Data processing apparatus, data processing method, and program

Abstract

To provide a data processing apparatus, a data processing method, and a program capable of improving the accuracy of role-playing training.SOLUTION: A data processing apparatus includes: a processing unit which performs specific processing using a data generative model capable of generating a sentence according to input content; and a setting unit which generates the input content based on information on an imaginary company. The processing unit is configured to perform role-playing, as the specific processing, of a person in charge in the imaginary company, for a predetermined approach, using an output of the data generative model which receives, as the input content, the talks for making a predetermined approach to the person in charge in the imaginary company.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The technology disclosed herein relates to a data processing device, a data processing method, and a program. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is a known method for training a user to approach a fictitious company by role-playing with a chatbot. However, the conventional technique has room for improvement in terms of improving the accuracy of the role-playing training. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein includes a processing unit that performs specific processing using a data generation model capable of generating sentences according to input content, and a setting unit that generates the input content based on information about a fictitious company, and the processing unit performs specific processing by role-playing the person in charge of the fictitious company in response to the specific approach using the output of the data generation model when the input content is a talk for making a specific approach to a person in charge of the fictitious company.

[0006] A second aspect of the technology disclosed herein is a data processing method including a processing step in which a processor performs specific processing using a data generation model capable of generating sentences according to input content, and a setting step in which the input content is generated based on information about a fictitious company, and in the processing step, the processor uses the output of the data generation model when the input content is a talk for making a specific approach to a person in the fictitious company, to perform role-playing of the person in the fictitious company in response to the specific approach as a specific process.

[0007] A third aspect of the technology disclosed herein is a program for causing a computer to execute a process including a processing step of performing specific processing using a data generation model capable of generating sentences according to input content, and a setting step of generating the input content based on information about a fictitious company, in which the processing step includes performing role-playing of a person in charge of the fictitious company in response to the specific approach using output from the data generation model when the input content is a talk for making a specific approach to a person in charge of the fictitious company. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Diagram 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a smart device. [Diagram 3] The outline of the specific process is shown below. [Figure 4]2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Diagram 5] 13 is an example of a display mode displayed on a terminal device during a sales role-play. [Figure 6] 13 illustrates an example of an operational flow of pre-processing by a data processing device. [Figure 7] 1 is an example of a prompt generated by a data processing device and an output of a data generation model. [Figure 8] 1 is an example of a prompt generated by a data processing device and an output of a data generation model. [Figure 9] 13 illustrates an example of an operational flow of a specific process performed by a data processing device. [Figure 10] 1 is an example of a prompt generated by a data processing device. [Figure 11] 1 is an example of a prompt generated by a data processing device and an output of a data generation model. [Figure 12] 1 is an example of a prompt generated by a data processing device and an output of a data generation model. [Figure 13] 13 is an example of an output of an evaluation result by the data processing device. [Figure 14] 13 illustrates an example of an operational flow of a reception and output process by a terminal device. [Figure 15] 13 is an example of output of evaluation results by a data processing device and manually. [Figure 16A] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 16B] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0017] As shown in Fig. 1, a data processing system 10 includes a data processing device 12 and a terminal device 14. An example of the data processing device 12 is a server. An example of the terminal device 14 is a personal computer such as a laptop or desktop computer, or a smart device such as a smartphone or smart glasses. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0019] The terminal device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression that the person 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the terminal device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 60. The data generation model 58 and the emotion identification model 60 are used by the identification processing unit 290.

[0026] In the terminal device 14, the reception output processing is performed by the processor 46. A reception output program 62 is stored in the storage 50. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 62 from the storage 50, and executes the read reception output program 62 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0027] Next, we will explain the processing of the specific processing unit 290 when the data processing device 12 uses the data generation model 58 to become a representative of a fictitious company and performs specific processing as a sales role-play in which the user operating the terminal device 14 makes sales as a specified approach.

[0028] As training for salespeople to sell to companies, a salesperson is set as a person in a fictitious company and role-playing is performed with the person in the fictitious company. In the identification process in this embodiment, as shown in Fig. 3, a salesperson who is a user of the terminal device 14 performs a sales role-play using the output of the data generation model 58. Fig. 3 is a schematic diagram showing a sales role-play being performed between a salesperson 310 and a person in charge 324 of a fictitious company 320.

