Information processing device, information processing method, and information processing program

Abstract

To efficiently conduct interviews.SOLUTION: An information processing device comprises a text generation unit and an output unit. The text generation unit generates response texts to user utterances and question texts for asking the user preset interview items using a text generation model for generating responses to the input texts on the basis of expert knowledge related to an interview subject and interview knowledge related to interviewing skills. The output unit outputs the response texts and question texts generated by the text generation unit to the user.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The disclosed embodiments relate to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are systems for conducting interviews with interviewees. For example, Patent Document 1 discloses a technology for eliciting requests regarding a house from an interviewee who will be a client when designing the house.

[0003] In the technology described in Patent Document 1, keywords that are highly desired by the interviewee are extracted by setting the next question item from keywords contained in the interviewee's answers. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2023-145358 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the conventional technology, it is necessary to repeatedly ask the same questions to the interviewee, so there is room for improvement in terms of conducting interview surveys efficiently.

[0006] The present invention has been made in view of the above, and has as its object to provide an information processing device, an information processing method, and an information processing program that can efficiently conduct interview surveys. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, an information processing device according to the present invention includes a sentence generation unit and an output unit. The sentence generation unit uses a sentence generation model that generates answers to input sentences based on specialized knowledge about the interview subject and interview knowledge about interview skills, and generates answer documents to the content of the user's utterance and question sentences that ask the user about predetermined interview items. The output unit outputs the answer sentences and question sentences generated by the sentence generation unit to the user. [Effects of the Invention]

[0008] According to the present invention, interview surveys can be carried out efficiently. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an outline of an information processing apparatus according to an embodiment. [Figure 2] Figure 2 is an explanatory diagram of the interview. [Figure 3] FIG. 3 is a block diagram of an information processing device. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in the user information storage unit. [Figure 5] FIG. 5 is a diagram illustrating an example of information stored in the interview information storage unit. [Figure 6] FIG. 6 is a diagram illustrating an example of a report generated by the report generating unit. [Figure 7] FIG. 7 is a flowchart illustrating an example of the setting process according to the embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of an interview process according to the embodiment. [Figure 9] FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0011] [Information Processing] First, an overview of an information processing device according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram illustrating an overview of an information processing device according to an embodiment. The information processing device 1 shown in Fig. 1 is a device that carries out an interview survey requested by a company representative.

[0012] More specifically, the information processing device 1, at the request of a company employee, conducts an in-depth interview with a user U who is to be interviewed. The information processing device 1 is realized by a server or a cloud.

[0013] The user terminal 100 shown in Fig. 1 is a terminal device owned by a user U. In the example shown in Fig. 1, the user terminal 100 is a smartphone. However, the user terminal 100 may also be a personal computer, a tablet terminal, or the like.

[0014] Companies provide products such as their own services and goods, and improve them based on user evaluations of the products. For example, in-depth interviews are a method for collecting user evaluations.

[0015] In-depth interviews are effective at understanding a user's true thoughts and feelings because they involve a one-on-one conversation between the interviewer and the user. However, when a company conducts in-depth interviews with users, it requires a lot of effort and cost, including arranging an interviewer.

[0016] Furthermore, depending on the interviewer's interviewing skills, useful information may not be obtained from the user, and even if the user gives the same answer, appropriate feedback may not be obtained from the user due to the interviewer's personal bias.

[0017] Interviewers are required to have specialized knowledge about the product and interview knowledge about interview skills. In this disclosure, we aim to improve the efficiency of interview surveys by conducting in-depth interviews using so-called generative AI (Artificial Intelligence).

[0018] 1, the information processing device 1 receives interview settings from a company (step S1). The interview settings include settings for items such as the product to be interviewed, interview questions, attributes of the interviewee, the number of interviews to be conducted, and compensation to be paid to the interviewee.

[0019] The information processing device 1 selects a user U to be interviewed based on this information, and conducts an interview with the user U via the user terminal 100 (step S2).

[0020] The information processing device 1 uses a sentence generation model to conduct an interview with a user U. The sentence generation model is a model that generates an answer to an input sentence. The sentence generation model generates a response document to an utterance sentence that is obtained by converting the content of an utterance by a user into a sentence. For example, the sentence generation model is a large-scale machine learning model mainly constructed by deep learning, and is a generative AI that generates new data by utilizing learned data.

