using the set taboo phrases.

[0049] [First Learning Process Executed by Computer 10] The first learning process executed by the computer 10 will be described with reference to Fig. 6. The figure shows a flowchart of the first learning process executed by the computer 10. The first learning process is executed before the interviewer conducts an interview with the interviewee.

[0050] The internal data acquisition module acquires predetermined internal data (step S40). Internal data is data exchanged within a company, organization, etc., such as internal documents and internal chat content. The internal data acquisition module acquires the internal data from an external database (not shown), etc. If the computer 10 itself holds the internal data in advance, the internal data held therein may be acquired.

[0051] The learning module learns predetermined internal data (step S41). The learning method performed by the learning module may be machine learning such as supervised learning, unsupervised learning, or reinforcement learning, or deep learning using convolutional neural networks, recurrent neural networks, long-short-term memory, etc. Note that the learning method performed by the learning module is not limited to the examples described above.

[0052] The model generation module generates a first trained model based on the training result (step S42). The method by which the model generation module generates the first trained model based on the learning results may be any existing method, and detailed description thereof will be omitted.

[0053] The storage module stores the first trained model (step S43).

[0054] This completes the first learning process. The computer 10 uses the generated first trained model to execute the interview advice providing process described below.

[0055] [Second Learning Process Executed by Computer 10] The second learning process executed by the computer 10 will be described with reference to Fig. 7. The figure shows a flowchart of the second learning process executed by the computer 10. The second learning process is executed before the interviewer conducts an interview with the interviewee.

[0056] The voice data acquisition module acquires voice data that has been acquired in the past (step S50). The previously acquired voice data is voice data from an interview that was previously acquired and stored as a result of the interview advice providing process described below. The voice data acquisition module acquires voice data that has been acquired in the past and that is held by the module itself.

[0057] The learning module learns previously acquired voice data (step S51). The learning method executed by the learning module may be the same as that in the process of step S41 described above.

[0058] The model generation module generates a second trained model based on the training result (step S52). The method by which the model generation module generates the second trained model based on the learning results may be any existing method, and detailed description thereof will be omitted.

[0059] The storage module stores the second trained model (step S53).

[0060] This completes the second learning process. The computer 10 uses the generated second trained model to execute the interview advice providing process described below.

[0061] [Interview advice providing process executed by computer 10] The interview advice providing process executed by the computer 10 will be described with reference to Figure 8. This figure is a diagram showing a flowchart of the interview advice providing process executed by the computer 10. This interview advice providing process details an audio data acquisition process (step S2) that acquires audio data during the interview during the interview proceeding in real time, a statement content analysis process (step S3) that analyzes the meaning of the statement content of the acquired audio data during the interview proceeding in real time, an interview advice generation process (step S4) that generates interview advice for achieving the interview goal based on the analysis result of the meaning of the statement content during the interview proceeding in real time, and an interview advice providing process (step S5) that provides interview advice to the interviewer during the interview proceeding in real time. This interview advice providing process is executed while the interviewer is conducting an interview with the interviewee.

[0062] The voice data acquisition module acquires voice data during the interview while the interview is proceeding in real time (step S60). A sound collection device (not shown) such as a microphone installed at the location where the interview is being conducted, or a sound collection device installed on the information terminal 3, collects the voices of the interviewer and the interviewee during the interview which is proceeding in real time, and transmits the collected voices to the computer 10 as voice data from the interview. The voice data acquisition module receives this voice data and acquires voice data during the interview as it progresses in real time. The voice data acquired by the voice data acquisition module may be the voice of either the interviewer or the interviewee, rather than just the voice of both the interviewer and the interviewee. The computer 10 may also perform speaker diarization on the acquired audio data to identify each speaker included in the audio data (whether the speaker is the interviewer, the interviewee, or, if there are multiple interviewees, which of the interviewees they are, or, if there are multiple interviewees, which of the interviewees they are).

[0063] The storage module stores the acquired voice data (step S61). The storage module stores the acquired voice data in association with data related to the ongoing interview, such as the type of interview, the interview goal, the interviewer's identifier, the interviewee's identifier, the date and time of the interview, etc. The storage module may also associate the identifier of each speaker with each voice based on the result of speaker diarization of the acquired voice data.