[0029] As the fictitious company 320, first information 322_1 and second information 322_2 regarding the fictitious company 320 are set. The first information 322_1 is information that is less difficult for other companies to know than the second information 322_2. Examples of the first information 322_1 include the company name, the number of employees, annual turnover, details of the business overview, and the latest news. On the other hand, the second information 322_2 is information that is more difficult for other companies to know than the first information 322_1. Examples of the second information 322_2 include business issues. Note that the types of information that the first information 322_1 and the second information 322_2 are may be determined in advance or may be set by the user.

[0030] 3, of the first information 322_1 and the second information 322_2, only the first information 322_1 is presented to the sales representative 310. The sales representative 310, who is the user of the terminal device 14, refers to the first information 322_1 and performs a sales role play in which the sales representative 310 makes sales to a person in charge 324 of a fictitious company 320.

[0031] The data processing device 12 sets the first information 322_1 and the second information 322_2 related to the fictitious company 320, and further performs a sales role-play as a person in charge 324 of the fictitious company 320 using the data generation model 58.

[0032] When the sales representative 310 actually does sales, the sales representative 310 generally knows only a part of the information about the company to which the sales representative 310 is selling. However, the person in charge of the company that receives sales from the sales representative 310 responds to the sales representative 310 based on information that the sales representative 310 does not know. In contrast, as described above, in the sales role-playing provided by the specification process of this embodiment, only the first information 322_1 of the first information 322_1 and the second information 322_2 set for the fictitious company 320 is presented to the sales representative 310. On the other hand, the person in charge 324 of the fictitious company 320 receives sales from the sales representative 310 based on the first information 322_1 and the second information 322_2. Therefore, in the sales role-playing provided by the specification process of this embodiment, the sales role-playing can be performed under conditions that are closer to the actual situation, and therefore the accuracy of training by the sales role-playing can be improved.

[0033] The second information 322_2 is not information that is never presented to the sales representative 310, but may be disclosed to the sales representative 310 depending on sales talk or the like.

[0034] As shown in FIG. 4, the specific processing unit 290 includes an input unit 292, a setting unit 293, a processing unit 294, a memory control unit 295, and an output unit 296.

[0035] The input unit 292 acquires user input received by the terminal device 14. Specifically, it acquires user voice input received by the terminal device 14. User input such as "Please set information about a fictitious company," "Please become a person in charge of a fictitious company and perform a sales role-play," and "Please output the evaluation results of the sales role-play" are sent from the terminal device 14 to the data processing device 12.

[0036] The setting unit 293 sets information about the fictitious company 320 using the data generation model 58 as a pre-processing before the processing unit 294 starts the sales role-play. Specifically, when the setting unit 293 receives a start instruction from the terminal device 14, the setting unit 293 generates a prompt for setting information about the fictitious company 320 as a pre-processing, and sets information about the fictitious company 320 based on the output of the data generation model 58 obtained by inputting the generated prompt. The setting unit 293 of this embodiment sets the first information 322_1 and the second information 322_2 as described above. Of the set first information 322_1 and second information 322_2, the first information 322_1 is transmitted to the terminal device 14. In the terminal device 14, the first information 322_1 is presented to the user of the terminal device 14 before the sales role-playing is started.

[0037] The processing unit 294 performs specific processing using the data generation model 58 .

[0038] Specifically, the processing unit 294 determines whether or not a predetermined trigger condition is satisfied. More specifically, the trigger condition is that the input unit 292 acquires a voice input of the user received by the terminal device 14 after the setting unit 293 performs pre-processing and sets the first information 322_1 and the second information 322_2.

[0039] Then, when the trigger condition is satisfied, the processing unit 294 inputs text representing an instruction for obtaining data for a specific process to the data generation model 58, and acquires a processing result based on the output of the data generation model 58. More specifically, the processing unit 294 inputs an instruction for performing a sales role-play as the person in charge 324 of the fictitious company 320 set by the setting unit 293, and a voice input related to the user's sales talk input from the terminal device 14, to the data generation model 58, and acquires the output of the data generation model 58. The data processing device 12 transmits the output of the data generation model 58 to the terminal device 14, and the processing unit 294 performs a sales role-play with the user of the terminal device 14. The processing unit 294 also outputs an emotion parameter for each output for the sales talk.

[0040] Furthermore, after the sales role-playing is completed, the processing unit 294 inputs text inquiring about the evaluation results of the sales role-playing into the data generation model 58, and also performs an evaluation process to evaluate the sales role-playing based on the output of the data generation model 58.

[0041] The processing unit 294 may estimate the user's emotion using the emotion identification model 60 and perform identification processing using the user's emotion and the data generation model 58.