[0021] In the present disclosure, the sentence generation model generates answer sentences based on specialized knowledge about the product being interviewed and interview knowledge about interview skills.

[0022] In this way, the sentence generation model can reproduce an ideal interviewer by generating sentences based on specialized knowledge and interview knowledge.

[0023] Then, the information processing device 1 acquires feedback on the product from the user U through the interview (step S3), and generates an analysis report based on the feedback and provides it to the company (step S4).

[0024] In this way, the information processing device 1 can automate a series of processes such as selecting interviewees, conducting interviews, and generating analysis reports.

[0025] Next, an overview of an interview according to the embodiment will be described with reference to Fig. 2. Fig. 2 is an explanatory diagram of an overview of an interview. Fig. 2 shows recorded data that is recorded in the information processing device 1 during the interview.

[0026] As shown in Fig. 2, first areas A1 to A5 are displayed in the recorded data. The first area A1 displays an image of the interview. In the present disclosure, the first area A1 displays an AI avatar generated by an image generation AI.

[0027] The AI ​​avatar is an avatar that learns the characteristics of a person from video footage of the actual person, and realistically reproduces the facial expressions and movements of the actual person. The AI ​​avatar displayed in the first area A1 realistically reproduces the mouth movements in response to the voice spoken.

[0028] In other words, in the present disclosure, by conducting an interview with user U through an AI avatar, it is possible to provide user U with the experience of being interviewed by a real interviewer. Note that the AI ​​avatar is not limited to the above example, and may be any video or image.

[0029] The second area A2 is an area where recorded data of the interviewee T that was recorded during the interview is displayed. The third area A3 is an area where the current utterance content of the interviewee T is displayed as text.

[0030] The fourth display area A4 is an area where attribute information of the interviewee T is displayed. In the example of FIG. 2, the attribute information includes age, place of residence, place of employment, weekend activities, and first impressions of using the product.

[0031] The attribute information displayed in the fourth display area A4 may be information collected before the interview, or may be information obtained from the interviewee T at the beginning of the interview.

[0032] The fifth display area A5 displays a transcript of the interview content. In the example shown in Figure 2, the fifth display area A5 displays the conversation between the interviewer and interviewee T in a chat format.

[0033] In this way, the information processing device 1 according to the embodiment replaces the interview conducted by an interviewer with a generative AI. As a result, the information processing device 1 according to the embodiment does not need to coordinate a schedule with the interviewer, and the interview can be conducted at a date and time that is convenient for the interviewee T.

[0034] Furthermore, the sentence generation model according to the embodiment generates answers based on specialized knowledge about the product that is the subject of the interview and interview knowledge about interview skills.

[0035] As a result, the information processing device 1 according to the embodiment can conduct high-quality interviews with high reproducibility. That is, the information processing device 1 according to the embodiment can efficiently conduct interview surveys.

[0036] [Configuration example of information processing device] Next, an example of the configuration of an information processing device 1 according to an embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram of the information processing device 1. The information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. Note that these units may be distributed and held by multiple devices. The processing of these units will be described below.

[0037] The communication unit 2 is realized by a NIC (Network Interface Card) or the like, and enables communication between the control unit 4 and an external device via a telecommunication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 2 enables communication between the user terminal 100 and the control unit 4.

[0038] The storage unit 3 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in Fig. 3, the storage unit 3 has a user information storage unit 31, a sentence generation model storage unit 32, an image generation model storage unit 33, and an interview information storage unit 34.

[0039] The user information storage unit 31 stores user information. The user information is information about a user U who is to be interviewed. FIG. 4 is a diagram showing an example of information stored in the user information storage unit 31.

[0040] 4, the user information storage unit 31 stores information such as "user ID," "account information," "log information," and "bank account information" in association with each other. The "user ID" item stores an identifier for identifying each user U.

[0041] The information processing device 1 may cooperate with services provided by various companies and identify the user U by a common user ID for the services provided by the companies. The services include various services such as e-commerce-related services such as shopping sites, auction sites, and flea market sites, finance-related services such as electronic money payments, credit cards, securities, and FX, messengers, search sites, news sites, and video sites.

[0042] The "account information" item stores account information of a user U identified by a corresponding user ID. The account information includes information about the user U's demographic attributes such as name, age, and occupation, and psychographic attributes such as hobbies and preferences.