[0064] The speech content analysis module analyzes the meaning of the speech content of the acquired voice data during the interview that is progressing in real time (step S62). The utterance content analysis module analyzes the meaning of each utterance made by the interviewer and the interviewee in the audio data. Furthermore, the utterance content analysis module analyzes the audio data including the tone, tempo, and conversation content of the interviewer's voice and the tone, tempo, and conversation content of the interviewee's voice in addition to the meaning of each utterance. When speaker diarization is performed and there are multiple interviewers, the utterance content analysis module analyzes the audio data for each speaker including the tone, tempo, and conversation content in addition to the meaning of the utterance content. The utterance content analysis module analyzes the meaning, tone, tempo, and content of each utterance using a predetermined algorithm, etc. The analysis method executed by the utterance content analysis module is not particularly limited and can be designed as appropriate.

[0065] The advice generation module generates interview advice for achieving the interview goal based on the analysis result of the meaning of the utterance content during the interview that is progressing in real time (step S63). Interview advice is advice necessary to achieve the set interview goals, such as whether time allocation is good / good, whether the number of questions is sufficient / insufficient, whether the questions are appropriate / inappropriate, whether the speaking speed is fast / normal / slow, and whether the answers are clear / unclear. The advice generation module generates this interview advice based on the analysis results of the voice data. For example, if the analysis results show that the interviewee speaks too quickly, the advice generation module generates interview advice such as "please speak a little more slowly" to encourage the interviewee to slow down. In other cases, the advice generation module similarly generates interview advice such as a statement about measures the interviewee needs to take to achieve the interview goal.

[0066] The advice generation module may also generate interview advice that suggests improvements for the interviewee based on the results of an analysis of the meaning of the utterances and the results of an analysis of the tone, tempo, and content of the interviewee's voice. For example, the advice generation module may determine the content of the question, speaking speed, clarity of the answer, etc. based on the analysis results, and generate interview advice that suggests improvements based on the results of the determination.

[0067] Furthermore, the advice generation module may generate interview advice using the results of learning predetermined internal data in addition to the results of analyzing the voice data. In this case, the advice generation module may generate interview advice based on the first trained model generated by the first learning process described above and the analysis results of the voice data. For example, the advice generation module compares the learning results of the internal data with the analysis results of the voice data, and if there is any contradiction or inconsistency with the internal data, generates interview advice to resolve this contradiction or inconsistency. Furthermore, the advice generation module may generate interview advice based on the first trained model and the meaning, tone, tempo, and conversation content of the interviewee's utterances, generating an answer tailored to the interviewee's question. This answer may be in Q&A format, or may simply be the answer itself. The answer may be multiple, not just one. For example, the advice generation module compares the interviewee's question based on the analysis results with the learning results of the internal data, and generates interview advice by selecting an answer that matches or is similar to the learning results of the internal data as the answer to the question.

[0068] Furthermore, the advice generation module may generate interview advice using the results of learning past voice data in addition to the analysis results of the voice data acquired this time. In this case, the advice generation module may generate interview advice based on the second trained model generated by the second learning process described above and the analysis results of the voice data. For example, the advice generation module may compare the learning results of past voice data with the interviewer's time allocation, number of questions, and question content based on the analysis results of the voice data, determine whether the time allocation is incorrect, whether the number of questions is insufficient, whether the questions are appropriate, etc., and generate interview advice based on the determination results.

[0069] The advice generation module may also calculate the interviewee's satisfaction level based on the analysis of the voice data and generate interview advice based on this satisfaction level. For example, satisfaction level may indicate that the interviewee is interested in the company in the case of a recruitment interview, or that the interviewee is satisfied with the interview in the case of a personnel evaluation interview. In this case, the advice generation module may calculate the satisfaction level based on the analysis results of the meaning of the interviewee's utterances, the tone and tempo of the voice, and the content of the conversation. For example, the advice generation module calculates the satisfaction level of the interviewee based on whether the analysis results of the meaning of the interviewee's utterances, the tone and tempo of the voice, and the content of the conversation meet preset standards (high tone, high tempo, number of questions, etc.). The advice generation module determines that satisfaction is high when the tone and tempo are high, and that satisfaction is high when the number of questions is increasing. The advice generation module calculates the satisfaction level of the interviewee based on the determined satisfaction level. The satisfaction level may be expressed by a numerical value, or may be expressed by something other than a numerical value, such as a symbol or a character string. The method of calculating satisfaction level is not particularly limited and can be designed as appropriate. The advice generation module generates interview advice based on the calculated satisfaction level. For example, the advice generation module may use the satisfaction level itself as the interview advice, or may use a preset phrase or the like for the satisfaction level as the interview advice.

