Dialogue support method, information processing device, and program

Abstract

To improve dialogue support technology in business negotiations. [Solution] A dialogue support method executed by an information processing device, comprising: determining a topic based on audio data relating to a predetermined object and a database relating to a predetermined object; extracting a question sentence from the audio data; generating a supplementary question sentence based on the question sentence and the topic during the period in which the question sentence was extracted; and outputting an answer corresponding to the supplementary question sentence.

Description

Technical Field

[0001] The present disclosure relates to a dialogue support method, an information processing apparatus, and a program.

Background Art

[0002] Conventionally, techniques for analyzing the content of business negotiations have been known. For example, Patent Document 1 discloses a dialogue analysis system that checks whether a salesperson explains matters to be explained and does not mention matters that should not be mentioned in a business negotiation with a customer.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Although Patent Document 1 discloses a technique for analyzing the content of business negotiations by machine learning, a technique for supporting dialogue in business negotiations and the like has not been studied. Here, in a dialogue such as a business negotiation, a question regarding a product, service, or the like may be presented from a customer or the like. It can be assumed that answer candidates are automatically obtained for such a question by a machine learning model such as a chatbot or a large language model. However, in order to obtain an appropriate answer, it is necessary to understand the flow and context of the conversation and interpret the question, and such matters have not been studied in the prior art. Thus, there has been room for improvement in dialogue support technology.

[0005] In view of such circumstances, an object of the present disclosure is to improve dialogue support technology.

Means for Solving the Problems

[0006] A dialogue support method according to an embodiment of the present disclosure is A method for providing dialogue support that is performed by an information processing device, Determining a topic based on audio data relating to a specified object and a database relating to the said specified object, The process involves extracting question sentences from the audio data, generating supplementary question sentences based on the question sentences and the topics during the period in which the question sentences were extracted, Outputting the answer corresponding to the aforementioned supplementary question, Includes. [Effects of the Invention]

[0007] According to one embodiment of this disclosure, dialogue support technology is improved. [Brief explanation of the drawing]

[0008] [Figure 1] This is a block diagram showing the schematic configuration of the system according to this embodiment. [Figure 2] This is a flowchart showing the operation of the information processing device according to this embodiment. [Figure 3] This is a flowchart showing the operation of the information processing device related to the modified example 1. [Figure 4] This is a flowchart showing the operation of the information processing device related to the modified example 2. [Figure 5] This is a flowchart showing the operation of the information processing device related to the modified example 3. [Figure 6] This is a flowchart showing the operation of the information processing device related to Modification 4. [Modes for carrying out the invention]

[0009] The embodiments of this disclosure will be described below.

[0010] (Summary of the embodiment) Referring to Figure 1, the overview and configuration of System 1 according to this embodiment will be described. System 1 according to this embodiment comprises an information processing device 10 and a server device 20. The information processing device 10 and the server device 20 are communicated with a network 30, which includes, for example, a mobile communication network and the Internet.

[0011] The information processing device 10 is any device used by staff during business negotiations, etc. For example, a personal computer, smartphone, tablet terminal, wearable device, or other general-purpose electronic device, or a dedicated electronic device, can be used as the information processing device 10. Although Figure 1 shows an example where System 1 has one information processing device 10, it is not limited to this. System 1 may have two or more information processing devices 10.

[0012] The server device 20 is a server device installed, for example, in a data center. For example, the server device 20 is a server belonging to a cloud computing system or other computing system. The server device 20 can communicate with the information processing device 10 via the network 30. The server device 20 includes a language model. In this embodiment, the language model includes, for example, a Large Language Model (LLM), a chatbot, or any other dialogue system. The language model outputs text or the like corresponding to a prompt based on the input of a prompt. For example, the information processing device 10 inputs a prompt to the language model of the server device 20 and obtains the output result corresponding to the prompt. Although Figure 1 shows an example in which system 1 has one server device 20, it is not limited to this. System 1 may have two or more server devices 20.

[0013] First, an overview of the dialogue support technology according to the present embodiment will be described, and details will be described later. The dialogue support technology according to the present embodiment can be used, for example, in business negotiations and the like. For example, business negotiations may be meetings and the like for the purpose of concluding various types of contracts, such as the sale of vehicles, the purchase and sale of real estate, the conclusion of insurance contracts, the sale of financial products, and the like. Also, the predetermined thing in the present embodiment may include the offerings provided in business negotiations and the like. For example, the predetermined thing may be a product such as a vehicle, a service, digital content, a license, data / information, a financial product, real estate, an intangible asset, other tradable rights, and the like.