[0043] The "log information" item stores log information of a user U identified by a corresponding user ID. The log information is information about the user U's usage history in each linked service.

[0044] The "account information" item stores the account information of the user U identified by the corresponding user ID. The account information is the account number of the account to which the fee will be paid if the corresponding user U is interviewed.

[0045] In the present disclosure, the account information is the account number of an electronic money account, and the reward is paid in electronic money. The account information may be a bank account or may include, for example, a virtual currency wallet. In this case, the reward may be paid in a currency corresponding to the type of account.

[0046] Returning to the explanation of Figure 3, the sentence generation model storage unit 32 will now be described. The sentence generation model storage unit 32 stores a sentence generation model. A sentence generation model is a model that generates an answer to an input sentence. A sentence generation model is a large-scale machine learning model built mainly by deep learning, and is a generative AI that generates new data by utilizing learned data.

[0047] In the present disclosure, the sentence generation model engages in dialogue with the user U based on specialized knowledge about the product being interviewed and skill knowledge about interview skills. The specialized knowledge includes knowledge about the product's specialized field, knowledge about the product's background, the current status of the product, etc., and the skill knowledge about interview skills includes psychology that draws out deep psychology, etc.

[0048] The image generation model storage unit 33 stores an image generation model. The image generation model is an AI that creates videos of AI avatars. For example, in the learning stage, the image generation model can learn using videos of a specific person as learning data, and generate an AI avatar of the specific person as a moving image.

[0049] Furthermore, when an image generation model is trained using a video of a specific person as training data during the learning stage, it can generate audio that reproduces the voice of that specific person. In other words, the image generation model can reproduce the video and voice of the specific person used for training. Note that the model that generates the video of the AI ​​avatar and the model that generates the voice of the AI ​​avatar may be composed of separate models.

[0050] The interview information storage unit 34 stores interview information. The interview information stores information about interviews conducted with the user U. FIG. 5 is a diagram showing an example of information stored in the interview information storage unit 34.

[0051] 5, the interview information storage unit 34 stores information items such as "date and time," "user ID," and "video data" in association with each other. The "date and time" item stores information about the date and time when the user was interviewed.

[0052] The "User ID" field stores the identifier of the user U who participated in the interview. In the example of Figure 5, the "User" field stores the user ID. The "Video data" field stores the video data recorded when the interview with the user U was conducted.

[0053] Returning to the explanation of Fig. 3, the control unit 4 will be described. The control unit 4 is realized using a CPU (Central Processing Unit), NP (Network Processor), FPGA (Field Programmable Gate Array), etc., and executes processing programs stored in memory. As shown in Fig. 3, the control unit 4 has a setting unit 41, a receiving unit 42, a text generation unit 43, an output unit 44, and a report generation unit 45. Each unit of the control unit 4 will be described below.

[0054] The setting unit 41 performs various settings related to the interview. For example, when the setting unit 41 receives a request for an interview from a company employee, it performs settings related to the interview according to the content of the request. For example, the setting unit 41 receives the interview request through a predetermined client platform. The client platform also serves as a platform for providing reports, which will be described later with reference to FIG. 8.

[0055] For example, through the requester platform, companies can specify items such as the product to be interviewed, the interview topics, the user attributes to be interviewed, the number of interviews to be conducted, the interview deadline, the fee and total fee to be paid to the interviewee, etc.

[0056] Based on this information, the setting unit 41 sets up recruitment of users U to be interviewees through the recruiter platform. For example, the setting unit 41 recruits users U with user attributes desired by a company representative through the recruiter platform. Note that the setting unit 41 may recruit users U for interviews with the user attributes desired by the company through targeted advertising, or may recruit users U for interviews through individual direct marketing.

[0057] The reception unit 42 receives applications from users to participate in interviews via a predetermined platform. For example, the reception unit 42 receives applications from users U to participate in interviews via a recruiter platform.

[0058] When accepting an application, the accepting unit 42 accepts, for example, the setting of an interview date and time. As described above, the interview is conducted using generative AI and does not require human intervention such as an interviewer. Therefore, the user U can specify the date and time of his or her choice as the interview date and time. In other words, the user U can be interviewed at the same time as applying for the interview.