[0070] The advice generation module may also calculate the interviewee's dissatisfaction level based on the analysis of the voice data, and generate interview advice based on this dissatisfaction level. The dissatisfaction level may be, for example, that the interviewee is angry, sad, or depressed. In this case, the advice generation module may calculate the dissatisfaction level based on the analysis results of the meaning of the interviewee's utterances, the tone and tempo of the voice, and the content of the conversation. For example, the advice generation module calculates the dissatisfaction level of the interviewee based on whether the analysis results of the meaning of the interviewee's utterances, the tone and tempo of the voice, and the content of the conversation meet preset standards (high tone, high tempo, number of questions, etc.). The advice generation module determines that dissatisfaction is high when the tone or tempo is low, and high when the number of questions is decreasing. The advice generation module calculates the dissatisfaction level of the interviewee based on the determined dissatisfaction level. The dissatisfaction level may be expressed by a numerical value, or may be expressed by something other than a numerical value, such as a symbol or a character string. The method of calculating the dissatisfaction level is not particularly limited and can be designed as appropriate. The advice generation module generates interview advice based on the calculated dissatisfaction level. For example, the advice generation module may use the dissatisfaction level itself as the interview advice, or may use a phrase or the like that is preset for the dissatisfaction level as the interview advice.

[0071] The advice generation module may also generate an interview agenda as interview advice using the learning results of predetermined internal data. In this case, the advice generation module may generate, as interview advice, an interview agenda based on the first trained model generated by the first learning process described above. For example, the advice generation module may generate, as interview advice, an interview agenda including important questions, time allocation, etc., based on the learning results of the internal data. Furthermore, if a pre-existing interview agenda exists, the advice generation module may update the pre-existing interview agenda with the content of the interview agenda generated based on the learning results of the internal data. For example, the advice generation module updates the pre-existing interview agenda by increasing the number of important questions or changing the content of the questions to better questions. Furthermore, if a prior interview agenda exists, the advice generation module may determine whether the interview is progressing according to the interview agenda based on the analysis results of the voice data, and generate interview advice based on the determination result of the interview progress. For example, the advice generation module may determine whether there are any omissions or omissions in the prior interview agenda, whether unnecessary things have been said, whether the interview is taking too long, etc., and generate interview advice based on the determination result.

[0072] Furthermore, the advice generation module may generate interview advice using the analysis results of the evaluation information in addition to the analysis results of the voice data. In this case, the advice generation module may generate interview advice based on the analysis results of the evaluation information and the voice data obtained by the processing in step S22 described above. For example, the advice generation module may compare the analysis results of the evaluation information with the analysis results of the voice data, and if there is any contradiction or inconsistency with the evaluation information, generate interview advice to resolve this contradiction or inconsistency.

[0073] Furthermore, when there are multiple interviewees, the advice generation module may generate interview advice for interviewees other than the speaker to achieve the interview goal. In this case, the advice generation module may identify the speaker based on the meaning of each speaker's utterance content based on speaker diarization, the tone of the voice, the tempo, or the analysis results of the conversation content, and then generate interview advice for achieving the interview goals of the other speakers. That is, interview advice tailored to the interview content may be generated for each interviewer other than the one interviewer. For example, the advice generation module may generate interview advice tailored to the question asked by one interviewer for another interviewer. In this case, in the process of step S64 described below, the advice providing module may provide the generated interview advice to interviewees other than the speaker, or to interviewees including the speaker.

[0074] The advice providing module provides interview advice to the interviewee during the interview that is proceeding in real time (step S64). The advice providing module provides the interview advice to the interviewee by sending the generated interview advice to the information terminal 3 or by having a speaker (not shown) installed at the interview location emit the advice. A case where the advice providing module provides interview advice to the information terminal 3 will be described. The advice providing module transmits the generated interview advice to the information terminal 3. The information terminal 3 receives this interview advice and displays it on its own display unit via a predetermined UI such as a predetermined application or a predetermined website. The advice providing module displays interview advice on the information terminal 3, thereby providing the interview advice to the interviewee during the interview that is progressing in real time.

[0075] The above is the interview advice providing process.

[0076] [Alert processing performed by computer 10] The alert processing executed by the computer 10 will be described with reference to Fig. 9. The figure shows a flowchart of the alert processing executed by the computer 10. This alert process is executed while the interviewer is conducting an interview with the interviewee, and is executed simultaneously with the above-mentioned interview advice providing process.