[0014] The information processing apparatus 10 determines a topic based on voice data regarding a predetermined thing and a database regarding the predetermined thing. Further, the information processing apparatus 10 extracts a question sentence from the voice data, and generates a complementary question sentence based on the question sentence and the topic during the period when the question sentence is extracted. Then, the information processing apparatus 10 outputs an answer corresponding to the complementary question sentence.

[0015] As described above, according to the present embodiment, the information processing apparatus 10 determines a topic, complements questions in the conversation based on the determined topic, automatically generates an answer, and outputs it. For this reason, a complementary question sentence considering the flow of the conversation is generated, and an answer to the complementary question sentence is obtained, so that the dialogue support technology is improved.

[0016] Next, each configuration of the information processing apparatus 10 and the server apparatus​​​​​​​​​The control unit 11 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or a GPU (graphics processing unit), or a dedicated processor specialized for specific processing. The dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application specific integrated circuit). The control unit 11 executes processes related to the operation of the information processing device 10 while controlling each part of the information processing device 10.

[0019] The storage unit 12 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The semiconductor memory is, for example, a RAM (random access memory) or a ROM (read only memory). The RAM is, for example, an SRAM (static random access memory) or a DRAM (dynamic random access memory). The ROM is, for example, an EEPROM (electrically erasable programmable read only memory). The storage unit 12 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores data used for the operation of the information processing device 10 and data obtained by the operation of the information processing device 10.

[0020] Specifically, for example, the memory unit 12 may store a database of a predetermined object. The database of a predetermined object may include dictionary data such as the name, technical terms, descriptions, and manuals related to the predetermined object. The dictionary data may include detailed definitions of terms specific to a particular industry or technology field, as well as lists of related abbreviations, synonyms, and related terms. The dictionary data may also include usage examples, context, and scope of application for each term. This allows for the efficient provision of accurate information. More specifically, if the predetermined object is a specific vehicle, the database may include the name, model, installed engine, electric motor, fuel efficiency, vehicle size, weight, installed functions, optional parts, and other key specifications related to the vehicle. In this case, the database may also include detailed information such as the seat arrangement inside the vehicle, the level of autonomous driving technology, sensor technology, battery type, capacity, operation manual, and maintenance manual. The database of a predetermined object may be updated regularly in accordance with technological innovations and industry trends, and may reflect the latest technologies and industry standards. By utilizing such a database, a foundation for smooth communication can be provided.

[0021] The input unit 13 includes at least one input interface. The input interface may be, for example, a physical key, a capacitive key, a pointing device, or a touchscreen integrated with a display. Alternatively, the input interface may be, for example, a sound sensor that accepts voice input, or a camera that accepts gesture input. The input unit 13 accepts operations to input data used for the operation of the information processing device 10. Instead of being integrated into the information processing device 10, the input unit 13 may be connected to the information processing device 10 as an external input device. Any connection method can be used, for example, USB (Universal Serial Bus), HDMI (registered trademark) (High-Definition Multimedia Interface), or Bluetooth (registered trademark).

[0022] The output unit 14 includes at least one output interface. The output interface is, for example, a display that outputs information as video, or a speaker that outputs information as sound. The display is, for example, an LCD (liquid crystal display) or an organic EL (electroluminescence) display. The output unit 14 outputs data obtained by the operation of the information processing device 10. Instead of being provided in the information processing device 10, the output unit 14 may be connected to the information processing device 10 as an external output device. Any connection method can be used, for example, USB, HDMI (registered trademark), or Bluetooth (registered trademark).

[0023] The communication unit 15 includes at least one external communication interface. The communication interface may be either a wired or wireless communication interface. In the case of wired communication, the communication interface may be, for example, a LAN (Local Area Network) interface or a USB (Universal Serial Bus) interface. In the case of wireless communication, the communication interface may be, for example, an interface compatible with mobile communication standards such as LTE (Long Term Evolution), 4G (4th generation), or 5G (5th generation), or an interface compatible with short-range wireless communication such as Bluetooth (registered trademark). The communication unit 15 receives data used for the operation of the information processing device 10 and transmits data obtained by the operation of the information processing device 10.

