Communication assistance apparatus, communication assistance system, communication assistance method, and recording medium

Abstract

A communication assistance apparatus for assisting in communication that a plurality of participants engage in includes an input unit, a speaker identification unit, an identification unit, a response generation unit, and a control unit. The input unit receives an input of a statement in the communication. The speaker identification unit identifies a participant who has made the statement for which the input is received among the plurality of participants. The identification unit identifies an attribute of the identified participant. The response generation unit generates a response, based on the attribute of the identified participant and content of the statement. The control unit performs control to output the generated response.

Description

[DESCRIPTION][Title of Invention]COMMUNICATION ASSISTANCE APPARATUS, COMMUNICATION ASSISTANCE SYSTEM, COMMUNICATION ASSISTANCE METHOD, AND RECORDING MEDIUM [Technical Field]

[0001] The present disclosure relates to a communication assistance apparatus, a communication assistance system, a communication assistance method, and a recording medium. [Background Art]

[0002] In a dialogue system, a dialogue agent automatically responds to an utterance made by a user. Further, a technique has been developed for generating training data based on an environment for recording speech produced by a user to improve speech recognition accuracy (see, for example, Patent Literature (PTL) 1).[Citation List][Patent Literature]

[0003] [PTL 1]Japanese Unexamined Patent Application Publication No. 2022-108803 [Summary of Invention] [Technical Problem]

[0004] In the related art, for example, artificial intelligence (Al) speakers, call centers, or chatbots respond to inquiries without considering the attributes of the utterers of the inquiries. In other words, it is difficult to assist in communication such as a sales meeting, considering attributes such as roles, job titles, standpoints, specific industries or businesses, occupations, and genders of a plurality of participants taking part in the communication.[Solution to Problem]

[0005] According to an embodiment of the present disclosure, a communication assistance apparatus for assisting in communication that a plurality of participants engage in includes an input unit, a speaker identification unit, an identification unit, a response generation unit, and a control unit. The input unit receives an input of a statement in the communication. The speaker identification unit identifies a participant who has made the statement for which the input is received among the plurality of participants. The identification unit identifies an attribute of the identified participant. The response generation unit generates a response, based on the attribute of the identified participant and content of the statement. The control unit performs control to output the generated response.According to an embodiment of the present disclosure, a communication assistance system for assisting in communication that a plurality of participants engage in includes a terminal apparatus and a server apparatus. The server apparatus includes an input unit, a speaker identification unit, an identification unit, a response generation unit, and a control unit. The input unit receives an input of a statement in the communication. The speaker identification unit identifies a participant who has made the statement for which the input is received among the plurality of participants. The identification unit identifies an attribute of the participant identified by the speaker identification unit. The response generation unit generates a response, based on the attribute of the identified participant and content of the statement. The control unit performs control to output the generated response. The terminal apparatus includes a data transmission unit. The data transmission unit transmits a statement made by a participant among the plurality of participants to the server apparatus.According to an embodiment of the present disclosure, a communication assistance method, implemented by a computer, for assisting in communication that a plurality of participants engage in, includes receiving an input of a statement in the communication; identifying a participant who has made the statement for which the input is received among the plurality of participants; identifying an attribute of the identified participant; generating a response, based on the attribute of the identified participant and content of the statement; and performing control to output the generated response.According to an embodiment of the present disclosure, a recording medium stores a program for causing a computer system to execute the above-described communication assistance method.[Advantageous Effects of Invention]

[0006] According to one or more embodiments, a communication assistance apparatus can assist in communication, considering attributes of a plurality of participants taking part in the communication.[Brief Description of Drawings]

[0007] A more complete appreciation of embodiments of the present disclosure and many of the attendant advantages and features thereof can be readily obtained and understood from the following detailed description with reference to the accompanying drawings.[FIG. 1]FIG. 1 is a diagram illustrating an example system configuration of a communication assistance system according to one or more embodiments.[FIG. 2]FIG. 2 is a diagram illustrating an example hardware configuration of a computer according to the one or more embodiments.[FIG. 3]FIG. 3 is a diagram illustrating an example hardware configuration of a terminal apparatus according to the one or more embodiments.[FIG. 4]FIG. 4 is a diagram illustrating an example functional configuration of a communication assistance system according to a first embodiment.[FIG. 5]FIG. 5 is a flowchart illustrating an example of an assistance process according to the first embodiment.[FIG. 6]FIG. 6 is a flowchart illustrating an example of a process for responding to a customer according to the first embodiment.[FIG. 7]FIG. 7 is a diagram illustrating an image of how a product is explained according to the first embodiment.[FIG. 8]FIG. 8 is a flowchart illustrating an example of a process for responding to a salesperson according to the first embodiment.[FIG. 9]FIG. 9 is a flowchart illustrating an example of a process for responding to an inquiry according to the first embodiment.[FIG. 10]FIG. 10 is a diagram illustrating an image of how a sales meeting takes place according to a second embodiment.[FIG. 11]FIG. 11 is a flowchart illustrating an example of an assistance process according to the second embodiment.[FIG. 12]FIG. 12 is a flowchart illustrating an example of a process for responding to an utterance according to the second embodiment.[FIG. 13]FIG. 13 is a diagram illustrating an example of a screen displayed on a terminal apparatus according to the second embodiment.[FIG. 14]FIG. 14 is a flowchart illustrating an example of an assistance process according to a third embodiment.[FIG. 15]FIG. 15 is a flowchart illustrating an example of an assistance process according to a fourth embodiment.[FIG. 16]FIG. 16 is a diagram illustrating an example functional configuration of a communication assistance system according to a fifth embodiment.[FIG. 17]FIG. 17 is a flowchart illustrating an example of a feedback collection process according to the fifth embodiment.[FIG. 18]FIG. 18 is a diagram illustrating an example of a database according to the fifth embodiment. [FIG. 19]FIG. 19 is a flowchart illustrating an example of a content determination process according to the fifth embodiment.[FIG. 20]FIG. 20 is a diagram illustrating an example functional configuration of a communication assistance system according to a sixth embodiment.[FIG. 21]FIG. 21 is a flowchart illustrating an example of an assistance process according to the sixth embodiment.The accompanying drawings are intended to depict embodiments of the present disclosure and should not be interpreted to limit the scope thereof. The accompanying drawings are not to be considered as drawn to scale unless explicitly noted. Also, identical or similar reference numerals designate identical or similar components throughout the several views. [Description of Embodiments]

[0008] In describing embodiments illustrated in the drawings, specific terminology is employed for the sake of clarity. However, the disclosure of this specification is not intended to be limited to the specific terminology so selected and it is to be understood that each specific element includes all technical equivalents that have a similar function, operate in a similar manner, and achieve a similar result.Referring now to the drawings, embodiments of the present disclosure are described below.As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.Some embodiments will be described in detail hereinafter with reference to the drawings.

[0009] System ConfigurationFIG. 1 is a diagram illustrating an example system configuration of a communication assistance system according to an embodiment. In the example illustrated in FIG. 1, a communication assistance system 1 includes a communication assistance apparatus 10 and a terminal apparatus 100. The communication assistance apparatus 10 and the terminal apparatus 100 are connected to a communication network N such as the Internet or a local area network (LAN). As an example of a use scenario, a salesperson 2 brings the terminalapparatus 100 to a sales meeting with a customer 3 to display a virtual sales agent 101, and engages in the sales meeting together with the virtual sales agent 101. The sales meeting is an example of communication. The salesperson 2 is an example of a host taking part in the communication, and the customer 3 is an example of a guest taking part in the communication. The virtual sales agent 101 is an example of a dialogue agent.

[0010] The terminal apparatus 100 is an information terminal such as a personal computer (PC), a tablet terminal, or a smartphone used by the salesperson 2. The terminal apparatus 100 acquires spoken utterances from the salesperson 2 and the customer 3, which are participants taking part in the sales meeting, and transmits the acquired spoken utterances (audio data) to the communication assistance apparatus 10. The spoken utterances are an example of statements in communication. The statements in the communication include, for example, but not limited to, chat statements based on text data. The following description will be given assuming that the statements in the communication are utterances.

[0011] The communication assistance apparatus (server apparatus) 10 is, for example, an information processing apparatus having the configuration of a computer, or a system including a plurality of computers. The communication assistance apparatus 10 acquires the spoken utterances transmitted from the terminal apparatus 100, analyzes the acquired spoken utterances, and generates a response for proposing recommendation information tailored to the needs of the customer 3. The response includes, for example, verbal information and non-verbal information of the virtual sales agent 101, the recommendation information, and the description of the recommendation information.

[0012] Further, the communication assistance apparatus 10 controls the virtual sales agent 101 displayed on the terminal apparatus 100 in accordance with the response. For example, the communication assistance apparatus 10 controls an utterance to be made by the virtual sales agent 101, based on the verbal information of the virtual sales agent 101. The communication assistance apparatus 10 further controls the display of the virtual sales agent 101, the output of a paralanguage, and so on, based on the non-verbal information of the virtual sales agent 101. The non-verbal information includes one or more of a facial expression, a direction of gaze, a body posture, an emotion, a gesture, and a paralanguage of the virtual sales agent 101. The paralanguage includes non-linguistic sound information such as tone of voice, speech rate, pitch of voice, intensity of voice, coughing, sighing, laughter, or silence.

[0013] The terminal apparatus 100 displays the virtual sales agent 101, which is controlled by the communication assistance apparatus 10, and also outputs an utterance and a paralanguage from the virtual sales agent 101. Accordingly, the virtual sales agent 101 can proposerecommendation information tailored to the needs of the customer 3 to the customer 3 and the salesperson 2 or the like in accordance with the flow of the sales meeting.

[0014] In a specific example, the needs of the customer 3 are determined to be for "electronic invoicing". In this case, the virtual sales agent 101 suggests, "For electronic invoicing, how about Product A?" and proposes a product related to an electronic invoice issuing system. In another example, the virtual sales agent 101 may explain the product by giving a reason for the proposal, such as "Product A has been the best-selling product for manufacturing companies in this prefecture this year", or provide comparisons with other products.