[0077] The taboo phrase determination module determines whether or not the acquired voice data contains any taboo phrases (step S70). The taboo phrase determination module determines whether or not the acquired voice data contains any of the taboo phrases set in the process of step S31, based on the analysis result of the voice data in the process of step S62. If the taboo phrase determination module determines that the acquired voice data does not contain any taboo phrases (NO in step S70), the computer 10 ends this alert process.

[0078] On the other hand, if the taboo phrase determination module determines that the acquired voice data contains a taboo phrase (YES in step S70), the alert module issues an alert to the interviewing party (step S71). The alert executed by the alert module is not particularly limited as long as it is a notification to point out to the interviewer that a forbidden word has been uttered, and for example, it may output a specified sound from a sound-emitting device such as a speaker installed at the location where the interview is being conducted, or notify the information terminal 3 of a specified message as an alert. A case where the alert module notifies the information terminal 3 of an alert will be described. The alert module transmits wording corresponding to the included taboo phrases (asking about religious views, asking about family structure, legally questionable statements, ethically questionable statements, etc.) to the information terminal 3. The information terminal 3 receives this wording and displays it on its own display unit via a predetermined UI such as a predetermined application or a predetermined website. The alert module alerts the interviewing party by displaying this message on the information terminal 3.

[0079] The advice generation module generates the recovery plan as consultation advice (step S72). The advice generation module generates interview advice based on the recovery plan for the included taboo phrases set by the process of step S32. For example, if the advice generation module has asked about religious views, it may generate interview advice such as how to apologize or how to change the topic. Thereafter, the advice providing module provides the generated interview advice to the interviewee during the interview that is proceeding in real time, similar to the process in step S64.

[0080] This completes the alert processing.

[0081] [Minutes provision process executed by computer 10] The minutes providing process executed by the computer 10 will be described with reference to Fig. 10. The figure shows a flowchart of the minutes providing process executed by the computer 10. This minutes provision process is executed from while the interviewer is conducting an interview with the interviewee until after the interview has ended.

[0082] The minutes generation module generates minutes during the interview that is proceeding in real time (step S80). The minutes generation module generates minutes based on the analysis results of the voice data processed in step S62. For example, if there is an interview sheet or the like with questions set in advance, the minutes generation module generates minutes by automatically inputting answers and reactions to the questions into this interview sheet. Note that the minutes generated by the minutes generation module are not limited to the examples described above, and the format, content, etc. can be designed as appropriate.

[0083] The end determination module determines whether the interview has ended (step S81). The end determination module determines whether or not the interview has ended by determining whether or not a preset message relating to the end of the interview (such as "the interview is over") is present, based on the analysis result of the voice data obtained by the process in step S62. If the end determination module determines that the interview has not ended (step S81 NO), the computer 10 repeats the process of step S80 again.

[0084] On the other hand, if the end determination module determines that the interview has ended (YES in step S81), the minutes creation module ends the creation of the minutes (step S82).

[0085] The minutes providing module provides the generated minutes to the interviewing party (step S83). The minutes providing module transmits the generated minutes to the information terminal 3. The information terminal 3 receives the minutes and displays them on its display unit via a predetermined UI such as a predetermined application or a predetermined website. The minutes providing module displays the minutes on the information terminal 3, thereby providing the minutes to the person having the meeting.

[0086] This completes the minutes provision process.

[0087] [Audio data providing process executed by computer 10] The voice data providing process executed by the computer 10 will be described with reference to Fig. 11. The figure shows a flowchart of the voice data providing process executed by the computer 10. This voice data providing process is executed from while the interviewer is conducting an interview with the interviewee until after the interview has ended.

[0088] The end determination module determines whether the interview has ended (step S90). The process of step S90 is similar to the process of step S81 described above. If the end determination module determines that the interview has not ended (step S90 NO), the computer 10 ends this voice data providing process.

[0089] On the other hand, if the end determination module determines that the interview has ended (YES in step S90), the storage module ends storage of the voice data (step S91).

[0090] The voice data providing module provides the stored voice data to the interviewing party (step S92). The voice data providing module transmits the stored voice data to the information terminal 3. The information terminal 3 receives and stores this voice data. The voice data providing module stores the stored voice data in the information terminal 3, thereby providing the stored voice data to the interviewing party.

[0091] This completes the voice data providing process.

[0092] [Evaluation Providing Process Executed by Computer 10] The evaluation providing process executed by the computer 10 will be described with reference to Fig. 12. The figure shows a flowchart of the evaluation providing process executed by the computer 10. This evaluation providing process is executed from while the interviewer is conducting an interview with the interviewee until after the interview has ended.