[0024] The functions of the information processing device 10 are realized by executing the program according to this embodiment on a processor corresponding to the control unit 11. In other words, the functions of the information processing device 10 are realized by software. The program causes the computer to perform the operations of the information processing device 10, thereby causing the computer to function as the information processing device 10. That is, the computer functions as the information processing device 10 by performing the operations of the information processing device 10 according to the program.

[0025] In this embodiment, the program can be recorded on a computer-readable recording medium. The computer-readable recording medium includes non-temporary computer-readable media, such as magnetic recording devices, optical discs, magneto-optical recording media, or semiconductor memory. The program can be distributed, for example, by selling, transferring, or lending portable recording media such as DVDs (digital versatile discs) or CD-ROMs (compact disc read-only memory) on which the program is recorded. Alternatively, the program may be distributed by storing it on the storage of an external server and transmitting it from the external server to other computers. The program may also be provided as a program product.

[0026] Some or all of the functions of the information processing device 10 may be implemented by a dedicated circuit corresponding to the control unit 11. In other words, some or all of the functions of the information processing device 10 may be implemented by hardware.

[0027] (Configuration of server device 20) As shown in Figure 1, the server device 20 comprises a control unit 21, a storage unit 22, an input unit 23, an output unit 24, and a communication unit 25.

[0028] The control unit 21 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or GPU (graphics processing unit), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application-specific integrated circuit). The control unit 21 controls each part of the server device 20 and executes processes related to the operation of the server device 20.

[0029] The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or at least two combinations thereof. The semiconductor memory is, for example, RAM (random access memory) or ROM (read-only memory). The RAM is, for example, SRAM (static random access memory) or DRAM (dynamic random access memory). The ROM is, for example, EEPROM (electrically erasable programmable read-only memory). The storage unit 22 functions, for example, as main memory, auxiliary memory, or cache memory. The storage unit 22 stores data used for the operation of the server device 20 and data obtained by the operation of the server device 20.

[0030] The input unit 23 includes at least one input interface. The input interface may be, for example, a physical key, a capacitive key, a pointing device, or a touchscreen integrated with a display. Alternatively, the input interface may be, for example, a sound sensor that accepts voice input, or a camera that accepts gesture input. The input unit 23 accepts operations to input data used for the operation of the server device 20. Instead of being provided in the server device 20, the input unit 23 may be connected to the server device 20 as an external input device. Any connection method can be used, for example, USB (Universal Serial Bus), HDMI (registered trademark) (High-Definition Multimedia Interface), or Bluetooth (registered trademark).

[0031] The output unit 24 includes at least one output interface. The output interface is, for example, a display that outputs information as video, or a speaker that outputs information as sound. The display is, for example, an LCD (liquid crystal display) or an organic EL (electroluminescence) display. The output unit 24 outputs data obtained by the operation of the server device 20. Instead of being provided in the server device 20, the output unit 24 may be connected to the server device 20 as an external output device. Any connection method can be used, for example, USB, HDMI (registered trademark), or Bluetooth (registered trademark).

[0032] The communication unit 25 includes at least one external communication interface. The communication interface may be either a wired or wireless communication interface. In the case of wired communication, the communication interface may be, for example, a LAN (Local Area Network) interface or a USB (Universal Serial Bus) interface. In the case of wireless communication, the communication interface may be, for example, an interface compatible with mobile communication standards such as LTE (Long Term Evolution), 4G (4th generation), or 5G (5th generation), or an interface compatible with short-range wireless communication such as Bluetooth (registered trademark). The communication unit 25 receives data used for the operation of the server device 20 and transmits data obtained by the operation of the server device 20.

[0033] The functions of the server device 20 are realized by executing the program according to this embodiment on a processor corresponding to the control unit 21. In other words, the functions of the server device 20 are realized by software. The program causes the computer to perform the operations of the server device 20, thereby causing the computer to function as the server device 20. That is, the computer functions as the server device 20 by performing the operations of the server device 20 according to the program.

[0034] Some or all of the functions of the server device 20 may be implemented by a dedicated circuit corresponding to the control unit 21. In other words, some or all of the functions of the server device 20 may be implemented by hardware.

[0035] (Operation of the information processing device 10) Referring to Figure 2, the operation of the information processing device 10 according to this embodiment will be described. Here, we will mainly describe an example in which the audio data is audio data of a business negotiation related to vehicle sales, and the predetermined object is a specific vehicle.

[0036] Step S10: The control unit 11 of the information processing device 10 determines a topic based on audio data relating to a predetermined object (in this case, a specific vehicle) and a database relating to the predetermined object.

