Data processing device, data processing method, and data processing program

Abstract

To provide a data processing device, a data processing method, and a program that can generate a virtual person and have the virtual person answer a questionnaire.SOLUTION: A data processing device includes: a reception unit configured to receive information on a survey subject of a questionnaire; a generation unit configured to generate multiple virtual persons with distributed attributes according to the survey subject; and an output unit configured to output an answer to the questionnaire posed to each of the generated virtual persons.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The technology of the present disclosure relates to a data processing apparatus, a data processing method, and a data processing program.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The persona as a virtual character in the chat of Patent Document 1 is said to "represent a character that reflects a specific age, gender, region, and linguistic personality (e.g., a lively personality, a polite personality, a positive personality, etc.)" (paragraph 0024). When conducting a questionnaire using the persona of Patent Document 1 as a respondent for the purpose of labor-saving and speeding up the questionnaire survey, bias will occur in the response content. Therefore, there is room for improvement in conducting a meaningful questionnaire using a virtual character.

[0005] An object of the technology of the present disclosure is to provide an apparatus, a method, and a program capable of achieving labor-saving and speeding up of an investigation while ensuring the significance of a questionnaire.

Means for Solving the Problems

[0006] A first aspect of the technology according to the present disclosure is a data processing apparatus including a reception unit that receives information on a questionnaire survey target, a generation unit that generates a plurality of virtual characters with attributes dispersed according to the survey target, and an output unit that outputs answers to the questionnaire obtained by asking questions to each of the generated virtual characters.

[0007] A second aspect of the technology according to the present disclosure is the data processing apparatus of the first aspect, wherein the generation unit generates a plurality of virtual characters according to the category of the survey target.

[0008] A third aspect of the technology according to the present disclosure is the data processing apparatus of the first aspect, wherein the generation unit generates a plurality of the virtual characters by inputting the information to a generation AI, and the output unit outputs answers for each of the virtual characters by asking questions assuming a case where each of the virtual characters answers the questionnaire to the generation AI.

[0009] A fourth aspect of the technology according to the present disclosure is the data processing apparatus of the third aspect, further including a learning unit that uses answers to questions for actual people as correct data to train the actual people as the virtual characters, and the learning unit inputs answers to common questions for the actual people and the trained virtual characters to the generation AI, and updates the virtual characters based on the obtained results.

[0010] A fifth aspect of the technology according to the present disclosure is a data processing method in which a computer executes a process of receiving information on a questionnaire survey target, generating a plurality of virtual characters with attributes dispersed according to the survey target, and outputting answers to the questionnaire obtained by asking questions to each of the generated virtual characters.

[0011] A sixth aspect of the technology according to the present disclosure is a data processing program that causes a computer to execute a process of receiving information on a survey target of a questionnaire, generating a plurality of virtual characters with attributes dispersed according to the survey target, and outputting answers to the questionnaire obtained by asking questions to each of the generated virtual characters.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Modes for Carrying Out the Invention

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), etc.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0020] (First Embodiment) FIG. 1 shows an example of the configuration of a data processing system 10 according to an embodiment.

[0021] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. An example of the smart device 14 is a smartphone. In this embodiment, the data processing device 12 is an example of the "data processing device" according to the technology of the present disclosure, and the smart device 14 is an example of the "smartphone" according to the technology of the present disclosure. Also, the smart device 14 is a terminal possessed by a user 60 (see FIG. 4).

[0022] 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 the "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. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, etc., and receives input from the user. The touch panel 38A receives the user's input by the contact of the pointer (for example, a pen or a finger, etc.) by detecting the contact of the pointer. The microphone 38B receives the user's input by voice by detecting the user's voice. The control unit 46A transmits data indicating the user's 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 data indicating the user's input.

[0025] The output device 40 includes a display 40A, a speaker 40B, etc., and presents data to the person 20 by outputting the data in a form (for example, voice and / or text) that the person 20 can perceive. The display 40A displays visible information such as text and images according to an instruction from the processor 46. The speaker 40B outputs voice according to an instruction from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, a diaphragm, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / F 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in FIG. 2, in the data processing device 12, specific processing is performed by the processor 28. The storage 32 stores a specific processing program 56. The specific processing program 56 is an example of the "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The external tool 16 (see FIG. 4) stores a data generation model 58. The data generation model 58 is used by the specific processing unit 290. The data processing device 12 can be connected to the external tool 16 via the communication I / F 26, and the external tool 16 receives an instruction from the specific processing unit 290. The external tool 16 is, for example, an application executed on the cloud.