[0015] Preferably, the communication assistance apparatus 10 generates a different response for each utterer according to the acquired spoken utterance. For example, when the utterer is the salesperson 2, the virtual sales agent 101 displays a material for the product to be proposed to the customer 3 on the terminal apparatus 100 and waits for instructions from the salesperson 2. Accordingly, the salesperson 2 can explain the product based on the material displayed by the virtual sales agent 101, or can have the virtual sales agent 101 explain the product. In contrast, when the utterer is the customer 3, the virtual sales agent 101 makes a gesture such as raising a hand to indicate the presence of a product that can be proposed. Accordingly, the salesperson 2 can have the virtual sales agent 101 propose the product when a proposal by the virtual sales agent 101 is desired, and can stop the virtual sales agent 101 from proposing the product when a proposal by the virtual sales agent 101 is not desired.

[0016] As described above, the communication assistance system 1 according to the present embodiment easily assists in communication, considering the attributes of a plurality of participants taking part in the communication, by using a dialogue system such as the virtual sales agent 101. Communication is a means of exchanging information, intentions, emotions, and so on between individuals or groups. Such a means includes verbal information using words and non-verbal information such as gestures, facial expressions, and body language.

[0017] The sales meeting is an example of communication. The communication assistance system 1 may assist in other types of communication such as conferences, interviews, lectures, lessons, medical care, nursing care, or counseling. The virtual sales agent 101 and the dialogue agent are examples of a dialogue system.

[0018] Hardware ConfigurationHardware Configuration of ComputerThe communication assistance apparatus 10 has the hardware configuration of a computer 200 as illustrated in FIG. 2. Alternatively, the communication assistance apparatus 10includes a plurality of computers 200. The terminal apparatus 100 may have the hardware configuration of the computer 200 as illustrated in FIG. 2.FIG. 2 is a diagram illustrating an example hardware configuration of the computer 200. As illustrated in FIG. 2, the computer 200 includes, for example, a central processing unit (CPU) 201, a read only memory (ROM) 202, a random access memory (RAM) 203, a hard disk (HD) 204, a hard disk drive (HDD) controller 205, a display 206, an external device connection interface (I / F) 207, a network I / F 208, a keyboard 209, a pointing device 210, a digital versatile disk rewritable (DVD-RW) drive 212, a media I / F 214, and a bus line 215.

[0019] In a case where the computer 200 operates as the terminal apparatus 100, the computer 200 further includes, for example, a microphone 221, a speaker 222, an audio input / output I / F 223, a complementary metal oxide semiconductor (CMOS) sensor 224, an imaging element VF 225.

[0020] The CPU 201 controls the overall operation of the computer 200. The ROM 202 stores a program such as an initial program loader (IPL) used to boot the computer 200. The RAM 203 is used as, for example, a work area for the CPU 201. The HD 204 stores, for example, an operating system (OS), applications, device driver programs, and various types of data. The HDD controller 205 controls reading and writing of various data from and to the HD 204 under control of the CPU 201. The HD 204 and the HDD controller 205 are examples of a storage device.

[0021] The display 206 displays various types of information such as a cursor, a menu, a window, characters, and an image. The display 206 may be provided external to the computer 200. The external device connection I / F 207 is an interface for connecting various external devices to the computer 200. The network I / F 208 is an interface for connecting the computer 200 to the communication network N to communicate with other devices.

[0022] The keyboard 209 is one example of an input device provided with a plurality of keys for allowing a user to input characters, numerals, or various instructions. The pointing device 210 is another example of the input device, which allows the user to select or execute a specific instruction, select a target for processing, or move a cursor being displayed. The keyboard 209 and the pointing device 210 may be provided external to the computer 200.

[0023] The DVD-RW drive 212 controls reading and writing of various data from and to a DVD-RW 211, which is an example of a removable recording medium. The DVD-RW 211 may be any other removable recording medium, instead of a DVD-RW. The media I / F 214 controls reading and writing (storing) of data from and to media 213 such as a flash memory. The busline 215 includes an address bus, a data bus, various control signal lines, and the like for electrically connecting the components described above to one another.

[0024] The microphone 221 is a built-in circuit that converts sound into an electrical signal. The speaker 222 is a built-in circuit that generates sound such as music or voice by converting an electrical signal into physical vibration. The audio input / output PF 223 is a circuit that handles the input and output of audio signals between the microphone 221 and the speaker 222 under control of the CPU 201.

[0025] The CMOS sensor 224 is an example of a built-in imaging device that captures an image of an object (e.g., an image of the user) under control of the CPU 201 to obtain image data. The computer 200 may include any other imaging device such as a charge coupled device (CCD) sensor instead of the CMOS sensor 224. The imaging element I / F 225 is a circuit that controls driving of the CMOS sensor 224.

[0026] Example Hardware Configuration of Terminal ApparatusFIG. 3 is a diagram illustrating an example hardware configuration of a terminal apparatus according to one embodiment. In the illustrated example hardware configuration of the terminal apparatus 100, the terminal apparatus 100 is an information terminal such as a smartphone or a tablet terminal.

[0027] In the example illustrated in FIG. 3, the terminal apparatus 100 includes a CPU 301, a ROM 302, a RAM 303, a storage device 304, a CMOS sensor 305, an imaging element PF 306, an acceleration and orientation sensor 307, a media PF 309, and a Global Positioning System (GPS) receiver 310.

[0028] The CPU 301 executes a predetermined program to control the overall operation of the terminal apparatus 100. The ROM 302 stores a program such as an IPL used to boot the CPU 301. The RAM 303 is used as a work area for the CPU 301. The storage device 304 is a large- capacity storage device that stores programs such as an OS and applications, as well as various data. The storage device 304 is implemented by, for example, a solid state drive (SSD) or a flash ROM.

[0029] The CMOS sensor 305 is an example of a built-in imaging device that captures an image of an object (e.g., an image of the user) under control of the CPU 301 to obtain image data. The terminal apparatus 100 may include any other imaging device such as a CCD sensor instead of the CMOS sensor 305. The imaging element I / F 306 is a circuit that controls driving of the CMOS sensor 305. The acceleration and orientation sensor 307 is any sensor for detecting geomagnetism, such as, but not limited to, an electromagnetic compass, a gyrocompass, or anacceleration sensor. The media I / F 309 controls reading and writing (storing) of data from and to media (storage media) 308 such as a flash memory. The GPS receiver 310 receives a GPS signal (positioning signal) from a GPS satellite.

[0030] The terminal apparatus 100 further includes a long-range communication circuit 311, an antenna 311a for the long-range communication circuit 311, a CMOS sensor 312, an imaging element I / F 313, a microphone 314, a speaker 315, an audio input / output I / F 316, a display 317, an external device connection I / F 318, a short-range communication circuit 319, an antenna 319a for the short-range communication circuit 319, and a touch panel 320.

[0031] The long-range communication circuit 311 is a circuit that communicates with other devices via, for example, the communication network N. The CMOS sensor 312 is an example of a built-in imaging device that captures an image of an object under control of the CPU 301 to obtain image data. The imaging element I / F 313 is a circuit that controls driving of the CMOS sensor 312. The microphone 314 is a built-in circuit that converts sound into an electrical signal. The speaker 315 is a built-in circuit that generates sound such as music or voice by converting an electrical signal into physical vibration. The audio input / output I / F 316 is a circuit that handles the input and output of audio signals between the microphone 314 and the speaker 315 under control of the CPU 301.

[0032] The display 317 is an example of a display device such as a liquid crystal display (LCD) or an organic electroluminescent (EL) display that displays, for example, an image of an object or various icons. The external device connection I / F 318 is an interface for connecting various external devices to the terminal apparatus 100. The short-range communication circuit 319 includes a circuit for performing short-range wireless communication. The touch panel 320 is an example of an input device provided on the display 317, which allows the user to operate the terminal apparatus 100 by touching the screen of the touch panel 320.

[0033] The terminal apparatus 100 further includes a bus line 321. The bus line 321 includes an address bus, a data bus, various control signal lines, the like for electrically connecting the components illustrated in FIG. 3, such as the CPU 301, to one another.

[0034] The hardware configuration of the terminal apparatus 100 illustrated in FIG. 3 is an example. The terminal apparatus 100 may have any other hardware configuration including, for example, the configuration of a computer, a communication circuit, a display, a microphone, and a speaker.

[0035] Functional ConfigurationFIG. 4 is a diagram illustrating an example functional configuration of the communication assistance system 1 according to one embodiment.

[0036] Functional Configuration of Terminal ApparatusThe terminal apparatus 100 implements, for example, functional components as illustrated in FIG. 4 by, for example, the CPU 301 (or the CPU 201) included in the terminal apparatus 100 executing a predetermined program. In the example illustrated in FIG. 4, the terminal apparatus 100 includes a data transmission unit 421, a display unit 422, a speech output unit 423, and an operation receiving unit 424.

[0037] The data transmission unit 421 executes a data transmission process for acquiring a spoken utterance from a participant taking part in communication and transmitting the acquired spoken utterance (audio data) to the communication assistance apparatus 10. In the example illustrated in FIG. 1, the data transmission unit 421 acquires spoken utterances from the salesperson 2 and the customer 3 taking part in the sales meeting, and transmits the acquired spoken utterances to the communication assistance apparatus 10. The data transmission unit 421 also transmits operation data and any other data received by the operation receiving unit 424 to the communication assistance apparatus 10. The spoken utterance from the participant is an example of a statement made by the participant.

[0038] The display unit 422 executes a display process for displaying video of the dialogue agent, a proposal material, and any other content received from the communication assistance apparatus 10. For example, the display unit 422 displays video of the virtual sales agent 101 as illustrated in FIG. 1, recommendation information to be proposed to the customer 3, and any other content on the terminal apparatus 100.

[0039] The speech output unit 423 executes a speech output process for outputting, for example, an utterance to be spoken by the dialogue agent received from the communication assistance apparatus 10. The operation receiving unit 424 executes an operation reception process for receiving operations for the terminal apparatus 100.