[0037] Any method can be used for acquiring audio data. For example, the control unit 11 may acquire audio data from an external device via the communication unit 15 and the network 30. Alternatively, the control unit 11 may acquire audio data via the input unit 13.

[0038] Any method can be used for topic determination. For example, machine learning algorithms and natural language processing (NLP) techniques may be used for topic determination. For instance, the control unit 11 may analyze keywords contained in the audio data, conversation content based on the audio data, etc., in real time using a database of predetermined objects, and determine the topic for each period of the audio data based on the analysis results. Specifically, the control unit 11 can extract characteristic words and phrases from the audio data and determine the topic by considering their frequency of occurrence and context. A pre-trained topic model (e.g., Latent Dirichlet Allocation, BERT, etc.) may be used for topic determination.

[0039] Step S20: The control unit 11 extracts a question sentence from the audio data and generates a supplementary question sentence based on the question sentence and the topic during the period in which the question sentence was extracted. Any method can be used for the question sentence extraction process. The topic during the period in which the question sentence was extracted is identified based on the period in the audio data in which the question sentence was extracted and the topic determined in step S10.

[0040] Any method can be used for generating supplementary questions. For example, the control unit 11 may generate supplementary questions by determining the interpretation of terms in the question (demonstrative pronouns, specific terms, etc.) based on the terms in the question and the topic during the period in which the question was extracted (specific vehicle, model, function, optional parts, etc.). In other words, the control unit 11 reconstructs the question into a clearer form by supplementing specific content in question sentences that use demonstrative pronouns, ambiguous expressions, etc., by referring to the topic, the flow of the conversation, etc. Specifically, for example, if the question is "What is the fuel efficiency of this?", the control unit 11 may determine that "this" in the question is specific vehicle model A, based on the topic during the period in which the question was extracted. Based on this determination, the control unit 11 may generate the supplementary question "What is the fuel efficiency of specific vehicle model A?". Furthermore, speaker attribute data of the audio data may be used in the supplementary question generation process. The speaker of the audio data may be, for example, a customer or a sales staff member. In other words, customer attribute data, sales staff attribute data, etc., may be used in the process of generating supplementary questions. Customer attribute data, sales staff attribute data, etc., may be stored in, for example, the storage unit 12, and the control unit 11 may generate supplementary questions by referring to the customer attribute data, sales staff attribute data, etc., in the storage unit 12.

[0041] Step S30: The control unit 11 outputs an answer corresponding to the supplementary question.

[0042] The answer corresponding to the supplementary question can be generated in any way. For example, the control unit 11 sends a prompt containing the supplementary question to the server device 20 via the communication unit 15 and inputs the prompt into the language model of the server device 20. The language model of the server device 20 outputs an answer corresponding to the prompt. The control unit 11 retrieves the answer via the communication unit 15. In this way, the control unit 11 may generate the answer corresponding to the supplementary question using the language model of the server device 20. The answer corresponding to the supplementary question may also be generated by referring to customer data. For example, if the content of the supplementary question is a question about the size of the customer's parking space, the control unit 11 may also generate the answer based on customer data such as purchase history data and address data.

[0043] Any method can be used for processing the output of the response. For example, the control unit 11 may output the response via a user interface displayed by the output unit 14.

[0044] As described above, the information processing device 10 according to this embodiment determines a topic based on audio data relating to a predetermined object and a database relating to that predetermined object. The information processing device 10 also extracts a question sentence from the audio data and generates a supplementary question sentence based on the question sentence and the topic during the period in which the question sentence was extracted. The information processing device 10 then outputs an answer corresponding to the supplementary question sentence. More specifically, for example, during a sales negotiation for a specific vehicle model A, even if the utterance "What is the fuel efficiency of this?" from a customer is extracted, if the context is not understood, the object referred to by the demonstrative pronoun "this" is unclear, and an answer of "the fuel efficiency of specific vehicle model A" cannot be obtained. Therefore, with the above configuration, the information processing device 10 according to this embodiment can generate "What is the fuel efficiency of specific vehicle model A?" as a supplementary question sentence and output an answer corresponding to the supplementary question sentence.

[0045] In this way, the information processing device 10 determines the topic, and based on the determined topic, it automatically generates and outputs answers by supplementing the questions in the conversation. As a result, supplementary questions that take into account the flow of the conversation are generated, and answers to those supplementary questions are obtained, thus improving the dialogue support technology.