[0042] The storage control unit 295 controls the storage 32 to store the sales role-playing content, emotion parameters, and evaluation results in association with each other. Furthermore, the storage control unit 295 receives a user evaluation of the sales role-playing, and controls the storage 32 to store the sales role-playing content, emotion parameters, and evaluation results in association with each other.

[0043] The output unit 296 transmits the result of the specific processing to the terminal device 14. In the terminal device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0044] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0045] For example, when the trigger condition is satisfied, the processing unit 294 generates a prompt such as “Become a salesperson in a fictitious company and perform a sales role-play,” and inputs the generated prompt into the data generation model 58 .

[0046] Next, the operation of the data processing system 10 will be described.

[0047] First, prior to the description of the processing performed by each device, an example of a display mode displayed on the display 40A of the terminal device 14 during the execution of the sales role-play will be described with reference to FIG. 5. As shown in FIG. 5, the display 40A displays a first setting instruction information 330_1, a second setting instruction information 330_2, and a third setting instruction information 330_3 selected by the user when setting the fictitious company 320. In the example shown in FIG. 5, the first setting instruction information 330_1 is information for instructing the data processing device 12 to set the industry of the fictitious company 320, and shows a state in which "construction industry" has been selected by the user. The second setting instruction information 330_2 is information for instructing the data processing device 12 to set the annual turnover of the fictitious company 320, and shows a state in which "less than 10 billion yen" has been selected by the user. Furthermore, the third setting instruction information 330_3 is information for instructing the data processing device 12 to set the person in charge 324 of the fictitious company 320, and shows a state in which "Casual person in charge 8 (low difficulty)" has been selected by the user.

[0048] Also displayed on the display 40A are a start button 350, a voice input button 352, a send button 354, and an end button 356. After the user selects the first setting instruction information 330_1, the second setting instruction information 330_2, and the third setting instruction information 330_3, he or she operates the start button 350 to give an instruction to start the sales role-playing.

[0049] Also, the display 40A displays the first information 322_1 set by the setting unit 293 of the data processing device 12. The user of the terminal device 14 makes a sales talk by referring to the displayed first information 322_1. Specifically, the user operates the voice input button 352, and then speaks the sales talk into the microphone 38B. Furthermore, when the user operates the send button 354, the voice input of the sales talk is transmitted to the data processing device 12.

[0050] The data processing device 12 inputs a prompt corresponding to the voice input received by the terminal device 14 into the data generation model 58, and transmits the result of the specific processing to the terminal device 14. The terminal device 14 displays the result of the specific processing received from the data processing device 12 on the display 40A as output information 342 of the data processing device 12, as shown in FIG. 5A.

[0051] The series of processes of operating the voice input button 352 to input voice, operating the send button 354 to transmit the result of the specific processing to the data processing device 12, and displaying the result of the specific processing received from the data processing device 12 as output information 342 on the display 40A continues until the end button 356 is operated by the user.

[0052] Next, an example of the flow of pre-processing for setting information about a fictitious company 320, which is performed in the data processing device 12, will be described with reference to Fig. 6. Note that the flow of the pre-processing shown in Fig. 6 and the flow of the specification processing (see Fig. 9) described later are examples of the "data processing method" according to the technology of the present disclosure.

[0053] In the pre-processing shown in FIG. 6, first, in step S50, the input unit 292 acquires the above-mentioned first setting instruction information 330_1, second setting instruction information 330_2, and third setting instruction information 330_3 selected by the user on the terminal device 14.

[0054] In the next step S52, the setting unit 293 generates a prompt for setting the first information 322_1 related to the fictitious company 320.

[0055] In the next step S54, the setting unit 293 sets the first information 322_1 by using the data generation model 58. Specifically, the setting unit 293 inputs the prompt generated in step S52 to the data generation model 58 and acquires the output of the data generation model 58.

[0056] 7 shows an example of a prompt to be input to the data generation model 58 and an output of the data generation model 58 in response to the input. In the example shown in FIG. 7, the setting unit 293 generates a prompt saying "Please set and tell us information about a fictitious company according to the following conditions. The information to be set is the company name, annual sales, number of employees, detailed business overview, and latest news" and a prompt saying "Condition 1: The industry is construction. Condition 2: The annual sales is 10 billion yen or less" generated based on the first setting instruction information 330_1 and the second setting instruction information 330_2 acquired in step S50, and inputs them to the data generation model 58. Then, the setting unit 293 obtains an output from the data generation model 58 saying, "The set information is as follows. Company name: XX Co., Ltd. Number of employees: 200. Detailed business overview: We engage in building design and construction, civil engineering work, and renovation work. We provide high-quality buildings on time and at cost. Latest news: On August 1, 2023, we received an order for construction of a new public facility for a local government." and sets this as the first information 322_1.