[0040] Functional Configuration of Communication Assistance ApparatusThe communication assistance apparatus 10 implements, for example, the functional configuration as illustrated in FIG. 4 by the computer 200 included in the communication assistance apparatus 10 executing a predetermined program stored in a storage medium. In the example illustrated in FIG. 4, the communication assistance apparatus 10 includes functional components such as an input unit 401, a speech recognition unit 402, a speaker identification unit 403, an identification unit 404, a response unit 405, a speech synthesis unit 410, adrawing unit 411, and an output unit 412. At least some of the functional components described above may be implemented by hardware such as a circuit.

[0041] The communication assistance apparatus 10 further includes a storage unit 413. The storage unit 413 is implemented by storage devices such as the HD 204 and HDD controller 205. The storage unit 413 may be implemented by a storage server provided external to the communication assistance apparatus 10, a cloud service, or the like.

[0042] The input unit 401 executes an input process for receiving an input of a statement in communication. In the example illustrated in FIG. 1, the input unit 401 receives an input of spoken utterances from the salesperson 2 and the customer 3 transmitted from the terminal apparatus 100.

[0043] The speech recognition unit 402 executes a speech recognition process on the spoken utterances received by the input unit 401. For example, the speech recognition unit 402 executes a known speech recognition process on the spoken utterances received by the input unit 401 to convert the acquired spoken utterances into text. In a case where statements in communication input to the input unit 401 are text data, the speech recognition unit 402 of the communication assistance apparatus 10 may be omitted.

[0044] The speaker identification unit 403 executes a speaker identification process for identifying a participant who has made the statement input to the input unit 401 among a plurality of participants. In the example illustrated in FIG. 1, the speaker identification unit 403 may use known speaker recognition technology or the like to identify statements made by the salesperson 2 and identify statements other than the statements made by the salesperson 2 as statements made by the customer 3. In another example, the speaker identification unit 403 may use known speaker recognition technology or the like to identify statements made by the salesperson 2 and a support person, and identify statements other than the statements made by the salesperson 2 and the support person as statements made by the customer 3.

[0045] In a case where a statement in the communication input to the input unit 401 is text data, the speaker identification unit 403 may determine a participant who has made the statement, based on the terminal apparatus from which the text has been input. For example, in a case where text data is input from the terminal apparatus 100 of the salesperson 2, the participant who has made the statement may be determined to be the salesperson 2. In a case where text data is input from another terminal apparatus, the participant who has made the statement may be determined to be the customer 3.

[0046] The identification unit 404 executes, for example, an identification process for identifying the attributes of the participant identified by the speaker identification unit 403. As long as the identification unit 404 can identify the attributes of a participant who has made a statement, it is optional for the speaker identification unit 403 to identify the participant. For example, the identification unit 404 may analyze features of a spoken utterance, the context of the utterance, or the like to identify whether the utterer is the salesperson 2 or the customer 3.

[0047] In another example, the attribute (role) to which the speech of each participant corresponds, such as customer, salesperson, or support person, may be set in the communication assistance apparatus 10 in advance. In this case, the identification unit 404 can identify the attribute from the speech of a participant who has made a statement. In a case where it is difficult to register the speech of the customer in advance, the speech of the salesperson and the support person may be set in the communication assistance apparatus 10, and other speech may be set to correspond to the attribute (role) of the customer. Accordingly, the attribute of a participant who has made a statement may be automatically set.

[0048] In another example, profile information, such as roles, job titles, positions, specific industries, business types, occupations, or genders, of the participants may be registered in the communication assistance apparatus 10 in advance. In this case, the identification unit 404 may identify the attribute of a participant who has made a statement, such as the salesperson 2 or the customer 3, based on the profile information of the speaker identified by the speaker identification unit 403. In a case where it is difficult to register the profile information of the customer in advance, the attribute of a participant who has made a statement may be automatically set as the attribute (role) of the customer if the profile information of the participant who has made the statement has not been registered.

[0049] In another example, the communication assistance apparatus 10 may collect audio data from various utterers in advance and train a machine learning model that analyzes features of the voice, such as tone, intonation, speed, and accent, from the collected audio data, and identifies attributes. The audio data collected in advance includes audio data from utterers with various roles, genders, ages, occupations, and social backgrounds. In this case, when the speech of a participant who has made a statement is input to the trained machine learning model, the identification unit 404 can identify the attribute of the participant who has made the statement.

[0050] In another example, the communication assistance apparatus 10 may collect audio data from various utterers in advance and train a machine learning model that extracts and analyzes language patterns or expressions related to each category from the collected audio data and identifies attributes. In this case, when the speech of a participant who has made a statement isinput to the trained machine learning model, the identification unit 404 can identify the attribute of the participant who has made the statement as salesperson from, for example, specific phrases or technical terms used by salespersons.

[0051] In another example, account information to be used by the participants to log into PCs, smart devices, or the like may be registered in the communication assistance apparatus 10 in advance. In this case, the identification unit 404 can use attribute information associated with the account information of a participant who has made a statement such as an utterance or a chat to identify the attribute of the speaker of the statement.

[0052] The response unit 405 executes a process for responding to a statement input to the input unit 401. The response unit 405 includes, for example, a determination unit 406, an intention interpretation unit 407, a response generation unit 408, and a control unit 409.

[0053] The determination unit 406 executes a determination process for determining recommendation information to be proposed to the guest, based on, for example, a spoken utterance from the host or the guest taking part in the communication. For example, in FIG. 1, the determination unit 406 determines a product or the like to be proposed to the customer 3, based on the spoken utterance from the salesperson 2 or the customer 3, which has been converted into text by the speech recognition unit 402.

[0054] The intention interpretation unit 407 analyzes the spoken utterance converted into text (hereinafter referred to as an "utterance text") by the speech recognition unit 402 by using a natural language processing (NLP) algorithm and extracts, for example, the intention of the utterance, a keyword, and a field of interest.

[0055] The response generation unit 408 executes a generation process for generating a response different for each utterer in accordance with the spoken utterance acquired by the input unit 401. For example, in a case where the spoken utterance acquired by the input unit 401 is a spoken utterance from the salesperson 2, the response generation unit 408 generates a response for the salesperson 2. The generated response includes information such as a verbal response, a non-verbal response, and a proposal material, for example. The verbal response includes an utterance that the salesperson 2 has the virtual sales agent 101 make. The nonverbal response includes, for example, one or more of a facial expression, a direction of gaze, a body posture, an emotion, a gesture, a paralanguage, and the like. The proposal material includes a material for the product to be proposed to the customer 3. Examples of the material include a webpage, image data, document data, and interactive media.

[0056] The generation of the verbal information and the non-verbal information can be performed using, for example, rule-based natural language processing or natural language processing based on a large language model. One example of the large language model may be a text generation language model called Generative Pre-trained Transformer 3 (GPT-3). In the rulebased natural language processing, a response to be made by the virtual sales agent 101 is generated based on rules that specify responses according to the intentions of utterances made by users.

[0057] The proposal material may be a proposal material for the product determined by the determination unit 406 and may be acquired by the response generation unit 408 from a proposal material database prepared in advance. In another example, the response generation unit 408 may collect information on the product determined by the determination unit 406 on the web to create a proposal material. The proposal material may be prepared by the determination unit 406.

[0058] The control unit 409 executes a control process for controlling the dialogue agent in accordance with the response generated by the response generation unit 408. For example, the control unit 409 outputs the verbal response included in the response to the speech synthesis unit 410, outputs the non-verbal response included in the response to the drawing unit 411, and outputs the proposal material to the output unit 412 to generate video of the virtual sales agent 101.

[0059] The speech synthesis unit 410 executes a speech synthesis process for converting the input verbal response into speech by using speech synthesis technology. The drawing unit 411 executes a drawing process for drawing the dialogue agent in accordance with the input nonverbal response. For example, the drawing unit 411 reflects, in the drawing of the virtual sales agent 101, facial expressions, directions of gaze, body postures, emotions, gestures, and paralanguages in accordance with the non-verbal response.

[0060] Preferably, the drawing unit 411 also performs processing such as drawing the virtual sales agent 101 with lip-syncing such that the mouth of the virtual sales agent 101 moves in accordance with an utterance being made by the virtual sales agent 101.

[0061] The output unit 412 executes an output process for outputting video, including the voice of the dialogue agent obtained by the speech synthesis unit 410, the dialogue agent drawn by the drawing unit 411, and the proposal material, to the terminal apparatus 100 or the like. For example, the output unit 412 transmits video of the virtual sales agent 101 to the terminal apparatus 100 via the communication network N.

[0062] The system configuration of the communication assistance system 1 illustrated in FIG. 4 is an example. For example, the communication assistance system 1 may include one terminal apparatus 100 having the functional configuration of the communication assistance apparatus 10 illustrated in FIG. 4. In this case, the terminal apparatus 100 serves as a communication assistance apparatus. At least some of the functional components of the communication assistance apparatus 10 may be included in the terminal apparatus 100. For example, the terminal apparatus 100 may include the speech synthesis unit 410, the drawing unit 411, and the output unit 412.

[0063] Operation FlowNext, the operation flow of the communication assistance method according to the present embodiment will be described with reference to several embodiments as examples.

[0064] First EmbodimentAssistance ProcessFIG. 5 is a flowchart illustrating an example of an assistance process according to a first embodiment. The illustrated process is an example of an assistance process performed by the communication assistance apparatus 10 to assist in communication. The following describes an example of the process when, as illustrated in FIG. 1, the communication assistance apparatus 10 assists in a sales meeting between the salesperson 2 and the customer 3 by using the virtual sales agent 101 displayed on the terminal apparatus 100. For example, the communication assistance apparatus 10 repeatedly executes the process illustrated in FIG. 5 during the sales meeting. The following description will be given assuming that statements in the communication input to the input unit 401 are spoken utterances from the participants in the communication.