[0046] While this disclosure has been described based on the drawings and embodiments, it should be noted that those skilled in the art may make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions, etc., included in each component or step can be rearranged in a logically consistent manner, and multiple components or steps can be combined into one or divided into two.

[0047] For example, in step S30 above, the control unit 11 outputs a response corresponding to the supplementary question, but this is not limited to this. For example, the control unit 11 may output the supplementary question instead of a response corresponding to the supplementary question. This allows for the output of a supplementary question that takes the flow of the conversation into consideration, and is expected to support the smooth progress of the conversation even when the question is ambiguous.

[0048] Furthermore, in the embodiment described above, it is also possible to have an embodiment in which the configuration and operation of the information processing device 10 are distributed among multiple computers, including a server device 20, that are able to communicate with each other.

[0049] For example, the information processing device 10 may also perform a switching process to determine whether or not to generate a supplementary question and output an answer corresponding to the supplementary question. Specific examples of the switching process are described below as Modification 1 to Modification 4.

[0050] (Variation 1) For example, the control unit 11 of the information processing device 10 may generate supplementary question sentences based on the number of times the sales staff has been asked questions in past sales negotiations, and output answers corresponding to the supplementary question sentences. Figure 3 illustrates the operation of the information processing device 10 according to Modification 1.

[0051] Step S110: The control unit 11 of the information processing device 10 determines the topic of a business negotiation based on the audio data of the negotiation for the sale of a predetermined item and a database relating to the predetermined item. The process of acquiring the audio data and determining the topic can be carried out using any method, similar to the method described above in step S10.

[0052] Step S120: The control unit 11 extracts the question sentence from the audio data. Any method can be used for the question sentence extraction process.

[0053] Step S130: The control unit 11 determines whether the question was asked by the customer. Any method can be used for this determination process. For example, the control unit 11 may determine whether the question was asked by the customer based on features related to the voice data (voice quality, pitch, speaking speed, etc.). A machine learning model may also be applied in this determination process. If the question was asked by the customer, the process proceeds to step S140. On the other hand, if the question was not asked by the customer, the process terminates.

[0054] Step S140: The control unit 11 determines whether the number of questions previously asked by the sales staff that are identical to questions asked by the customer is less than a predetermined number. Any method can be used for this determination process. For example, the control unit 11 may refer to a database that stores historical information of questions received by each sales staff member and perform this determination process. This database may be stored, for example, in the storage unit 12. If the number of questions previously asked by the sales staff member that are identical to questions asked by the customer is less than a predetermined number, the process proceeds to step S150. On the other hand, if the number of questions previously asked by the sales staff member that are identical to questions asked by the customer is not less than a predetermined number, the process terminates.

[0055] Step S150: The control unit 11 generates a supplementary question based on the question and the topic during the period in which the question was extracted. The topic during the period in which the question was extracted is identified in the audio data based on the period in which the question was extracted and the topic determined in step S110.

[0056] Step S160: The control unit 11 outputs an answer corresponding to the supplementary question. The process of obtaining the answer corresponding to the supplementary question and the process of outputting the answer can be carried out using any method, similar to the method described in step S10.

[0057] Thus, in Modification 1, if the question is one asked by a customer during a business negotiation, the control unit 11 determines whether the number of times the negotiation staff has been asked the same question in the past is less than a predetermined number. If the control unit 11 determines that the number of times the negotiation staff has been asked the same question in the past is less than a predetermined number, it generates a supplementary question and outputs an answer corresponding to the supplementary question. On the other hand, if the control unit 11 determines that the number of times the negotiation staff has been asked the same question in the past is greater than or equal to a predetermined number, it does not generate a supplementary question and does not output an answer corresponding to the supplementary question. In this way, for questions that the negotiation staff have little experience answering in past business negotiations, an answer corresponding to the question is output. Furthermore, for questions that the negotiation staff have a lot of experience answering in past business negotiations, the answer corresponding to the question is omitted, which reduces the processing load of calculation processing, communication processing, etc. by the information processing device 10 and improves the convenience of this technology.

[0058] (Modification 2) For example, in Modification 2, the control unit 11 of the information processing device 10 may generate supplementary questions based on the time required for the sales staff to respond, and output answers corresponding to the supplementary questions. Figure 4 illustrates the operation of the information processing device 10 according to Modification 2. The same reference numerals are used for operations that are the same as in Modification 1, and their explanations are omitted.