[0093] The end determination module determines whether the interview has ended (step S100). The process of step S100 is similar to the process of step S81 described above. If the end determination module determines that the interview has not ended (step S100 NO), the computer 10 ends this evaluation providing process.

[0094] On the other hand, if the end determination module determines that the interview has ended (YES in step S100), the evaluation generation module generates an overall evaluation of the interview (step S101). The overall evaluation of the interview is an evaluation of the interviewer who conducted the interview or an evaluation of the interview itself, and may be expressed numerically, or as symbols, characters of text, etc. The evaluation generation module generates an overall evaluation of the interview based on the results of analyzing the voice data in step S62 and the results of generating the interview advice in step S63. For example, the evaluation generation module generates a high evaluation if the interviewee's satisfaction level is high based on the results of analyzing the voice data, or if the generated interview advice indicates that there were few problems with the interview. Conversely, the evaluation generation module generates a low evaluation if the interviewee's dissatisfaction level is high, or if the generated interview advice indicates that there were many problems with the interview. In addition to the examples described above, the evaluation generation module may also generate an overall evaluation of the interview based on other content, such as the results of generating each interview advice described in the processing of step S63, and whether or not an alert was issued by the processing of step S70.

[0095] The evaluation providing module provides the generated evaluation to the interviewing party (step S102). The evaluation providing module transmits the generated evaluation to the information terminal 3. The information terminal 3 receives this evaluation and displays it on its display unit via a predetermined UI such as a predetermined application or a predetermined website. The evaluation providing module provides the generated evaluation to the interviewing party by causing the information terminal 3 to display the evaluation.

[0096] This completes the evaluation providing process.

[0097] [Report provision process executed by computer 10] The report providing process executed by the computer 10 will be described with reference to Fig. 13. The figure shows a flowchart of the report providing process executed by the computer 10. This report provision process is executed from while the interviewer is conducting an interview with the interviewee until after the interview has ended.

[0098] The end determination module determines whether the interview has ended (step S110). The process of step S100 is similar to the process of step S81 described above. If the end determination module determines that the interview has not ended (step S110 NO), the computer 10 ends this report providing process.

[0099] On the other hand, if the end determination module determines that the interview has ended (YES in step S110), the summarization module summarizes the contents of the interview based on the analysis result of the meaning of the utterances (step S111). The summarization module summarizes the contents of the interview based on the analysis results of the voice data by the processing in step S62. The method of summarizing the contents of the interview executed by the summarization module is not particularly limited, and the format and content can be designed as appropriate.

[0100] The extraction module extracts important points from the interview based on the summary (step S112). The key points are pre-set phrases related to the interview goals. The extraction module extracts important points based on the generated summary. The method of extracting important points executed by the extraction module is not particularly limited, and the format and content can be designed as appropriate.

[0101] The report generation module generates a report summarizing important points (step S113). The report generation module generates a report summarizing the important points based on the extracted important points. The method of generating the report executed by the report generation module is not particularly limited, and the format and content can be designed as appropriate.

[0102] The report providing module provides the report to the interviewee (step S114). The report providing module transmits the generated report to the information terminal 3. The information terminal 3 receives this report and displays it on its own display unit via a predetermined UI such as a predetermined application or a predetermined website. The report providing module provides the generated report to the interviewing party by displaying the report on the information terminal 3.

[0103] This completes the report providing process.

[0104] Although the above-described processes are described as separate processes, the computer 10 can be configured to execute a combination of some or all of the above-described processes. Also, the computer 10 can be configured to execute each process at a timing other than the timing described. Furthermore, although each of the above-mentioned processes is described as a process executed by the computer 10, it is also possible to configure some or all of the processes to be executed by the information terminal 3 itself or a specific application installed on the information terminal 3.

[0105] The above-described means and functions are realized by a computer (including a CPU, an information processing device, and various terminals) reading and executing a predetermined program. The program may be provided, for example, from a computer via a network (Software as a Service (SaaS)) or as a cloud service. The program may also be provided in a form recorded on a computer-readable recording medium. In this case, the computer reads the program from the recording medium, transfers it to an internal or external recording device, records it, and executes it. The program may also be pre-recorded on a recording device (recording medium) and provided to the computer from the recording device via a communication line.

[0106] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. Furthermore, the effects described in the embodiments of the present invention are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments of the present invention.