[0065] In step S501, the input unit 401 of the communication assistance apparatus 10 acquires a spoken utterance from a participant taking part in the sales meeting. For example, the input unit 401 acquires spoken utterances from the salesperson 2 and the customer 3 transmitted from the terminal apparatus 100.

[0066] In step S502, the communication assistance apparatus 10 performs speech recognition and speaker identification on the spoken utterance acquired by the input unit 401. For example, the speech recognition unit 402 converts the spoken utterance acquired by the input unit 401 into text to create an utterance text. Further, the speaker identification unit 403 identifies a participant who has made the spoken utterance acquired by the input unit 401, and the identification unit 404 identifies whether the participant who has made the spoken utterance is the salesperson 2 or the customer 3.

[0067] In step S503, the response unit 405 of the communication assistance apparatus 10 determines whether an inquiry mode is set. For example, when the utterance text obtained by the speech recognition unit 402 includes a wake word for a transition to the inquiry mode, the response unit 405 determines that the inquiry mode is set. When the utterance text does not include a wake word, the response unit 405 determines that the inquiry mode is not set. If the inquiry mode is set, the response unit 405 causes the process to proceed to step S504. On the other hand, if the inquiry mode is not set, the response unit 405 causes the process to proceed to step S505. The inquiry mode is an example and may be optional.

[0068] When the process proceeds from step S503 to step S504, the response unit 405 executes a process for responding to an inquiry. The details of the process for responding to the inquiry will be described below.

[0069] When the process proceeds from step S503 to step S505, the response unit 405 determines whether the speaker is the customer 3. If the speaker is the customer 3, the response unit 405 causes the process to proceed to step S506. On the other hand, if the speaker is not the customer 3, the response unit 405 causes the process to proceed to step S507.

[0070] When the process proceeds from step S505 to step S506, the response unit 405 executes a process for responding to the customer 3. The details of the process for responding to the customer 3 will be described below.

[0071] When the process proceeds from step S505 to step S507, the response unit 405 determines whether the speaker is the salesperson 2. If the speaker is the salesperson 2, the response unit 405 causes the process to proceed to step S508.

[0072] On the other hand, if the speaker is not the salesperson 2, the response unit 405 ends the process illustrated in FIG. 5. As described above, it is desirable that the communication assistance apparatus 10 can be set such that no consideration is given to a statement made by a speaker when the speaker is neither the salesperson 2 nor the customer 3.

[0073] When the process proceeds from step S507 to step S508, the response unit 405 executes a process for responding to the salesperson 2. The details of the process for responding to the salesperson 2 will be described below.

[0074] Process for Responding to CustomerFIG. 6 is a flowchart illustrating an example of a process for responding to a customer according to the first embodiment. The illustrated process is an example of a process forresponding to the customer 3, which is executed by the communication assistance apparatus 10 in step S506 illustrated in FIG. 5.

[0075] In step S601, the determination unit 406 determines whether the utterance made by the customer 3 includes an issue or a product name. If the utterance made by the customer 3 includes an issue or a product name, the determination unit 406 causes the process to proceed to step S602. On the other hand, if the utterance made by the customer 3 does not include an issue or a product name, the determination unit 406 ends the process illustrated in FIG. 6.

[0076] In step S602, the determination unit 406 determines a product to be proposed to the customer 3, based on the content of the utterance made by the customer 3. For example, in a case where the utterance made by the customer 3 includes an issue, the determination unit 406 determines, from a database or the like prepared in advance, a product for addressing the issue as the product to be proposed to the customer 3. In a case where the utterance made by the customer 3 includes a product name, the determination unit 406 determines that a product with the product name included in the utterance or a product related to the product name included in the utterance is the product to be proposed to the customer 3. Since it is problematic to provide all proposals about competitive products, the determination unit 406 proposes a predetermined product (a desired product for sales) from the database prepared in advance when the determination unit 406 determines the product to be proposed to the customer 3 based on the content of the utterance made by the customer 3.

[0077] In step S603, the response generation unit 408 generates a response to the utterance made by the customer 3. For example, the response generation unit 408 generates a verbal response and a non-verbal response for the virtual sales agent 101 to explain the product determined by the determination unit 406.

[0078] In step S604, the response generation unit 408 searches for or creates a material for the product to be proposed to the customer 3.

[0079] In step S605, the control unit 409 outputs the non-verbal response to the drawing unit 411 to display a sign indicating the presence of a proposal. As a result, the sign is displayed on the terminal apparatus 100.

[0080] The sign may be an action indicating the presence of a proposal, such as raising or waving a hand of the virtual sales agent 101, or may be an utterance such as "I have a proposal". In another example, the sign may be an action not performed by the virtual sales agent 101, such as displaying a proposal material on the terminal apparatus 100.

[0081] In step S606, the control unit 409 determines whether a predetermined operation is received within a predetermined amount of time. For example, when the virtual sales agent 101 provides a sign indicating the presence of a proposal, the salesperson 2 can permit the virtual sales agent 101 to explain the product by performing a predetermined operation such as pressing a button. If the predetermined operation is received within the predetermined amount of time, the control unit 409 causes the process to proceed to step S607. On the other hand, if the predetermined operation is not received within the predetermined amount of time, the control unit 409 ends the process illustrated in FIG. 6.

[0082] In step S607, the response generation unit 408 creates, for example, a tagline summarizing the proposal. This processing is optional.

[0083] In step S608, the control unit 409 causes the terminal apparatus 100 to display the material for the product prepared in step S604, and has the virtual sales agent 101 explain the product using, for example, the response generated in step S603 and the tagline generated in step S607.

[0084] FIG. 7 is a diagram illustrating an image of how a product is explained according to the first embodiment. For example, the communication assistance apparatus 10 determines that the issue faced by the customer 3 is "electronic invoicing", based on an utterance text 701 as illustrated in FIG. 7. In this case, as displayed on a display screen 710, the control unit 409 displays a material 711 for Product A, which is to be proposed to the customer 3, and has the virtual sales agent 101 provide an explanation 712 of Product A. Preferably, the control unit 409 provides an explanation of Product A by giving a reason 721 for the proposal, as displayed on a display screen 720.

[0085] When the salesperson 2 prefers that the virtual sales agent 101 not make a proposal, the salesperson 2 can stop the virtual sales agent 101 from making a proposal by not performing the predetermined operation in step S606 illustrated in FIG. 6.

[0086] Process for Responding to SalespersonFIG. 8 is a flowchart illustrating an example of a process for responding to a salesperson according to the first embodiment. The illustrated process is an example of a process for responding to the salesperson 2, which is executed by the communication assistance apparatus 10 in step S508 illustrated in FIG. 5.

[0087] In step S801, the determination unit 406 determines whether the utterance made by the salesperson 2 includes an issue or a product name. If the utterance made by the salesperson 2 includes an issue or a product name, the determination unit 406 causes the process to proceedto step S802. On the other hand, if the utterance made by the salesperson 2 does not include an issue or a product name, the determination unit 406 ends the process illustrated in FIG. 8.

[0088] In step S802, the determination unit 406 determines a product to be proposed to the customer 3, based on the content of the utterance made by the salesperson 2. For example, in a case where the utterance made by the salesperson 2 includes an issue, the determination unit 406 determines, from a database or the like prepared in advance, a product for addressing the issue as the product to be proposed to the customer 3. In a case where the utterance made by the salesperson 2 includes a product name, the determination unit 406 determines that a product with the product name included in the utterance or a product related to the product name included in the utterance is the product to be proposed to the customer 3.

[0089] In step S8O3, the response generation unit 408 generates a response to the utterance made by the salesperson 2. For example, the response generation unit 408 generates a verbal response and a non-verbal response for the virtual sales agent 101 to explain the product determined by the determination unit 406.

[0090] In step S804, the response generation unit 408 searches for or creates a material for the product to be proposed to the customer 3.

[0091] In step S805, the control unit 409 causes the terminal apparatus 100 to display the material for the product prepared in step S804.

[0092] In step S806, the control unit 409 determines whether the virtual sales agent 101 explains the product. For example, if the salesperson 2 performs a predetermined operation, such as pressing a button or giving a sign by voice, within a predetermined amount of time, the control unit 409 determines that the virtual sales agent 101 explains the product. On the other hand, if the salesperson 2 does not perform the predetermined operation within the predetermined amount of time, the control unit 409 determines that the virtual sales agent 101 does not explain the product.

[0093] If it is determined that the virtual sales agent 101 explains the product, the control unit 409 causes the process to proceed to step S807. On the other hand, if it is determined that the virtual sales agent 101 does not explain the product, the control unit 409 ends the process illustrated in FIG. 8. In this case, the salesperson 2 may explain the product to the customer 3 using the material displayed on the terminal apparatus 100.

[0094] In step S807, the response generation unit 408 creates, for example, a tagline summarizing the proposal. This processing is optional.

[0095] In step S8O8, the control unit 409 has the virtual sales agent 101 explain the product using, for example, the material displayed in step S805 and the tagline generated in step S807.

[0096] As described above, the communication assistance system 1 can generate a response different for each utterer in accordance with the utterances made by the participants taking part in the sales meeting.

[0097] Process for Responding to InquiryFIG. 9 is a flowchart illustrating an example of a process for responding to an inquiry according to the first embodiment. The illustrated process is an example of a process for responding to an inquiry, which is executed by the communication assistance apparatus 10 in step S504 illustrated in FIG. 5.

[0098] In step S901, the intention interpretation unit 407 understands the inquiry from the utterance text obtained by the speech recognition unit 402.

[0099] In step S902, the response generation unit 408 generates a response to the inquiry. For example, if the intention interpretation unit 407 is successful in understanding the inquiry, the response generation unit 408 generates a response to answer the inquiry. The generated response includes, for example, a verbal response and a non-verbal response. On the other hand, if the intention interpretation unit 407 has failed to understand the inquiry, the communication assistance apparatus 10 may stop the processing of step S903 and the subsequent processing.

[0100] In step S903, the response generation unit 408 searches for or creates a material used for responding to the inquiry. When no material is used to respond to the inquiry, the response generation unit 408 may omit the processing of step S903.