[0059] Step S141: The control unit 11 of the information processing device 10 determines whether the sales staff has started to respond within a predetermined time after the question has been spoken. The predetermined time may be set as appropriate, for example, 3 seconds. The predetermined time may also be set to a different value for each sales staff member. If the sales staff has started to respond within the predetermined time after the question has been spoken, the process ends. On the other hand, if the sales staff has not started to respond within the predetermined time after the question has been spoken, the process proceeds to step S150.

[0060] Thus, in Modification 2, when the question is a question posed by a customer during a business negotiation, the control unit 11 determines whether the negotiation staff has started to respond within a predetermined time after the question was uttered. If it determines that the negotiation staff has not started to respond within a predetermined time after the question was uttered, the control unit 11 generates a supplementary question and outputs the answer corresponding to the supplementary question. On the other hand, if it determines that the negotiation staff has started to respond within a predetermined time after the question was uttered, the control unit 11 does not generate a supplementary question and does not output the answer corresponding to the supplementary question. In this way, for questions that the negotiation staff cannot answer immediately, the answer corresponding to the question is output. Furthermore, for questions that the negotiation staff can answer immediately, the answer corresponding to the question is omitted, which reduces the processing load on the information processing device 10, such as calculation processing and communication processing, and improves the convenience of this technology.

[0061] (Variation 3) For example, in Modification 3, the control unit 11 of the information processing device 10 may generate supplementary questions based on the tension level of the sales staff and output answers corresponding to the supplementary questions. Figure 5 illustrates the operation of the information processing device 10 according to Modification 3. The same reference numerals are used for operations that are the same as in Modification 1, and their explanations are omitted.

[0062] Step S142: The control unit 11 of the information processing device 10 determines whether the tension level of the sales staff during the period in which the question was extracted is above a predetermined value. The tension level of the sales staff during the period in which the question was extracted may be estimated as appropriate by emotion estimation processing, etc. Face image data of the sales staff may be used in the emotion estimation processing. In this case, the control unit 11 may acquire face image data of the sales staff during the negotiation, for example, taken by an external camera, and estimate the tension level of the sales staff based on said face image data. The predetermined value for tension level may be set as appropriate. The predetermined value may also be set to a different value for each sales staff member. Note that the tension level may also be estimated by methods other than emotion estimation processing. For example, the tension level may be estimated by pulse rate, respiratory rate, body temperature, pupil dilation, etc. If the tension level of the sales staff during the period in which the question was extracted is above a predetermined value, the process proceeds to step S150. On the other hand, if the tension level of the sales staff during the period in which the question was extracted is not above a predetermined value, the process ends.

[0063] Thus, in Modification 3, when the question is a question posed by a customer during a business negotiation, the control unit 11 determines whether the tension level of the negotiation staff during the period in which the question was extracted is above a predetermined value. If it is determined that the tension level of the negotiation staff during the period in which the question was extracted is above a predetermined value, the control unit 11 generates a supplementary question and outputs an answer corresponding to the supplementary question. On the other hand, if it is determined that the tension level of the negotiation staff during the period in which the question was extracted is not above a predetermined value, the control unit 11 does not generate a supplementary question and does not output an answer corresponding to the supplementary question. In this way, for questions that the negotiation staff cannot answer due to confusion or other reasons and high tension, an answer corresponding to the question is output. Furthermore, for questions that the negotiation staff can answer without confusion, the answer corresponding to the question is omitted, which reduces the processing load of calculation processing, communication processing, etc. by the information processing device 10 and improves the convenience of this technology.

[0064] (Modification 4) For example, sales staff may ask questions to customers. These questions may be difficult for customers to answer. Therefore, as in Modification 4, supplementary questions corresponding to the sales staff's questions may be generated. Figure 6 illustrates the operation of the information processing device 10 according to Modification 4. The same reference numerals are used for operations identical to those in Modification 1, and their explanations are omitted.

[0065] Step S133: The control unit 11 determines whether the question was asked by the sales staff. Any method can be used for this determination process. For example, the control unit 11 may determine whether the question was asked by the sales staff based on features related to the voice data (voice quality, pitch, speaking speed, etc.). A machine learning model may also be applied in this determination process. If the question was asked by the sales staff, the process proceeds to step S140. On the other hand, if the question was not asked by the sales staff, the process terminates.