[0059] For example, when the reception unit 42 receives the setting of the interview date and time, it issues, for example, an invitation code for the user U to participate in the interview and transmits it to the user terminal 100 of the user U via the communication unit 2.

[0060] The interview with user U will then begin when user U joins the interview using the invitation code at the date and time specified by the user. For example, if the interview requires a total of one hour, the interview may be conducted in multiple sessions. In other words, user U can interrupt the interview midway and then resume it at a convenient time.

[0061] The sentence generation unit 43 uses an answer generation model that generates answers to input sentences, and generates answer documents to the content of the user's utterance and question sentences that ask the user about predetermined interview items.

[0062] Before the interview begins, the sentence generation unit 43 inputs a prompt regarding the setting of interview items to the sentence generation model, thereby setting the sentence generation model to conduct an interview with the user U based on the interview items.

[0063] At this time, the sentence generation unit 43 may extract information about the user U to be interviewed from the user information storage unit 31 and input it to the sentence generation model. That is, the sentence generation unit 43 may cause the sentence generation model to learn in advance the account information and log information of the user U to be interviewed.

[0064] Thereafter, when the interview begins, the sentence generation unit 43 converts the speech uttered by the user U into sentences using a voice recognition engine. The sentence generation unit 43 inputs the converted sentences into a sentence generation model, and passes the sentences output from the sentence generation model to the output unit 44. During this series of processes, the sentence generation unit 43 generates answer documents to the content of the user's utterance and question sentences that ask the user about predetermined interview items.

[0065] The output unit 44 outputs to the user the answer sentence and the question sentence generated by the sentence generation unit 43. The output unit 44 outputs the question sentence and the answer sentence by voice through an AI avatar that serves as the interviewer.

[0066] The output unit 44 inputs the answer sentence and question sentence generated by the sentence generation unit 43 into the image generation model stored in the image generation model storage unit 33, and generates moving images and sounds of the AI ​​avatar.

[0067] The output unit 44 then transmits information about the moving images and audio of the AI ​​avatar to the user terminal 100 of the user U via the communication unit 2. The processing by the sentence generation unit 43 and the output unit 44 is repeated until the interview ends.

[0068] The report generation unit 45 generates a report that compiles the results of the interview. First, the report generation unit 45 starts recording the interview when the interview starts, and stops recording when the interview ends.

[0069] Thereafter, the report generating unit 45 generates a report based on the video recording data. For example, the report generating unit 45 calculates a user evaluation of the interviewee based on the results of the interview.

[0070] For example, the report generation unit 45 classifies each user U into a critic, a neutral, or a promoter of the product, and calculates a user evaluation by calculating an NPS (Net Promoter Score), which is an index representing customer satisfaction.

[0071] Then, the report generation unit 45 generates a report including the user evaluation and the transition of the user evaluation. Note that, when the report generation unit 45 calculates the user evaluation, for example, the sentence generation unit 43 may ask the user U a question that enables the calculation of the user evaluation. That is, in this case, the sentence generation unit 43 may generate a question sentence that makes it easy to calculate the user evaluation in addition to the question sentence related to the interview item specified by the company person in charge. Also, the question sentence that makes it easy to calculate the user evaluation may be set in advance as a default.

[0072] The report generation unit 45 also generates a persona and a customer journey for the interviewee. For example, in this case, the report generation unit 45 inputs, to the sentence generation model, instruction prompts for generating a persona and a customer journey from the text transcribed from the interview conducted with each user U and the user information of the user U. The output results output from the sentence generation model are the persona and the customer journey. The report generation unit 45 then generates a report including the persona and the customer journey.

[0073] The report generation unit 45 may generate a report using AI that estimates the emotions of the user U from the facial expressions of the user U during the interview. For example, in this case, the report generation unit 45 estimates the emotions of the user U for each interview item and calculates a user rating using the emotions as variables. The report generation unit 45 calculates a low user rating when the emotion of the user U is close to anger, and calculates a high user rating when the emotion of the user U is close to joy.

[0074] An example of a report generated by the report generating unit 45 will now be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of a report generated by the report generating unit 45.

[0075] As shown in FIG. 6, the report has a menu area Am, a counting period area A10, a score area A11, a score distribution area A12, a score transition area A13, an interview area A20, and a budget area A30.