[0101] In step S904, the control unit 409 causes the terminal apparatus 100 to display the material generated by the response generation unit 408, and has the virtual sales agent 101 respond to the inquiry.

[0102] Through the processes described with reference to Figs. 5, 6, 8, and 9, the virtual sales agent 101 can propose a product tailored to the needs of the customer 3 and respond to an inquiry from the salesperson 2 or the customer 3 in the sales meeting. Further, the virtual sales agent 101 can provide a response different for each utterer, based on the spoken utterances from the participants taking part in the sales meeting.

[0103] Second EmbodimentFIG. 10 is a diagram illustrating an image of how a sales meeting takes place according to a second embodiment. In the example illustrated in FIG. 1, the communication assistance system 1 displays, on the terminal apparatus 100, a display screen intended for presentation to the salesperson 2 and the customer 3. In another example, as illustrated in FIG. 10, the communication assistance system 1 may have a function of displaying, on the terminal apparatus 100, a display screen 1001 intended for presentation to the salesperson 2, rather than the customer 3. This configuration enables the communication assistance system 1 to provide the salesperson 2 with more specific information to be hidden from the customer 3.

[0104] The functional configuration of the communication assistance system 1 according to the second embodiment may be similar to that according to the first embodiment.

[0105] Assistance ProcessFIG. 11 is a flowchart illustrating an example of an assistance process according to the second embodiment. The illustrated process is another example of the assistance process performed by the communication assistance apparatus 10 to assist in communication. The following describes an example of the process when, as illustrated in FIG. 10, the communication assistance apparatus 10 displays, on the terminal apparatus 100, a display screen for the salesperson 2. For example, the communication assistance apparatus 10 repeatedly executes the process illustrated in FIG. 11 during the sales meeting.

[0106] The basic content of the process is similar to that of the assistance process according to the first embodiment described with reference to FIG. 5, and the detailed description of the content of processing similar to that in the first embodiment will thus be omitted.

[0107] In step SI 101, the input unit 401 of the communication assistance apparatus 10 acquires a spoken utterance from a participant taking part in the sales meeting.

[0108] In step SI 102, the communication assistance apparatus 10 performs speech recognition and speaker identification on the spoken utterance acquired by the input unit 401.

[0109] In step SI 103, the response unit 405 of the communication assistance apparatus 10 determines whether the inquiry mode is set. If the inquiry mode is set, the response unit 405 causes the process to proceed to step S 1104. On the other hand, if the inquiry mode is not set, the response unit 405 causes the process to proceed to step SI 105.

[0110] When the process proceeds from step S 1103 to step S 1104, the response unit 405 executes a process for responding to an inquiry. The process for responding to an inquiry according tothe second embodiment is similar to the process for responding to an inquiry according to the first embodiment described with reference to FIG. 9.

[0111] When the process proceeds from step S 1103 to step S 1105, the response unit 405 determines whether a customer-voice mode is set. The customer-voice mode is a mode in which the virtual sales agent 101 provides recommendation information such as a product in response to an utterance made by the customer 3 while ignoring an utterance made by the salesperson 2. The salesperson 2 can set the customer- voice mode by using, for example, a setting button displayed on the display screen on the terminal apparatus 100.

[0112] If the customer-voice mode is set, the response unit 405 causes the process to proceed to step S 1106. On the other hand, if the customer- voice mode is not set, the response unit 405 causes the process to proceed to step S 1107.

[0113] In step S 1106, the response unit 405 determines whether the speaker of the spoken utterance acquired by the input unit 401 is the customer 3. If the speaker is the customer 3, the response unit 405 causes the process to proceed to step SI 107. On the other hand, if the speaker is not the customer 3, the response unit 405 ends the process illustrated in FIG. 11.

[0114] In step SI 107, the response unit 405 executes a process for responding to an utterance.

[0115] Process for Responding to UtteranceFIG. 12 is a flowchart illustrating an example of a process for responding to an utterance according to the second embodiment. The illustrated process is an example of a process for responding to an utterance, which is executed by the communication assistance apparatus 10 in step SI 107 illustrated in FIG. 11. The detailed description of the content of processing similar to that in the first embodiment will be omitted.

[0116] In step SI 201, the determination unit 406 determines whether the utterance includes an issue or a product name. In a case where the customer-voice mode is set, the term "utterance" includes an utterance made by the customer 3. In a case where the customer- voice mode is not set, the term "utterance" includes an utterance made by the salesperson 2 and an utterance made by the customer 3. If the utterance includes an issue or a product name, the determination unit 406 causes the process to proceed to step S1202. On the other hand, if the utterance does not include an issue or a product name, the determination unit 406 ends the process illustrated in FIG. 12.

[0117] In step S1202, the determination unit 406 determines a product to be proposed to the customer 3, based on the content of the utterance.

[0118] In step S1203, the response generation unit 408 generates data related to the product determined by the determination unit 406. The generated data is not intended for presentation to the customer 3, and thus may include detailed data such as sales data related to the product or data of a comparison between the product and a competitor's product.

[0119] In step S1204, the control unit 409 causes the terminal apparatus 100 to display the data generated by the response generation unit 408. For example, the control unit 409 causes the terminal apparatus 100 to display a display screen 1300 as illustrated in FIG. 13.

[0120] FIG. 13 is a diagram illustrating an example of a screen displayed on the terminal apparatus 100 according to the second embodiment. FIG. 13 illustrates an example of the display screen 1300 for the salesperson 2 displayed on the terminal apparatus 100. In the example illustrated in FIG. 13, the display screen 1300 for the salesperson 2 displays, for example, data 1301 generated by the response generation unit 408, a "Listen to customer's voice" button 1302, and a "Make visible to customer" button 1303.

[0121] The data 1301 generated by the response generation unit 408 includes detailed information such as the number of units sold for Product A in the last three months and information on types of businesses that buy Product A, as data on a well-selling product related to electronic invoicing.

[0122] By selecting the "Listen to customer's voice" button 1302 on the display screen 1300, the salesperson 2 can set or cancel the customer-voice mode. By selecting the "Make visible to customer" button 1303, the salesperson 2 can switch the display screen 1300 for the salesperson 2 to, for example, the display screen 710 visible to the customer 3 as illustrated in FIG. 7.

[0123] In step S1205, the control unit 409 determines whether the virtual sales agent 101 explains the product. For example, if the salesperson 2 performs a predetermined operation, such as pressing a button or giving a sign by voice, within a predetermined amount of time, the control unit 409 determines that the virtual sales agent 101 explains the product. On the other hand, if the salesperson 2 does not perform the predetermined operation within the predetermined amount of time, the control unit 409 determines that the virtual sales agent 101 does not explain the product.

[0124] If it is determined that the virtual sales agent 101 explains the product, the control unit 409 causes the process to proceed to step S1206. On the other hand, if it is determined that the virtual sales agent 101 does not explain the product, the control unit 409 ends the processillustrated in FIG. 12. In this case, the salesperson 2 can provide a detailed explanation of the product (e.g., Product A) to the customer 3 while viewing the detailed information of the data 1301 displayed on the display screen 1300 for the salesperson 2.

[0125] In step S1206, the response generation unit 408 generates a response to the utterance. For example, the response generation unit 408 generates a verbal response and a non-verbal response for the virtual sales agent 101 to explain the product determined by the determination unit 406.

[0126] In step S1207, the response generation unit 408 searches for or creates a material for the product to be proposed to the customer 3.

[0127] In step S1208, the control unit 409 causes the terminal apparatus 100 to display the generated material. For example, the control unit 409 displays, on the display screen 710 visible to the customer 3 as illustrated in FIG. 7, the material 711 that has been the generated.

[0128] In step S1209, the control unit 409 has the virtual sales agent 101 explain the product using, for example, the material displayed in step S1207.

[0129] As described above, the communication assistance system 1 can display, to the salesperson 2, the display screen 1300 for the salesperson 2 to provide more detailed information related to the product.

[0130] Third EmbodimentThe communication assistance system 1 can identify whether the utterer is the salesperson 2 or the customer 3, and make a different response to the same topic depending on the utterer. For example, when the salesperson 2 states, "This product is energy-efficient", the virtual sales agent 101 can provide information on a comparison between the product and a competitor's product. When the customer 3 states the same phrase, the virtual sales agent 101 can provide specific advantages and usage examples of the product.

[0131] Further, the communication assistance system 1 can analyze an inquiry, a reaction, or the like from the customer 3 and display a product flyer according to the interests, needs, or the like of the customer 3. For example, when the customer 3 states, "I am interested in eco-friendly products", the virtual sales agent 101 can automatically present flyers and information on environmentally friendly products.

[0132] FIG. 14 is a flowchart illustrating an example of an assistance process according to a third embodiment. The illustrated process is another example of the communication assistance process performed by the communication assistance system 1.

[0133] In step S1401, the input unit 401 of the communication assistance apparatus 10 acquires a spoken utterance from a participant taking part in the sales meeting. For example, the input unit 401 acquires spoken utterances from the salesperson 2 and the customer 3 transmitted from the terminal apparatus 100.

[0134] In step S1402, the communication assistance apparatus 10 performs speech recognition and speaker identification on the spoken utterance acquired by the input unit 401. For example, the speech recognition unit 402 converts the spoken utterance acquired by the input unit 401 into text to create an utterance text. Further, the speaker identification unit 403 identifies a participant who has made the spoken utterance acquired by the input unit 401, and the identification unit 404 identifies whether the participant who has made the spoken utterance is the salesperson 2 or the customer 3.

[0135] In step S1403, the response unit 405 determines whether the speaker is the customer 3. If the speaker is the customer 3, the response unit 405 causes the process to proceed to step S1404. On the other hand, if the speaker is not the customer 3, the response unit 405 causes the process to proceed to step S1408.

[0136] When the process proceeds from step S1403 to step S1404, the response unit 405 analyzes the content (response strategy) based on the utterer (the customer 3) and the content of the utterance.