[0066] Step S143: The control unit 11 of the information processing device 10 determines whether the customer has started to respond within a predetermined time after the question has been spoken. The predetermined time may be set as appropriate, for example, 3 seconds. The predetermined time may also be set to a different value for each customer. If the customer has started to respond within the predetermined time after the question has been spoken, the process ends. On the other hand, if the customer has not started to respond within the predetermined time after the question has been spoken, the process proceeds to step S150.

[0067] As described above, in Modification 4, when the question is a question posed by a sales staff member during a business negotiation, the control unit 11 determines whether the customer has started to respond within a predetermined time after the question was uttered. If it is determined that the customer has not started to respond within a predetermined time after the question was uttered, the control unit 11 generates a supplementary question and outputs an answer corresponding to the supplementary question. On the other hand, if it is determined that the customer has started to respond within a predetermined time after the question was uttered, the control unit 11 does not generate a supplementary question and does not output an answer corresponding to the supplementary question. In this way, for questions that the customer cannot answer immediately, an answer corresponding to the question is output. This allows the sales staff member to smoothly advance the business negotiation by presenting the outputted answer to the question as an example answer to the customer, or by changing the way the question is asked. On the other hand, for questions that the customer can answer immediately, the answer corresponding to the question is omitted, which reduces the processing load on the information processing device 10, such as calculation processing and communication processing, and improves the convenience of this technology. Furthermore, if the question is one posed by a sales staff member during a sales negotiation, the supplementary question may be presented in step S160 instead of the corresponding answer. Based on the supplementary question, the sales staff member can modify the question to the customer and change the way it is asked, thereby facilitating the sales negotiation.

[0068] In step S133, the process terminates if the question is not posed by the sales staff, but this is not limited to that case. In this case, since the question is posed by the customer, the control unit 11 may appropriately generate a supplementary question and output an answer corresponding to the supplementary question.

[0069] Some embodiments of the present disclosure are described below. However, it should be noted that the embodiments of the present disclosure are not limited to these. [Note 1] A method for providing dialogue support that is performed by an information processing device, Determining a topic based on audio data relating to a specified object and a database relating to the said specified object, The process involves extracting question sentences from the audio data, generating supplementary question sentences based on the question sentences and the topics during the period in which the question sentences were extracted, Outputting the answer corresponding to the aforementioned supplementary question, A dialogue support method that includes this. [Note 2] The dialogue support method described in Appendix 1, Outputting the aforementioned answer includes outputting the answer obtained by inputting the aforementioned supplementary question sentence into a language model. [Note 3] A dialogue support method described in Appendix 1 or Appendix 2, The aforementioned audio data is audio data from a business negotiation to sell the aforementioned specified item. [Note 4] The dialogue support method described in Appendix 3, The aforementioned question is a question asked by the customer during the aforementioned business negotiation, and the negotiation staff determines whether the number of times they have received the same question in the past is less than a predetermined number. If the sales staff member determines that the number of times they have been asked the same question in the past is less than the predetermined number, the system generates a supplementary question and outputs an answer corresponding to the supplementary question. A dialogue support method that, if it is determined that the number of times the sales staff member has received the same question in the past exceeds a predetermined number, does not generate the supplementary question sentence and does not output the answer corresponding to the supplementary question sentence. [Note 5] The dialogue support method described in Appendix 3, The aforementioned question is a question posed by the customer during the business negotiation, and it is determined whether the negotiation staff began to respond within a predetermined time after the question was uttered. If it is determined that the sales staff has not started responding within the predetermined time, the system generates the supplementary question and outputs the corresponding answer. A dialogue support method that, if it is determined that the sales staff has started to respond within the predetermined time, does not generate the supplementary question sentence and does not output the answer corresponding to the supplementary question sentence. [Note 6] The dialogue support method described in Appendix 3, The aforementioned questions are questions posed by the customer during the aforementioned business negotiation, and the level of tension of the negotiation staff during the period in which the aforementioned questions were extracted is estimated. If the tension level is above a threshold, the system generates the supplementary question and outputs the answer corresponding to the supplementary question. A dialogue support method that, when the level of tension is below a threshold, does not generate the supplementary question sentence and does not output an answer corresponding to the supplementary question sentence. [Note 7] The dialogue support method described in Appendix 3, The aforementioned question is a question posed by the sales staff, and it is determined whether or not the customer in the sales negotiation provided a corresponding answer within a predetermined time after the question was uttered. If it is determined that the customer has not provided a response within the predetermined time, the system generates a supplementary question and outputs a response corresponding to the supplementary question. A dialogue support method that, if it is determined that the customer has provided a response within the predetermined time, does not generate a supplementary question and does not output a response corresponding to the supplementary question. [Note 8] An information processing device comprising a control unit, The control unit, Based on audio data relating to a specified object and a database relating to the said specified object, the topic is determined. The system extracts a question from the audio data, generates a supplementary question based on the question and the topic during the period in which the question was extracted, An information processing device that outputs an answer corresponding to the aforementioned supplementary question. [Note 9] On the computer, Determining a topic based on audio data relating to a specified object and a database relating to the said specified object, The process involves extracting question sentences from the audio data, generating supplementary question sentences based on the question sentences and the topics during the period in which the question sentences were extracted, Outputting the answer corresponding to the aforementioned supplementary question, A program that executes the command. [Explanation of Symbols]