[0107] A first aspect disclosed in this embodiment is a real-time interview advice providing system that analyzes the meaning of utterance content of voice data during an interview that is progressing in real time, and generates and provides interview advice for achieving a predetermined interview goal, an interview goal setting unit that sets interview goals according to the type of interview; a voice data acquisition unit that acquires the voice data during the interview during the interview that is proceeding in real time; a speech content analysis unit that analyzes the meaning of speech content of the acquired voice data during the interview that is progressing in real time; an interview advice generating unit that generates interview advice for achieving the interview goal based on the analysis result of the meaning of the utterance content during the interview that is progressing in real time; an interview advice providing unit that provides the interview advice to the interviewee during the interview that is proceeding in real time; To provide a real-time interview advice providing system comprising:

[0108] A second aspect disclosed in this embodiment includes a storage unit that stores the acquired voice data; a voice data providing unit that provides the stored voice data to the interviewer after the interview is completed; The real-time interview advice providing system according to the first aspect is further provided.

[0109] A third aspect disclosed in this embodiment is an internal data learning unit that learns predetermined internal data; Further provided with the interview advice generation unit generates the interview advice based on the learning result of the internal data and the analysis result of the meaning of the utterance content; A real-time interview advice providing system according to a first aspect is provided.

[0110] In a fourth aspect disclosed in this embodiment, the speech content analysis unit analyzes the meaning of the speech content of the person being interviewed in the acquired voice data, the interview advice generation unit generates, as the interview advice, an answer content in accordance with the question content of the interviewee based on an analysis result of the meaning of the utterance content of the interviewee based on the learning result of the internal data; A system for providing real-time interview advice according to a third aspect is provided.

[0111] A fifth aspect disclosed in this embodiment is that the interview advice generation unit generates an interview agenda as the interview advice based on a learning result of the internal data. A system for providing real-time interview advice according to a third aspect is provided.

[0112] In a sixth aspect disclosed in this embodiment, when a prior interview agenda exists, the interview advice generation unit updates the prior interview agenda to the generated interview agenda. A real-time interview advice providing system according to a fifth aspect is provided.

[0113] A seventh aspect disclosed in the present embodiment is a voice data learning unit that learns the voice data acquired in the past; Further provided with the interview advice generation unit compares a learning result of the voice data previously acquired with the voice data currently acquired, and generates an area for improvement for the interviewing party as the interview advice; A real-time interview advice providing system according to a first aspect is provided.

[0114] An eighth aspect disclosed in this embodiment is that, when a prior interview agenda exists, the interview advice generation unit determines, based on the acquired voice data, whether the interview is proceeding according to the prior interview agenda, and generates the interview advice based on the determination result of the progress of the interview. A real-time interview advice providing system according to a first aspect is provided.

[0115] In a ninth aspect disclosed in this embodiment, the utterance content analysis unit analyzes the tone, tempo and conversation content of the voice of the person being interviewed in addition to the meaning of the utterance content, the interview advice generation unit generates the interview advice based on the analysis result of the meaning of the utterance content and the analysis result of the tone, tempo and conversation content of the voice of the interviewee. A real-time interview advice providing system according to a first aspect is provided.

[0116] In a tenth aspect disclosed in this embodiment, the interview advice generation unit calculates a satisfaction level of the interviewee based on an analysis result of the tone, tempo and conversation content of the voice of the interviewee, and generates interview advice based on the calculated satisfaction level. A real-time interview advice providing system according to a ninth aspect is provided.

[0117] An eleventh aspect disclosed in this embodiment is that the interview advice generation unit calculates the dissatisfaction level of the interviewee based on the analysis results of the tone, tempo and conversation content of the voice of the interviewee, and generates interview advice based on the calculated dissatisfaction level. A real-time interview advice providing system according to a ninth aspect is provided.

[0118] In a twelfth aspect disclosed in this embodiment, the interview advice generation unit generates, as the interview advice, improvements to be made by the interviewer based on the analysis results of the meaning of the utterance content and the analysis results of the tone, tempo and conversation content of the interviewee's voice. A real-time interview advice providing system according to a ninth aspect is provided.

[0119] A thirteenth aspect disclosed in this embodiment is a taboo phrase setting unit that sets taboo phrases; a taboo phrase determination unit that determines whether the voice data includes the set taboo phrase; an alert unit that alerts the interviewer when a forbidden phrase is included; The real-time interview advice providing system according to the first aspect is further provided.

[0120] In a fourteenth aspect disclosed in this embodiment, the interview advice generation unit generates a recovery plan as the interview advice when a taboo phrase is included. A thirteenth aspect of the present invention provides a system for providing real-time interview advice.