[0137] In step S1405, the response unit 405 determines content appropriate for the utterer (the customer 3) from the database. For example, the response unit 405 selects a related flyer, information, or the like from the database, based on the interests, needs, or the like of the utterer.

[0138] In step S1406, the response unit 405 generates a response for the utterer (the customer 3). The response is customized to include information on specific advantages and usage examples of the product.

[0139] In step S1407, the response unit 405 controls the virtual sales agent 101 in accordance with the generated response.

[0140] When the process proceeds from step S1403 to step S1408, the response unit 405 determines whether the speaker is the salesperson 2. If the speaker is the salesperson 2, the response unit 405 causes the process to proceed to step S 1409. On the other hand, if the speaker is not the salesperson 2, the response unit 405 ends the process illustrated in FIG. 14.

[0141] In step S1409, the response unit 405 analyzes the content (response strategy) based on the utterer (the salesperson 2) and the content of the utterance.

[0142] In step S1410, the response unit 405 determines content appropriate for the utterer (the salesperson 2) from the database. For example, the response unit 405 selects a related flyer, information, or the like from the database, based on the interests, needs, or the like of the utterer.

[0143] In step S 1411, the response unit 405 generates a response for the utterer (the salesperson 2). The response is customized to include, for example, information on the positioning of the product in the market or comparison with competitive products.

[0144] In step S1412, the response unit 405 controls the virtual sales agent 101 in accordance with the response generated by the response generation unit 408.

[0145] Through the process illustrated in FIG. 14, the communication assistance system 1 can identify whether the utterer is the salesperson 2 or the customer 3, and make a different response to the same topic depending on the utterer.

[0146] Fourth EmbodimentThe communication assistance system 1 can change the type of information to be provided, the method for expressing the information, or the like, based on the role of an utterer such as the salesperson 2, the customer 3, or a decision maker. For example, in a case where the customer 3 makes an inquiry about a specific function, the virtual sales agent 101 can provide the customer 3 with a response focusing on, for example, the advantages or user experience of the product. In a case where the salesperson 2 makes an inquiry about the same specific function, the virtual sales agent 101 can provide the salesperson 2 with more detailed technical information or advice related to, for example, a sales strategy.

[0147] FIG. 15 is a flowchart illustrating an example of an assistance process according to a fourth embodiment. The illustrated process is an example of the communication assistance process performed by the communication assistance system 1.

[0148] In the process illustrated in FIG. 15, the processing of steps S1401 to S1406 and S1408 to S 1411 is similar to that in the assistance process according to the third embodiment described with reference to FIG. 14, and a description thereof will thus be omitted.

[0149] In step S1501, the response unit 405 adjusts the method for expressing the response generated in step S1406 according to the role of the utterer (the customer 3).

[0150] In step S1502, the control unit 409 controls the virtual sales agent 101 in accordance with the response adjusted by the response unit 405 according to the role of the utterer (the customer 3).

[0151] In step S1503, the response unit 405 adjusts the method for expressing the response generated in step S 1411 according to the role of the utterer (the salesperson 2).

[0152] In step S1504, the control unit 409 controls the virtual sales agent 101 in accordance with the response adjusted by the response unit 405 according to the role of the utterer (the salesperson 2).

[0153] Through the process illustrated in FIG. 15, the communication assistance system 1 can change the type of information to be provided, the method for expressing the information, or the like, based on the role of an utterer such as the salesperson 2, the customer 3, or a decision maker.

[0154] Fifth EmbodimentFunctional ConfigurationFIG. 16 is a diagram illustrating an example functional configuration of a communication assistance system 1 according to a fifth embodiment. A communication assistance apparatus 10 according to the fifth embodiment illustrated in FIG. 16 includes a feedback unit 1601 in addition to the functional configuration of the communication assistance apparatus 10 according to the first embodiment described with reference to FIG. 4.

[0155] The feedback unit 1601 is implemented by, for example, a program executed by the CPU 201. The feedback unit 1601 executes a feedback process for determining whether the proposed recommendation information is effective and feeding the determination result back to the response unit 405. For example, the feedback unit 1601 analyzes audio data during the sales meeting, determines which provided information is effective or ineffective, and feeds the determination result back to the response unit 405. The response unit 405 continuously learns based on the feedback, and generates a more effective response. For example, in a case where the explanation of a specific product is popular with the customer 3, the response unit 405 also uses the explanation of the specific product in other sales meetings.

[0156] The communication assistance system 1 may analyze feedback and a reaction from each utterer during a conversation and adaptively adjust the next response. For example, in a case where a certain customer 3 demonstrates a price-sensitive reaction, the communication assistance system 1 makes proposals focusing on cost efficiency for the customer 3, while providing the salesperson 2 with advice on price negotiation strategies or presentation of alternative proposals.

[0157] The functional configuration of the communication assistance system 1 according to the fifth embodiment, other than the feedback unit 1601, may be similar to the functional configuration of the communication assistance system 1 according to the first embodiment described with reference to FIG. 4.

[0158] Operation FlowFeedback Collection ProcessFIG. 17 is a flowchart illustrating an example of a feedback collection process according to the fifth embodiment. The illustrated process may be implemented in combination with the assistance processes according to the other embodiments.

[0159] In step S1701, the communication assistance apparatus 10 executes a response process for controlling the virtual sales agent 101 in accordance with the generated response. This processing corresponds to, for example, the processing of steps S1407 and S1412 in FIG. 14.

[0160] In step S1702, the feedback unit 1601 determines whether the effect of the response is positive. For example, after the response process, the feedback unit 1601 analyzes the spoken utterance made by the utterer in real time and determines whether the response is effective. If the effect of the response is positive, the feedback unit 1601 causes the process to proceed to step S1703. On the other hand, if the effect of the response is not positive, the feedback unit 1601 causes the process to proceed to step S1704.

[0161] In step S1703, the feedback unit 1601 stores the response in, for example, a database 1800 as illustrated in FIG. 18 as training data for successful cases. In step S1704, on the other hand, the feedback unit 1601 stores the response in the database 1800 as training data for failure cases. The database 1800 is stored in, for example, the storage unit 413.

[0162] FIG. 18 is a diagram illustrating an example of the database 1800 according to the fifth embodiment. In the example illustrated in FIG. 18, the database 1800 includes items such as "ID", "speaker identification", "utterance", "content", "response", "output device", "outputformat", "analysis result (customer reaction)", "analysis result (salesperson reaction)", and "response effect".

[0163] The "ID" is identification information for identifying each record stored in the database 1800. The "speaker identification" is information indicating whether the utterer is the salesperson 2 or the customer 3. The "utterance" is an utterance text indicating the content of an utterance made by the utterer for the response process. The "content" is information indicating a proposal material or the like in the response process. The "response" is information indicating the content of a response in the response process. The "output device" is information indicating the device that outputs the utterance, and may be the terminal A operated by the customer 3 or the terminal B operated by the salesperson 2 in this example. The "output format" is information indicating the format of the proposal material or the like. The "analysis result" is information indicating the analysis result of the "utterance". The "response effect" is information indicating whether the effect of the response is positive or negative, as determined in step S1702.

[0164] Content Determination ProcessFIG. 19 is a flowchart illustrating an example of a content determination process according to the fifth embodiment. The illustrated process is an example of a process for determining content appropriate for the utterer from the database in steps S1405 and S1410 illustrated in FIG. 14.

[0165] In step S1901, the response unit 405 compares, based on the utterance text, the approach with the database and analyzes whether the approach is similar to any previous approach. For example, the response unit 405 refers to the database 1800 as illustrated in FIG. 18 and extracts training data (record) similar to the utterance text.

[0166] In step S1902, when the approach is similar to any previous approach, the response unit 405 determines appropriate content based on the training data for the previous successful examples. For example, the response unit 405 determines, based on training data that is extracted and indicates a positive "response effect", appropriate "content" according to the "analysis result (customer reaction)" or the "analysis result (salesperson reaction)" of the training data.

[0167] When the approach is not similar to any previous approach, the response unit 405 may determine, based on training data that is not similar to the utterance text and indicates a positive "response effect", appropriate "content" according to the "analysis result (customer reaction)" or the "analysis result (salesperson reaction)" of the training data.

[0168] Through the process illustrated in FIG. 19, the response unit 405 can determine content appropriate for the utterer from the database 1800.

[0169] Sixth EmbodimentThe communication assistance system 1 can automatically create, for example, a daily report or minutes of a sales meeting by using the virtual sales agent 101. For example, in a case where the salesperson 2 makes an inquiry about features of a product, the virtual sales agent 101 can provide advice related to a sales strategy, and in a case where the customer 3 makes the same inquiry, the virtual sales agent 101 can emphasize user experience or actual use scenarios of the product.

[0170] Further, the virtual sales agent 101 automatically records the content of the sales meeting and creates a daily report of the sales meeting for the salesperson 2. The daily report includes, for example, main points of the sales meeting, a reaction from the customer 3, a proposed product, and obtained feedback.

[0171] Such an approach can more appropriately address the needs and expectations of a salesperson and a customer and provide the most relevant information from each perspective. Thus, the communication assistance system 1 can contribute to improving customer experience and optimizing sales efficiency.

[0172] Functional ConfigurationFIG. 20 is a diagram illustrating an example functional configuration of a communication assistance system 1 according to a sixth embodiment. A communication assistance apparatus 10 according to the sixth embodiment illustrated in FIG. 20 includes a creation unit 2001 in addition to the functional configuration of the communication assistance apparatus 10 according to the fifth embodiment described with reference to FIG. 16.

[0173] The creation unit 2001 executes a creation process for recording the content of communication such as a sales meeting, based on spoken utterances acquired by the input unit 401, and creating, for example, a daily report or minutes of the sales meeting.

[0174] The functional configuration of the communication assistance system 1 according to the sixth embodiment, other than the creation unit 2001, may be similar to the functional configuration of the communication assistance system 1 according to the first embodiment described with reference to FIG. 4 and the functional configuration of the communication assistance system 1 according to the fifth embodiment described with reference to FIG. 16.