[0057] In the next step S56, the output unit 296 outputs the first information 322_1 set in above step S54 to the terminal device 14.

[0058] In the next step S58, the setting unit 293 generates a prompt for setting the second information 322_2 related to the fictitious company 320.

[0059] In the next step S60, the setting unit 293 sets the second information 322_2 by using the data generation model 58. Specifically, the setting unit 293 inputs the prompt generated in step S58 to the data generation model 58 and acquires the output of the data generation model 58.

[0060] 8 shows an example of a prompt to be input to the data generation model 58 and an output of the data generation model 58 in response to the input. In the example shown in FIG. 8, the setting unit 293 generates a prompt saying, "Please set and tell us three more business issues for the fictitious company for which information has been set," and inputs it to the data generation model 58. Then, the setting unit 293 obtains an output from the data generation model 58 saying, "First: OO. Second: XX. Third: △△," and sets it as the second information 322_2. When the process of step S60 ends, the pre-processing shown in FIG. 6 ends.

[0061] Next, an example of the flow of specific processing performed by the data processing device 12 will be described with reference to FIG.

[0062] In the identification process shown in Fig. 9, first, in step S100, the identification processing unit 290 determines whether or not a trigger condition is satisfied. As described above, in the present embodiment, as an example, the trigger condition is that the input unit 292 acquires a user's voice input received by the terminal device 14 after the pre-processing shown in Fig. 6 is completed. If the trigger condition is not satisfied, the identification process shown in Fig. 9 is terminated. On the other hand, if the trigger condition is satisfied, the determination in step S100 is an affirmative determination, and the process proceeds to step S102.

[0063] In step S102, the processing unit 294 generates a prompt for starting the sales role-playing and inputs it to the data generation model 58. FIG. 10 shows an example of a prompt generated by the processing unit 294 and input to the data generation model 58. In the example shown in FIG. 10, the processing unit 294 generates a prompt for instructing to start the sales role-playing, "You will be an average person working at a fictitious company with a relatively low level of difficulty, and will role-play a sales job from me. Please continue the role-playing until I say, 'The role-playing is over.'" based on the third setting instruction information 330_3, and inputs it to the data generation model 58. The processing unit 294 also generates a prompt saying, "In the following conversations, you will behave as if you have the following five emotion parameters. Each parameter will vary throughout the conversation. In the following conversations, first output the current emotion parameters, and then output the conversation." and inputs it to the data generation model 58, thereby making it possible to obtain emotion parameters for each conversation. Furthermore, the processing unit 294 generates a prompt for instructing the format of the output form and inputs it to the data generation model 58 .

[0064] In the next step S104, the processing unit 294 determines whether or not the input unit 292 has acquired a voice input from the user accepted by the terminal device 14. If no voice input has been acquired, the determination in step S104 is negative, and the process proceeds to step S104. On the other hand, if a voice input has been acquired, the determination in step S104 is positive, and the process proceeds to step S106.

[0065] In step S106, the processor 294 generates a prompt based on the acquired voice input.

[0066] In the next step S108, the processing unit 294 acquires emotion parameters and conversation content using the data generation model 58. Specifically, the processing unit 294 inputs the prompt generated in step S106 to the data generation model 58, and acquires the output of the data generation model 58. FIG. 11 shows an example of a prompt that the processing unit 294 generates based on the acquired voice input and inputs to the data generation model 58. FIG. 11 also shows “Chatbot's current emotion parameters”, which are emotion parameters output from the data generation model 58 in response to the prompt, and “Conversation portion”, which is the conversation content.

[0067] In the next step S110, the processing unit 294 outputs the conversation content acquired in the above step S108. Note that, unlike this embodiment, the processing unit 294 may also acquire the acquired emotion parameters.

[0068] In the next step S112, the processing unit 294 determines whether or not to end the sales role-playing. Until the input unit 292 receives an end instruction as a result of the user operating the end button 356 on the terminal device 14, the determination in step S112 is negative, the process returns to step S104, and the processes in steps S104 to S110 are repeated. On the other hand, if the input unit 292 receives an end instruction, the determination in step S112 is positive, and the process proceeds to step S114.

[0069] In step S114, the processing unit 294 generates a prompt for outputting the evaluation result for the sales role-playing.