[0121] A fifteenth aspect disclosed in this embodiment is a method for evaluating the effectiveness of the interview, comprising: an evaluation providing unit that provides the generated evaluation to the interviewing party; The real-time interview advice providing system according to the first aspect is further provided.

[0122] A sixteenth aspect disclosed in the present embodiment is a method for acquiring voice data of a plurality of interviewees during an interview, The speech content analysis unit analyzes the meaning of speech content of each interviewer in the acquired voice data of the plurality of interviewers, the interview advice generation unit generates the interview advice for the interviewer other than the speaker to achieve the interview goal based on the analysis result of the meaning of the utterance content; the interview advice providing unit provides the interview advice to an interviewer other than the speaker; A real-time interview advice providing system according to a first aspect is provided.

[0123] A seventeenth aspect disclosed in the present embodiment is a minutes generation unit that generates minutes during an interview that is proceeding in real time; The real-time interview advice providing system according to the first aspect is further provided.

[0124] An eighteenth aspect disclosed in this embodiment is a summary unit that summarizes the contents of the interview based on the analysis result of the meaning of the utterance contents after the interview is completed; an extraction unit that extracts important points from the interview based on the summary; a report generator that generates a report summarizing the important points; The real-time interview advice providing system according to the first aspect is further provided.

[0125] A nineteenth aspect disclosed in this embodiment is a method for preparing a template for a meeting, comprising: a selection unit for selecting a template desired by the person having the meeting from templates set according to the type of meeting; Further provided with the interview goal setting unit sets the selected template as the interview goal; A real-time interview advice providing system according to a first aspect is provided.

[0126] A twentieth aspect disclosed in the present embodiment is a method for acquiring evaluation information, comprising: an evaluation information analysis unit that analyzes the acquired evaluation information; Further provided with the interview advice generation unit generates the interview advice based on an analysis result of the meaning of the statement content and an analysis result of the evaluation information. A real-time interview advice providing system according to a first aspect is provided.

[0127] A 21st aspect disclosed in this embodiment is a rating information acquisition unit that acquires rating information; Further provided with the interview goal setting unit sets the interview goal according to the type of interview and the evaluation information; A real-time interview advice providing system according to a first aspect is provided. [Explanation of symbols]

[0128] 1. Real-time interview advice system 3. Information terminals 8 Network 10. Computers

Claims

1. A real-time interview advice providing system that analyzes the meaning of speech content of voice data during an interview that is progressing in real time, and generates and provides interview advice for achieving a predetermined interview goal, an interview goal setting unit that sets interview goals according to the type of interview; a voice data acquisition unit that acquires the voice data during the interview during the interview that is proceeding in real time; a speech content analysis unit that analyzes the meaning of speech content of the acquired voice data during the interview that is progressing in real time; an interview advice generating unit that generates interview advice for achieving the interview goal based on the analysis result of the meaning of the utterance content during the interview that is progressing in real time; an interview advice providing unit that provides the interview advice to the interviewee during the interview that is proceeding in real time; A real-time interview advice providing system.

2. a storage unit that stores the acquired voice data; a voice data providing unit that provides the stored voice data to the interviewer after the interview is completed; The system for providing real-time interview advice according to claim 1 , further comprising:

3. an internal data learning unit that learns predetermined internal data; Further provided with the interview advice generation unit generates the interview advice based on a learning result of the internal data and an analysis result of the meaning of the utterance content. The system for providing real-time interview advice according to claim 1 .

4. The speech content analysis unit analyzes the meaning of the speech content of the person being interviewed in the acquired voice data, the interview advice generation unit generates, as the interview advice, an answer content in accordance with the question content of the interviewee based on an analysis result of the meaning of the utterance content of the interviewee based on the learning result of the internal data; The real-time interview advice providing system according to claim 3 .

5. the interview advice generation unit generates an interview agenda as the interview advice based on the learning result of the internal data; The real-time interview advice providing system according to claim 3 .

6. When a prior interview agenda exists, the interview advice generation unit updates the prior interview agenda to the generated interview agenda. The real-time interview advice providing system according to claim 5 .

7. a voice data learning unit that learns the voice data acquired in the past; Further provided with the interview advice generation unit compares a learning result of the previously acquired voice data with the currently acquired voice data, and generates an area for improvement for the interviewing party as the interview advice; The system for providing real-time interview advice according to claim 1 .

8. When a prior interview agenda exists, the interview advice generation unit determines whether the interview is progressing according to the prior interview agenda based on the acquired voice data, and generates the interview advice based on the determination result of the progress of the interview. The system for providing real-time interview advice according to claim 1 .