[0175] Operation FlowFIG. 21 is a flowchart illustrating an example of an assistance process according to the sixth embodiment. The illustrated process is another example of the communication assistance process performed by the communication assistance system 1.

[0176] In step S2101, the communication assistance system 1 selects a scenario of a daily report, and then repeatedly executes the processing of step S2102 and the subsequent processing. The scenario defines, for example, related information such as the level of a sales meeting (e.g., a sales meeting with a new customer or a sales meeting with an existing customer), product features, and market trends. In one example, the roles of utterers, such as the salesperson 2, the customer 3, and other stakeholders, are identified, and their respective needs and expectations are further defined in the scenario.

[0177] In step S2102, the input unit 401 of the communication assistance apparatus 10 acquires a spoken utterance from a participant taking part in the sales meeting. For example, the input unit 401 acquires spoken utterances from the salesperson 2 and the customer 3 transmitted from the terminal apparatus 100.

[0178] In step S2103, the communication assistance apparatus 10 performs speech recognition and speaker identification on the spoken utterance acquired by the input unit 401. For example, the speech recognition unit 402 converts the spoken utterance acquired by the input unit 401 into text to create an utterance text. The identification unit 404 analyzes the spoken utterance acquired by the input unit 401 and identifies whether the utterer is the salesperson 2 or the customer 3.

[0179] In step S2104, the response unit 405 determines whether the speaker is the customer 3. If the speaker is the customer 3, the response unit 405 causes the process to proceed to step S2105. On the other hand, if the speaker is not the customer 3, the response unit 405 causes the process to proceed to step S2110.

[0180] When the process proceeds from step S2104 to step S2105, the response unit 405 selects an appropriate response strategy based on the role of the utterer (the customer 3) and the content of the utterance.

[0181] In step S2106, the response unit 405 determines content appropriate for the utterer (the customer 3) from the database. For example, the response unit 405 selects a related flyer, information, or the like from the database, based on the interests, needs, or the like of the utterer.

[0182] In step S2107, the response unit 405 generates a response for the utterer (the customer 3). The response is customized according to the needs of the utterer, based on the selected response strategy. For example, the response for the customer 3 includes information focusing on comfort of use or usage experience of the product.

[0183] In step S2108, the response unit 405 controls the virtual sales agent 101 in accordance with the generated response.

[0184] In step S2109, the creation unit 2001 records, for example, the utterance made by the customer 3 in the daily report, based on the scenario selected in step S2101.

[0185] When the process proceeds from step S2104 to step S2110, the response unit 405 determines whether the speaker is the salesperson 2. If the speaker is the salesperson 2, the response unit 405 causes the process to proceed to step S2111. On the other hand, if the speaker is not the salesperson 2, the response unit 405 ends the process illustrated in FIG. 21.

[0186] In step S2111, the response unit 405 selects an appropriate response strategy based on the role of the utterer (the salesperson 2) and the content of the utterance.

[0187] In step S2112, the response unit 405 determines content appropriate for the utterer (the salesperson 2) from the database. For example, the response unit 405 selects a related flyer, information, or the like from the database, based on the interests, needs, or the like of the utterer.

[0188] In step S2113, the response unit 405 generates a response for the utterer (the salesperson 2). The response is customized according to the needs of the utterer, based on the selected response strategy. For example, the response for the salesperson 2 includes information on a sales strategy for the product.

[0189] In step S2114, the response unit 405 controls the virtual sales agent 101 in accordance with the generated response.

[0190] In step S2115, the creation unit 2001 records, for example, the utterance made by the salesperson 2 and a reaction from the customer 3 in the daily report, based on the scenario selected in step S2101. Through the process illustrated in FIG. 21, the communication assistance system 1 can automatically create, for example, a daily report of a sales meeting by using the virtual sales agent 101.

[0191] Examples of Additional FunctionsPersonalized ProposalThe communication assistance system 1 can also make a more personalized product proposal by analyzing the previous purchase data or interests of the customer 3.

[0192] For example, the communication assistance system 1 collects data of the customer 3, such as the previous purchase history, online behavior, preferences, or feedback, and stores the data in, for example, a database. Further, the communication assistance system 1 analyzes the collected data and identifies, for example, the preference, interest, purchase pattern, or the like of the customer 3.

[0193] Based on the analysis result, the communication assistance system 1 proposes a product optimal for the customer 3 in the sales meeting or the like, and customizes information or the like for explaining the product according to the preference, interest, purchase pattern, or the like of the customer 3.

[0194] Preferably, the communication assistance system 1 collects reactions, feedback, or the like from the customer 3, and continuously enhance the proposal algorithm based on the collected information.

[0195] Language IdentificationThe communication assistance system 1 can identify the language used, from the content of the utterance made by the customer 3, and perform language switching and translation, for example.

[0196] For example, the communication assistance system 1 automatically identifies the language used by the customer 3, from the content of the utterance made by the customer 3. Further, the communication assistance system 1 switches, according to the identified language, the language to be used by the virtual sales agent 101 for responding, the language used on the display screen, or the like. This enables the communication assistance system 1 to translate the response spoken by the virtual sales agent 101 in real time and provide a spoken response in a language easy for the customer 3 to understand.

[0197] Preferably, the communication assistance system 1 continuously enhances the language translation algorithm based on feedback from the customer 3.The following describes examples of use scenarios.

[0198] Metaverse SpaceThe metaverse is an immersive digital space that utilizes virtual reality (VR) or augmented reality (AR) technology. In this space, the virtual sales agent 101 can appear as an avatar and conduct product introductions and demonstrations in real time.

[0199] In the metaverse, the virtual sales agent 101 provides the customer 3 with a more realistic product experience, and enables an interactive sales meeting.

[0200] For example, the virtual sales agent 101 identifies a conversation between the salesperson 2 and the customer 3 in the metaverse, and provides different reactions depending on the speaker. For example, in a case where the salesperson 2 makes an inquiry about features of a product, the virtual sales agent 101 responds from the perspective of a sales strategy or market analysis. In a case where the customer 3 makes the same inquiry, in contrast, the virtual sales agent 101 responds, focusing on how to use the product or user experience.

[0201] Online Conferencing SystemThe virtual sales agent 101 is utilized on an online conferencing platform and introduces products and services through video calls and screen sharing.

[0202] In an online conferencing system, the virtual sales agent 101 can support efficient communication in remote work or international business meetings.

[0203] For example, the virtual sales agent 101 analyzes a conversation in an online meeting in real time and distinguishes between a statement made by the salesperson 2 and a statement made by the customer 3. In a case where the salesperson 2 makes an inquiry about a competitive product, the virtual sales agent 101 explains a detailed comparison with the competitive product. In a case where the customer 3 makes the same inquiry, in contrast, the virtual sales agent 101 responds, focusing on direct benefits or value for the customer 3.

[0204] Web-Based ChatbotAs a chatbot integrated into a corporate website, an e-commerce platform, or the like, the virtual sales agent 101 responds to customer inquiries in real time and proposes related products or services.

[0205] The chatbot is available 24 hours a day and 365 days a year and provides immediate responses to improve customer satisfaction.

[0206] For example, the chatbot identifies the salesperson 2 and the customer 3 from a conversation on the website. In a case where the salesperson 2 makes an inquiry about the inventory status of a product, the chatbot provides information on inventory management or logistics. In a casewhere the customer 3 requests the same information, the chatbot prioritizes providing information on an available product option or a delivery schedule.

[0207] Social Media PlatformOn social media, the virtual sales agent 101 can introduce a product through interactive content, live streaming, or the like and communicate directly with the customer 3.

[0208] Social media can reach a wide audience and contribute to increasing brand awareness.

[0209] For example, on social media, the virtual sales agent 101 provides detailed product information or market analysis in response to a technical inquiry from the salesperson 2, and provides daily product usage examples or user reviews in response to a similar inquiry from the customer 3.

[0210] Mobile ApplicationIn a smartphone or tablet application, the virtual sales agent 101 provides a customer with, for example, a personalized promotion or product information.

[0211] A mobile application enhances customer convenience and enables providing information anytime and anywhere.

[0212] For example, within the mobile application, the virtual sales agent 101 provides a sales promotion strategy or market trend information in response to an inquiry from the salesperson 2, and prioritizes providing product features or usage information in response to an inquiry from the customer 3.

[0213] Interactive Kiosk or Digital SignageA kiosk, digital signage, or the like with the virtual sales agent 101 incorporated therein is installed in a physical store, an exhibition, or the like to provide a customer with product information.

[0214] Thus, a digitized interactive customer experience can be realized even in a physical space.

[0215] For example, at a kiosk in a physical store, the virtual sales agent 101 provides store sales data or customer trends to the salesperson 2, and offers interactive demonstrations on product features or usage to general customers.

[0216] According to the embodiments of the present disclosure described above, a dialogue agent can be used to easily assist in communication in which a plurality of participants are taking part.

[0217] The present invention can be implemented in any convenient form, for example using dedicated hardware, or a mixture of dedicated hardware and software. The present invention may be implemented as computer software implemented by one or more networked processing apparatuses. The processing apparatuses include any suitably programmed apparatuses such as a general purpose computer, a personal digital assistant, a Wireless Application Protocol (WAP) or third-generation (3G)-compliant mobile telephone, and so on. Since the present invention can be implemented as software, each and every aspect of the present invention thus encompasses computer software implementable on a programmable device. The computer software can be provided to the programmable device using any conventional carrier medium (carrier means). The carrier medium includes a transient carrier medium such as an electrical, optical, microwave, acoustic or radio frequency signal carrying the computer code. An example of such a transient medium is a Transmission Control Protocol / Intemet Protocol (TCP / IP) signal carrying computer code over an IP network, such as the Internet. The carrier medium may also include a storage medium for storing processor readable code such as a floppy disk, a hard disk, a compact disc read-only memory (CD- ROM), a magnetic tape device, or a solid state memory device.The functionality of the elements disclosed herein may be implemented using circuitry or processing circuitry which includes general purpose processors, special purpose processors, integrated circuits, application- specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and / or combinations thereof which are configured or programmed, using one or more programs stored in one or more memories, to perform the disclosed functionality. Processors are considered processing circuitry or circuitry as they include transistors and other circuitry therein. In the disclosure, the circuitry, units, or means are hardware that carry out or are programmed to perform the recited functionality. The hardware may be any hardware disclosed herein which is programmed or configured to carry out the recited functionality. There is a memory that stores a computer program which includes computer instructions. These computer instructions provide the logic and routines that enable the hardware (e.g., processing circuitry or circuitry) to perform the method disclosed herein. This computer program can be implemented in known formats as a computer-readable storage medium, a computer program product, a memory device, a record medium such as a CD- ROM or DVD, and / or the memory of an FPGA or ASIC.