[0076] The menu area Am displays a report menu. In the example shown in Figure 6, the menu includes items such as "Dashboard," "User Research Overview," "Hearing Items," "Moderator AI Settings," "Screening," "User Interview Records," "Persona Creation," and "Customer Journey Creation."

[0077] When "Dashboard" is selected, the dashboard screen shown in Figure 6 is displayed. When "User Research Overview" is selected, the user research overview screen is displayed, and when "Hearing Items" is selected, the hearing items screen is displayed.

[0078] The company's personnel can set various interview-related settings from the "User Research Overview" and "Interview Items." Note that the interview items here may be replaced with the interview items listed above.

[0079] When "Moderator AI Settings" is selected, the Moderator AI Settings screen will be displayed. For example, a company representative can use the Moderator AI Settings to set up the AI ​​avatar that will act as the interviewer.

[0080] When "Screening" is selected, a screening screen is displayed. For example, on the screening screen, a company representative can select desired conditions from the results of each interview and perform screening of the interview results.

[0081] When "User Interview Record" is selected, the User Interview Record screen is displayed. The company representative can view the User Interview Record screen from the User Interview Record screen.

[0082] When "Create Persona" is selected, a screen for creating a persona is displayed. For example, the screen for creating a persona displays information about the persona generated by the report generation unit 45. When "Create Customer Journey" is selected, a screen for creating a customer journey is displayed.

[0083] The customer journey creation screen displays information about the customer journey generated by the report generation unit 45.

[0084] Furthermore, information about the aggregation period for which the report is to be generated is displayed in the aggregation period area A10 in Fig. 6. For example, a company employee can specify a desired aggregation period by manipulating the aggregation period displayed in the aggregation period area A10.

[0085] The score area A11 displays the current score for the product. For example, the current score is the current user evaluation of the product. The score area A11 also displays a graph showing the score, the score of the benchmark product, and data such as the deviation from the benchmark. Note that the benchmark may be set by a company representative, for example, to represent rivals of their own company's product.

[0086] A graph showing the distribution of scores is displayed in the score distribution area A12. A bar graph showing the distribution of evaluations of the product by each user U is displayed in the score distribution area A12.

[0087] The score transition area A13 displays the score transition as a line graph. As shown in Fig. 6, the score transition area A13 also displays the benchmark transition.

[0088] The interview area A20 displays the interview record of user U. As shown in Fig. 6, the interview area A20 displays the start date and time, thumbnail image, overall rating, status, attribute / setting changes, transcript (highlights), and highlights.

[0089] The start date and time indicates the start date and time of the interview, and the thumbnail image indicates a thumbnail image of the interview. As shown in Figure 6, a play button is displayed on the thumbnail image, and when the company representative presses the play button, the video of the interview corresponding to the thumbnail image is played.

[0090] The status indicates the current state of the interview. In the example of FIG. 6, three status patterns are shown: interviewing, analyzing, and completed. Interviewing indicates that the interview is currently being conducted, and analyzing indicates that the report generation unit 45 is analyzing the interview. Completed indicates that the analysis of the interview by the report generation unit 45 has been completed.

[0091] Among the attributes and setting changes, the attributes indicate the attributes of user U, and the setting change indicates changing the user attributes displayed on the screen. In other words, company personnel can change the attributes displayed on the screen by changing the settings.

[0092] The transcript (highlights) shows highlights (summaries) of statements made by the interviewed user U. The report generation unit 45 causes the sentence generation model to summarize the content of the utterances made during the interview and displays the summary in the transcript (highlights).

[0093] Highlights shows highlight videos of the transcripts (highlights). A play button is displayed on the highlights, and company representatives can view interview videos related to the transcripts (highlights) by selecting the play button for the highlights.

[0094] The budget area A30 displays the budget for the interviews. In the example of Figure 6, there are items such as this month's expenditure and remaining budget, and this month's expenditure displays the number of interviews conducted this month and the budget consumed this month, and the remaining budget displays the remaining budget for the interviews.

[0095] The report generation unit 45 generates such a report and provides it to the person in charge at the company. The report generation unit 45 then updates the report in real time as new interviews are conducted.

[0096] This allows the company's personnel to check user evaluations of the product in real time, which means that the report generation unit 45 can reduce the time lag that occurs between conducting an interview and providing a report.

[0097] Next, a processing procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 7 and Fig. 8. Fig. 7 is a flowchart showing the processing procedure of the setting process according to the embodiment.