[0070] In the next step S116, the processing unit 294 obtains the evaluation result using the data generation model 58. Specifically, the processing unit 294 inputs the prompt generated in the above step S114 into the data generation model 58 and obtains the output of the data generation model 58. FIG. 12 shows an example of a prompt generated by the processing unit 294 to output the evaluation result for the sales role-playing and input to the data generation model 58. In the example shown in FIG. 12, prompts instructing "Overall evaluation" and "Feedback 1. Overall score, 2. Fluency of conversation, and 3. Logicality of conversation" are shown as the format of the output format of the evaluation result. Also, FIG. 12 shows an example of the evaluation result output from the data generation model 58 according to the format of the output format of the evaluation result. Note that the contents of the evaluation result, i.e., the format of the output format of the evaluation result, is not limited to the example shown in FIG. 12.

[0071] In the next step S118, the storage control unit 295 performs control to store the details of the sales role-playing, the emotion parameters, and the evaluation results in the storage 32 in association with each other, as described above.

[0072] In the next step S120, the output unit 296 outputs the details of the sales role-playing, the emotion parameters, and the evaluation results based on a predetermined format to the terminal device 14. When the process of step S120 ends, the specification process shown in FIG. 9 ends.

[0073] Next, an example of the flow of the reception and output process executed by the terminal device 14 will be described with reference to FIG.

[0074] In the reception output process shown in Fig. 14, first, in step S200, the control unit 46A determines whether or not the above-mentioned start button 350 (see Fig. 5) has been operated by the user. Until the start button 350 is operated, the determination in step S200 is negative, and the process enters a standby state. On the other hand, when the start button 350 is operated, the determination in step S200 is positive, and the process proceeds to step S202.

[0075] In step S202, the control unit 46A transmits the first setting instruction information 330_1, the second setting instruction information 330_2, and the third setting instruction information 330_3 selected by the user to the terminal device 14 via the communication I / F 44.

[0076] In the next step S204, the control unit 46A receives the first information 322_1 from the data processing device 12 via the communication I / F 44.

[0077] In the next step S206, the control unit 46A causes the display 40A to display the received first information 322_1 (see FIG. 5).

[0078] In the next step S208, the control unit 46A determines whether or not a voice input from the user has been acquired. Until the voice input is acquired, the determination in step S208 is negative, and the process proceeds to step S220. On the other hand, if the voice input is acquired, the determination in step S208 is positive, and the process proceeds to step S210.

[0079] In step S210, control unit 46A causes display 40A to display the content of the acquired voice input as input information 340 (see FIG. 5).

[0080] In the next step S212, the control unit 46A determines whether or not the user has operated the send button 354. Until the send button 354 is operated, the determination in step S212 is negative, and the control unit 46A enters a standby state. On the other hand, when the send button 354 is operated, the determination in step S212 is positive, and the control unit 46A proceeds to step S214.

[0081] In step S214, the control unit 46A outputs the acquired voice input to the terminal device 14 via the communication I / F 44.

[0082] In the next step S216, the control unit 46A receives the conversation content output by the data processing device 12 in the process of step S110 of the above-mentioned identification process (see FIG. 9).

[0083] In the next step S218, the control unit 46A causes the received conversation content to be displayed as output information 342 on the display 40A.

[0084] In the next step S220, control unit 46A determines whether or not the user has operated end button 356. Until end button 356 is operated, the determination in step S220 is negative, the process returns to step S208, and the processes in steps S208 to S218 are repeated. On the other hand, if end button 356 is operated, the determination in step S220 is positive, and the process proceeds to step S222.

[0085] In step S222, the control unit 46A transmits an end instruction to the data processing device 12, as described above.

[0086] In the next step S224, the control unit 46A receives the evaluation result output by the data processing device 12 in the process of step S120 of the above-mentioned identification process (see FIG. 9).

[0087] In the next step S226, the control unit 46A causes the acquired evaluation result to be displayed on the display 40A. Through this process, the evaluation result shown in Fig. 13 described above is displayed on the display 40A. When the process of step S226 ends, the reception output process shown in Fig. 14 ends.

[0088] As described above, the data processing device 12 includes the processing unit 294 that performs the specific processing using the data generation model 58 capable of generating sentences according to the input contents, and the setting unit 293 that generates the input contents based on information about the fictitious company 320. The processing unit 294 performs role-playing of the person in charge 324 of the fictitious company 320 in sales as the specific processing, using the output of the data generation model 58 when a sales talk to the person in charge 324 of the fictitious company 320 is input as the input contents.