[0218] The apparatuses described in one or more embodiments are just one example of plural computing environments that implement the embodiments disclosed herein. In some embodiments, the communication assistance apparatus 10 includes multiple computing devices, such as a server cluster. The multiple computing devices communicate with one another through any type of communication link including a network, a shared memory, or the like and perform the processes disclosed herein.

[0219] Further, the functional components of the communication assistance apparatus 10 may be integrated into one server apparatus or divided into a plurality of apparatuses. In addition, at least some of the functional components of the communication assistance apparatus 10 may be included in the terminal apparatus 100.

[0220] The above-described embodiments are illustrative and do not limit the present invention. Thus, numerous additional modifications and variations are possible in light of the above teachings. For example, elements and / or features of different illustrative embodiments may be combined with each other and / or substituted for each other within the scope of the present invention. Any one of the above-described operations may be performed in various other ways, for example, in an order different from the one described above. A communication assistance apparatus, a communication assistance system, a communication assistance method, and a program of the following aspects are disclosed herein.In a first aspect, a communication assistance apparatus for assisting in communication that a plurality of participants engage in includes an input unit, a speaker identification unit, an identification unit, a response generation unit, and a control unit. The input unit receives an input of a statement in the communication. The speaker identification unit identifies a participant who has made the statement for which the input is received among the plurality of participants. The identification unit identifies an attribute of the participant identified by the speaker identification unit. The response generation unit generates a response, based on the attribute of the identified participant and content of the statement. The control unit performs control to output the response generated by the response generation unit.According to a second aspect, in the communication assistance apparatus of the first aspect, the plurality of participants include a host and a guest, the host and the guest being taking part in the communication, and the response includes recommendation information to be proposed to the guest.According to a third aspect, in the communication assistance apparatus of the second aspect, the communication includes a sales meeting, and the response includes information on a product to be proposed to the guest, and an explanation of the product.According to a fourth aspect, in the communication assistance apparatus of the third aspect, the response includes an explanation of the product for the host and an explanation of the product for the guest different from the explanation of the product for the host.According to a fifth aspect, in the communication assistance apparatus of any one of the first aspect to the fourth aspect, the response includes non-verbal information, and the control unit causes a dialogue agent to output the non-verbal information.According to a sixth aspect, in the communication assistance apparatus of the fifth aspect, the non-verbal information includes one or more of a facial expression, a direction of gaze, a body posture, an emotion, a gesture, and a paralanguage.According to a seventh aspect, in the communication assistance apparatus of any one of the first aspect to the sixth aspect, the response includes verbal information of a dialogue agent, and the control unit controls an utterance to be made by the dialogue agent, based on the verbal information.According to an eighth aspect, in the communication assistance apparatus of any one of the second aspect to the fourth aspect, the control unit causes a dialogue agent to propose the recommendation information in accordance with flow of the communication.According to a ninth aspect, in the communication assistance apparatus of the third aspect, the control unit causes a dialogue agent to start the explanation of the product in accordance with an instruction from the host.According to a tenth aspect, in the communication assistance apparatus of any one of the first aspect to the ninth aspect, the response generation unit generates a different response according to an attribute of each of the plurality of participants.According to an eleventh aspect, the communication assistance apparatus of any one of the second aspect to the fourth aspect further includes a feedback unit. The feedback unit determines whether the recommendation information proposed to the guest is effective and provide feedback.According to a twelfth aspect, the communication assistance apparatus of any one of the first aspect to the eleventh aspect further includes a creation unit. The creation unit records content of the communication and creates a daily report or minutes of the communication, based on the statement.According to a thirteenth aspect, in the communication assistance apparatus of the twelfth aspect, the creation unit creates the daily report or the minutes based on a predefined scenario. According to a fourteenth aspect, in the communication assistance apparatus of any one of the first aspect to the thirteenth aspect, the response generation unit generates a response personalized for each of the plurality of participants, based on a history of a corresponding participant of the plurality of participants.In a fifteenth aspect, a communication assistance system for assisting in communication that a plurality of participants engage in includes a terminal apparatus and a server apparatus. The server apparatus includes an input unit, a speaker identification unit, an identification unit, a response generation unit, and a control unit. The input unit receives an input of a statement in the communication. The speaker identification unit identifies a participant who has made the statement for which the input is received among the plurality of participants. The identification unit identifies an attribute of the participant identified by the speaker identification unit. The response generation unit generates a response, based on the attribute of the identified participant and content of the statement. The control unit performs control to output the response generated by the response generation unit. The terminal apparatus includes a data transmission unit. The data transmission unit transmits a statement made by a participant among the plurality of participants to the server apparatus.In a sixteenth aspect, a communication assistance method is implemented by a computer for assisting in communication that a plurality of participants engage in. The communication assistance method includes receiving an input of a statement in the communication; identifying a participant who has made the statement for which the input is received among the plurality of participants; identifying an attribute of the identified participant; generating a response, based on the attribute of the identified participant and content of the statement; and performing control to output the generated response.In a seventeenth aspect, a program causes a computer to execute the communication assistance method of the sixteenth aspect.

[0221] This patent application is based on and claims priority to Japanese Patent Application No. 2024-044143, filed on March 19, 2024, in the Japan Patent Office, the entire disclosure of which is hereby incorporated by reference herein.[Reference Signs List]

[0222] 1 communication assistance system2 salesperson (host)3 customer (guest)10 communication assistance apparatus100 terminal apparatus200 computer401 input unit403 speaker identification unit404 identification unit408 response generation unit409 control unit421 data transmission unit422 display unit423 speech output unit1601 feedback unit2001 creation unit

Claims

[CLAIMS]1. A communication assistance apparatus for assisting in communication that a plurality of participants engage in, the communication assistance apparatus comprising: an input unit configured to receive an input of a statement in the communication; a speaker identification unit configured to identify a participant who has made the statement for which the input is received among the plurality of participants; an identification unit configured to identify an attribute of the identified participant; a response generation unit configured to generate a response, based on the attribute of the identified participant and content of the statement; and a control unit configured to perform control to output the generated response.

2. The communication assistance apparatus according to claim 1, wherein the plurality of participants include a host and a guest, the host and the guest being taking part in the communication, and the response includes recommendation information to be proposed to the guest.

3. The communication assistance apparatus according to claim 2, wherein the communication includes a sales meeting, and the response includes information on a product to be proposed to the guest, and an explanation of the product.

4. The communication assistance apparatus according to claim 3, wherein the response includes an explanation of the product for the host and an explanation of the product for the guest different from the explanation of the product for the host.

5. The communication assistance apparatus according to any one of claims 1 to 4, wherein the response includes non-verbal information, and the control unit is configured to cause a dialogue agent to output the non-verbal information.

6. The communication assistance apparatus according to claim 5, wherein the nonverbal information includes one or more of a facial expression, a direction of gaze, a body posture, an emotion, a gesture, and a paralanguage.

7. The communication assistance apparatus according to any one of claims 1 to 6, wherein the response includes verbal information of a dialogue agent, and the control unit is configured to control an utterance to be made by the dialogue agent, based on the verbal information.

8. The communication assistance apparatus according to any one of claims 2 to 4, wherein the control unit is configured to cause a dialogue agent to propose the recommendation information in accordance with flow of the communication.

9. The communication assistance apparatus according to claim 3, wherein the control unit is configured to cause a dialogue agent to start the explanation of the product in accordance with an instruction from the host.

10. The communication assistance apparatus according to any one of claims 1 to 9, wherein the response generation unit is configured to generate a different response according to an attribute of each of the plurality of participants.

11. The communication assistance apparatus according to any one of claims 2 to 4, further comprising a feedback unit configured to determine whether the recommendation information proposed to the guest is effective and provide feedback.

12. The communication assistance apparatus according to any one of claims 1 to 11, further comprising a creation unit configured to record content of the communication and create a daily report or minutes of the communication, based on the statement.

13. The communication assistance apparatus according to claim 12, wherein the creation unit is configured to create the daily report or the minutes based on a predefined scenario.

14. The communication assistance apparatus according to any one of claims 1 to 13, wherein the response generation unit is configured to generate a response personalized for each of the plurality of participants, based on a history of a corresponding participant of the plurality of participants.

15. A communication assistance system for assisting in communication that a plurality of participants engage in, the communication assistance system comprising: a terminal apparatus; and a server apparatus, wherein the server apparatus includes: an input unit configured to receive an input of a statement in the communication; a speaker identification unit configured to identify a participant who has made the statement for which the input is received among the plurality of participants; an identification unit configured to identify an attribute of the participant identified by the speaker identification unit;a response generation unit configured to generate a response, based on the attribute of the identified participant and content of the statement; and a control unit configured to perform control to output the generated response, and the terminal apparatus includes a data transmission unit configured to transmit a statement made by a participant among the plurality of participants to the server apparatus.

16. A communication assistance method, performed by a computer, for assisting in communication that a plurality of participants engage in, the communication assistance method comprising: receiving an input of a statement in the communication; identifying a participant who has made the statement for which the input is received among the plurality of participants; identifying an attribute of the identified participant; generating a response, based on the attribute of the identified participant and content of the statement; and performing control to output the generated response.

17. A recording medium storing a program for causing a computer system to execute the communication assistance method according to claim 16.

Images