9. The speech content analysis unit analyzes the meaning of the speech content as well as the tone, tempo and conversation content of the voice of the person being interviewed, the interview advice generation unit generates the interview advice based on an analysis result of the meaning of the utterance content and an analysis result of the tone, tempo and conversation content of the voice of the interviewee. The system for providing real-time interview advice according to claim 1 .

10. the interview advice generation unit calculates a degree of satisfaction of the interviewee based on an analysis result of the tone, tempo and conversation content of the voice of the interviewee, and generates interview advice based on the calculated degree of satisfaction; The system for providing real-time interview advice according to claim 9.

11. the interview advice generation unit calculates a dissatisfaction level of the interviewee based on an analysis result of the tone, tempo and conversation content of the voice of the interviewee, and generates interview advice based on the calculated dissatisfaction level; The system for providing real-time interview advice according to claim 9.

12. the interview advice generation unit generates, as the interview advice, improvements to be made by the interviewer based on the analysis results of the meaning of the utterance content and the analysis results of the tone, tempo and conversation content of the voice of the interviewee; The system for providing real-time interview advice according to claim 9.

13. a taboo phrase setting unit for setting taboo phrases; a taboo phrase determination unit that determines whether the voice data includes the set taboo phrase; an alert unit that alerts the interviewer when a forbidden phrase is included; The system for providing real-time interview advice according to claim 1 , further comprising:

14. the consultation advice generation unit generates a recovery plan as the consultation advice when the taboo phrase is included; The system for providing real-time interview advice according to claim 13.

15. an evaluation generation unit that generates an overall evaluation of the interview after the interview is completed; an evaluation providing unit that provides the generated evaluation to the interviewing party; The system for providing real-time interview advice according to claim 1 , further comprising:

16. the voice data acquisition unit acquires voice data of a plurality of interviewees during an interview; The speech content analysis unit analyzes the meaning of speech content of each interviewee from the acquired voice data of the plurality of interviewees, the interview advice generation unit generates the interview advice for the interviewer other than the speaker to achieve the interview goal based on the analysis result of the meaning of the utterance content; the interview advice providing unit provides the interview advice to an interviewer other than the speaker; The system for providing real-time interview advice according to claim 1 .

17. A minutes generation unit that generates minutes during an interview that is taking place in real time; The system for providing real-time interview advice according to claim 1 , further comprising:

18. a summarizing unit that summarizes the contents of the interview based on the analysis result of the meaning of the utterance contents after the interview is completed; an extraction unit that extracts important points from the interview based on the summary; a report generator that generates a report summarizing the important points; The system for providing real-time interview advice according to claim 1 , further comprising:

19. a selection unit for selecting a template desired by the interviewer from templates set according to the type of interview; Further provided with the interview goal setting unit sets the selected template as the interview goal; The system for providing real-time interview advice according to claim 1 .

20. an evaluation information acquisition unit that acquires evaluation information; an evaluation information analysis unit that analyzes the acquired evaluation information; Further provided with the interview advice generation unit generates the interview advice based on an analysis result of the meaning of the comment content and an analysis result of the evaluation information. The system for providing real-time interview advice according to claim 1 .

21. an evaluation information acquisition unit that acquires evaluation information; Further provided with the interview goal setting unit sets the interview goal according to the type of interview and the evaluation information; The system for providing real-time interview advice according to claim 1 .

22. A real-time interview advice providing method executed by a computer, which analyzes the meaning of utterance content of voice data during an interview proceeding in real time, and generates and provides interview advice for achieving a predetermined interview goal, A step of setting interview goals according to the type of interview; acquiring said voice data during the interview during the interview proceeding in real time; analyzing the meaning of the speech content of the acquired voice data during the interview proceeding in real time; generating interview advice for achieving the interview goal based on the analysis result of the meaning of the utterance content during the interview proceeding in real time; providing the interview advice to the interviewer during the interview proceeding in real time; A method for providing real-time interview advice.

23. A computer that analyzes the meaning of what is said in the voice data during a real-time interview and generates and provides interview advice to achieve pre-set interview goals. Steps for setting interview goals according to the type of interview; acquiring the voice data during the interview during the interview proceeding in real time; a step of analyzing the meaning of the speech content of the acquired voice data during the interview proceeding in real time; generating interview advice for achieving the interview goal based on the analysis result of the meaning of the utterance content during the interview proceeding in real time; providing the interview advice to the interviewee during the interview proceeding in real time; A computer-readable program for executing the program.

Images