[0070] 10 Information Processing Devices 11 Control Unit 12 Storage section 13 Input section 14 Output section 15 Communications Department 20 Terminal devices 21 Control Unit 22 Memory section 23 Input section 24 Output section 25 Communications Department 30 Networks

Claims

1. A method for providing dialogue support that is performed by an information processing device, Determining a topic based on audio data relating to a specified object and a database relating to the said specified object, The process involves extracting question sentences from the audio data, generating supplementary question sentences based on the question sentences and the topics during the period in which the question sentences were extracted, Outputting the answer corresponding to the aforementioned supplementary question, A dialogue support method that includes this.

2. A dialogue support method according to claim 1, Outputting the aforementioned answer includes outputting the answer obtained by inputting the aforementioned supplementary question sentence into a language model.

3. A dialogue support method according to claim 1, A dialogue support method wherein the aforementioned audio data is audio data from a business negotiation for selling the aforementioned specified goods.

4. A dialogue support method according to claim 3, The aforementioned question is a question asked by the customer during the aforementioned business negotiation, and the negotiation staff determines whether the number of times they have received the same question in the past is less than a predetermined number. If the sales staff member determines that the number of times they have been asked the same question in the past is less than the predetermined number, the system generates a supplementary question and outputs an answer corresponding to the supplementary question. A dialogue support method that, if it is determined that the number of times the sales staff member has received the same question in the past exceeds a predetermined number, does not generate the supplementary question sentence and does not output the answer corresponding to the supplementary question sentence.

5. A dialogue support method according to claim 3, The aforementioned question is a question posed by the customer during the business negotiation, and it is determined whether the negotiation staff began to respond within a predetermined time after the question was uttered. If it is determined that the sales staff has not started responding within the predetermined time, the system generates the supplementary question and outputs the corresponding answer. A dialogue support method that, if it is determined that the sales staff has started to respond within the predetermined time, does not generate the supplementary question sentence and does not output the answer corresponding to the supplementary question sentence.

6. A dialogue support method according to claim 3, The aforementioned questions are questions posed by the customer during the aforementioned business negotiation, and the level of tension of the negotiation staff during the period in which the aforementioned questions were extracted is estimated. If the tension level is above a threshold, the system generates the supplementary question and outputs the answer corresponding to the supplementary question. A dialogue support method that, when the level of tension is below a threshold, does not generate the supplementary question sentence and does not output an answer corresponding to the supplementary question sentence.

7. A dialogue support method according to claim 3, The aforementioned question is a question posed by the sales staff, and it is determined whether or not the customer in the sales negotiation provided a corresponding answer within a predetermined time after the question was uttered. If it is determined that the customer has not provided a response within the predetermined time, the system generates a supplementary question and outputs a response corresponding to the supplementary question. A dialogue support method that, if it is determined that the customer has provided a response within the predetermined time, does not generate a supplementary question and does not output a response corresponding to the supplementary question.

8. An information processing device comprising a control unit, The control unit, Based on audio data relating to a specified object and a database relating to the said specified object, the topic is determined. The system extracts a question from the audio data, generates a supplementary question based on the question and the topic during the period in which the question was extracted, An information processing device that outputs an answer corresponding to the aforementioned supplementary question.

9. On the computer, Determining a topic based on audio data relating to a specified object and a database relating to the said specified object, The process involves extracting question sentences from the audio data, generating supplementary question sentences based on the question sentences and the topics during the period in which the question sentences were extracted, Outputting the answer corresponding to the aforementioned supplementary question, A program that executes the command.

Images