[0098] A series of processes up to the start of an interview will be described with reference to Fig. 7. As shown in Fig. 7, first, the information processing device 1 receives an interview request from a company person in charge (step S101).

[0099] Next, the information processing device 1 sets interview items to be conducted using a sentence generation model (step S102). Next, the information processing device 1 accepts an applicant for the interview (step S103). Thereafter, the information processing device 1 sets the applicant and the date and time of the interview (step S104), and ends the process.

[0100] Next, a series of processes from the start to the end of an interview will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of an interview process according to an embodiment. As shown in Fig. 8, the information processing device 1 generates a sentence using a sentence generation model (step S111).

[0101] Next, the information processing device 1 outputs the generated sentence by voice through the AI ​​avatar (step S112). Next, the information processing device 1 accepts an utterance from the user U (step S113).

[0102] Next, the information processing device 1 determines whether the interview has ended (step S114). If the information processing device 1 determines that the interview has ended (step S114: Yes), it proceeds to the processing of step S115, and if the information processing device 1 determines that the interview is still ongoing (step S114: No), it returns to the processing of step S111.

[0103] After the interview is completed, the information processing device 1 generates a report (step S115) and ends the process. Note that the report may be generated in parallel with the interview.

[0104] [Modification] In the above embodiment, a case has been described in which a depth interview is conducted with the user U through the information processing device 1, but the present invention can also be used for purposes other than depth interviews.

[0105] Specifically, the present invention can also be applied to telephone work such as telephone operators, customer support, and technical support, which accept various inquiries from users U. In other words, interview knowledge related to interview skills includes skills for smoothly conducting interviews such as telephone operators, customer support, and technical support.

[0106] [Hardware configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 1 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0107] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0108] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0109] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 9, the output devices and input devices are collectively referred to as "input / output devices") via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0110] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0111] For example, when the computer 1000 functions as the information processing device 1 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0112] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0113] 〔others〕 Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0114] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0115] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0116] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an information acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0117] 1. Information processing equipment 2. Communications Department 3 Storage section 4. Control section 31 User information storage unit 32 Sentence generation model memory 33 Image generation model memory unit 34 Interview information storage section 41 Setting section 42 Reception Department 43 Sentence generation section 44 Output section 45 Report Generation Unit 100 user terminals

Claims

1. a sentence generation unit that uses a sentence generation model that generates answers to input sentences based on specialized knowledge about the interview subject and interview knowledge about interview skills, and generates answer sentences to the content of the user's utterance and question sentences that ask the user questions about predetermined interview items; an output unit that outputs the answer sentence generated by the sentence generation unit and the question sentence to the user; An information processing device comprising:

2. The output unit The question sentence and the answer sentence are output by voice through an AI (Artificial Intelligence) avatar that acts as an interviewer.

2. The information processing device according to claim 1,

3. A reception department that accepts applications from users to participate in interviews through a designated platform.

2. The information processing apparatus according to claim 1, further comprising:

4. A report generation section that generates a report summarizing the interview results 2. The information processing apparatus according to claim 1, further comprising:

5. The report generation unit generating the report summarizing the interviews for each of the users; 5. The information processing device according to claim 4,

6. The report generation unit Calculating a user rating for the interviewee based on the results of the interview, and generating the report including a transition of the user rating.

5. The information processing device according to claim 4,

7. The report generation unit generating a persona and a customer journey for the interviewee based on the results of the interview, and generating the report including the persona and the customer journey; 5. The information processing device according to claim 4,

8. 1. A computer-implemented information processing method, comprising: a sentence generation process for generating answer sentences to the content of the user's utterance and question sentences to ask the user about predetermined interview items using a sentence generation model that generates answers to input sentences based on specialized knowledge about the interview subject and interview knowledge about interview skills; an output step of outputting the answer sentence generated by the sentence generation step and the question sentence to the user; An information processing method comprising:

9. a sentence generation procedure for generating answer sentences to the content of the user's utterance and question sentences to ask the user about predetermined interview items using a sentence generation model that generates answers to input sentences based on specialized knowledge about the interview subject and interview knowledge about interview skills; an output step of outputting the answer sentence generated by the sentence generation step and the question sentence to the user; An information processing program characterized by causing a computer to execute the above.

Images