[0089] With the above-described configuration, the data processing device 12 of the above embodiment can improve the accuracy of training by sales role-playing.

[0090] Moreover, in the data processing device 12 of the above embodiment, sales role-playing is performed in a state where the first information 322_1, which is part of the information set for the fictitious company 320, is presented to the sales representative 310. Therefore, according to the data processing device 12, sales role-playing can be performed in a state closer to the actual situation, and therefore the accuracy of training by sales role-playing can be further improved.

[0091] In the above embodiment, the predetermined approach of the present disclosure is sales, but the predetermined approach is not limited to sales. For example, the predetermined approach may be job hunting.

[0092] In the above embodiment, the data processing device 12 evaluates the content of the sales role-playing. However, the evaluation may be performed manually by a person such as a superior of the user (salesperson 310) who performed the sales role-playing. In this case, the output unit 296 of the data processing device 12 outputs the evaluation result acquired from the storage 32 to the terminal device 14 of the user who performs the evaluation. The content of the sales role-playing and the evaluation result shown in FIG. 13 are displayed on the display 40A of the terminal device 14 of the user who performs the evaluation. The user who performs the evaluation refers to the content of the sales role-playing and the evaluation result, and inputs an evaluation FB (Feedback) (see "Evaluation FB" in FIG. 15), which is a comment evaluating the sales talk. The evaluation FB is transmitted to the data processing device 12. The storage control unit 295 of the data processing device 12 stores the received evaluation FB in the storage 32 in association with the content of the sales role-playing and the result of the evaluation process by the processing unit 294. In the data processing device 12, when an instruction from the user who was the sales representative 310 in the sales role-playing is received from the terminal device 14, the output unit 296 outputs the manual evaluation FB, the contents of the sales role-playing, and the evaluation results by the processing unit 294 of the data processing device 12 to the terminal device 14. By this processing, a display similar to that shown in FIG.

[0093] The emotion identification model 60 may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 60 may determine the emotion of the user according to an emotion map (see FIG. 16A), which is a specific mapping.

[0094] FIG. 16A is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0095] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0096] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0097] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0098] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0099] The emotion identification model 60 inputs user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. In addition, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 16B. FIG. 16B shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0100] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0101] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0102] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0103] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0104] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0105] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0106] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0107] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0108] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[0109] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0110] 10 Data Processing System 12 Data Processing Device 14 Terminal Equipment

Claims

1. A processing unit that performs a specific process using a data generation model that can generate a sentence according to an input content; A setting unit that generates the input contents based on information about a fictitious company; Including, The processing unit performs, as a specific process, a role-play of the person in charge of the fictitious company in response to the predetermined approach, using an output of the data generation model when a talk for making a predetermined approach to the person in charge of the fictitious company is used as the input content. Data processing device.

2. and an output unit that outputs a part of the information about the fictitious company and a result of the identification process.

2. A data processing apparatus according to claim 1.

3. The information about the fictitious company includes first information and second information that is more easily known by other companies than the first information.

2. A data processing apparatus according to claim 1.

4. The second information is a business problem of the fictitious company.

4. A data processing device according to claim 3.

5. The identification process further includes a process of outputting an emotion parameter for the talk.

2. A data processing apparatus according to claim 1.

6. The identification process further includes an evaluation process for evaluating the predetermined approach.

2. A data processing apparatus according to claim 1.

7. a storage control unit that receives a user evaluation of the role-playing, and stores the user evaluation, the content of the role-playing including a result of the specific processing, and a result of the evaluation processing in association with each other; and an output unit that outputs the associated user evaluations, the content of the role-playing, and the results of the evaluation process.

7. A data processing apparatus according to claim 6.

8. The predetermined approach is sales.

2. A data processing apparatus according to claim 1.

9. The processor: A processing step of performing a specific process using a data generation model capable of generating a sentence according to an input content; A configuration step of generating the input content based on information about a fictitious company; Including, In the processing step, a role-play of the person in charge of the fictitious company in response to the predetermined approach is performed as a specific process using an output of the data generation model when a talk for making a predetermined approach to the person in charge of the fictitious company is input. Data processing methods.

10. A processing step of performing a specific process using a data generation model capable of generating a sentence according to an input content; A configuration step of generating the input content based on information about a fictitious company; Including, In the processing step, a role-play of the person in charge of the fictitious company in response to the predetermined approach is performed as a specific process using an output of the data generation model when a talk for making a predetermined approach to the person in charge of the fictitious company is used as the input content. A program for causing a computer to execute a process including the above.

Images