[0030] The data generation model 58 functions as a so-called generative AI (Artificial Intelligence). Examples of the data generation model 58 include generative AIs such as ChatGPT (Internet search <URL: https: / / openai.com / blog / chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and at least one inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is input. The data generation model 58 infers 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, concretization, and / or summarization, etc.

[0031] In the smart device 14, reception / output processing is performed by the processor 46. The reception / output program 62 is stored in the storage 50. The reception / output program 62 is used in combination 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 operating as the control unit 46A according to the reception / output program 62 executed by the processor 46 on the RAM 48.

[0032] Next, an explanation will be given of the processing of the specific processing unit 290 when the data processing device 12 causes the data generation model 58 to generate a virtual person, which is a fictitious portrait of a person (so-called persona) prepared for answering a questionnaire, and to perform specific processing for generating answers to questions asked of the virtual person.

[0033] The specific processing unit 290 is a function executed by the processor 28 of the computer 22 shown in FIG. 1. As shown in FIG. 3, the specific processing unit 290 includes a reception unit 292, a generation unit 294, and an output unit 296. The generation unit 294 includes an attribute generation unit 294A, a virtual person generation unit 294B, and an answer generation unit 294C.

[0034] The reception unit 292 acquires the input result of the user received by the data processing device 12 or the smart device 14. Specifically, the reception unit 292 receives the result of the user 60 (see FIG. 4) inputting information on the target for which a questionnaire survey is desired. For example, when the user 60 wants to survey the sales forecast of shampoo, the user 60 inputs the product name, price, features, etc. of each shampoo as the survey target, and the reception unit 292 receives the input result. Note that the input by the user may be not only characters but also voice.

[0035] The generation unit 294 performs a specific process using the data generation model 58. The generation unit 294 inputs the character or voice data input from the user 60 to the data generation model 58 and obtains a generation result. Specifically, the generation unit 294 causes the data generation model 58 to generate attributes according to the information of the questionnaire survey target that is the input from the user, and further causes the data generation model 58 to generate a plurality of virtual characters with the attributes dispersed, and generates answers to the questionnaire.

[0036] The generation unit 294 of the present embodiment includes an attribute generation unit 294A, a virtual character generation unit 294B, and an answer generation unit 294C. Hereinafter, each functional unit will be described.

[0037] The attribute generation unit 294A causes the data generation model 58 to generate items of virtual character attributes. Specifically, the attribute generation unit 294A sends a command (for example, a prompt including an instruction) to the data generation model 58 so that the data generation model 58 generates items of attributes based on the information and categories of the target for which the questionnaire survey is desired received by the reception unit 292. Note that each item of the attributes of the virtual character is generated by the data generation model 58 according to an instruction from the attribute generation unit 294A according to the questionnaire survey target, but the user 60 may also specify each item of the attributes. The items of the attributes are, for example, occupation, age, address, hobby, and the like.

[0038] The virtual character generation unit 294B causes the data generation model 58 to generate a plurality of virtual characters in which the generated attribute items are materialized and the contents thereof are dispersed. Specifically, the virtual character generation unit 294B sends a command to the data generation model 58 to materialize the attributes generated by the attribute generation unit 294A and generate a plurality of virtual characters so that the contents of each attribute are dispersed. For example, if the survey target is the prediction of the best-selling shampoo, the virtual character generation unit 294B instructs the data generation model 58 to generate about 1000 virtual characters with dispersed attributes. Also, for example, if the survey target is the communication contract plan of a smartphone, the virtual character generation unit 294B instructs the data generation model 58 to determine the number of virtual characters and the dispersion of attributes based on the statistical information of the whole of Japan and generate virtual characters. The virtual character generation unit 294B causes the data generation model 58 to generate virtual characters by specifically describing the contents of each attribute.

[0039] Examples of the combination of the item of the attribute, which is an example of the virtual character, and the materialization are as follows. "Age: 35 years old, Gender: male, Address: Shinjuku-ku, Tokyo, Housing form: apartment, Place of origin: Shizuoka Prefecture, Education: university graduate, Occupation: web designer, Annual income: 6 million yen, Partner: has a lover, Hobby: driving, Others: has a rich knowledge and a curious personality." In this way, the virtual character generation unit 294B sets a virtual character image by materializing each attribute in the data generation model 58.

[0040] The response generation unit 294C causes the data generation model 58 to generate questionnaire responses as if the generated virtual characters answer the questionnaire. Specifically, a command is sent to the data generation model 58 to cause the plurality of virtual characters generated by the virtual character generation unit 294B to answer the questionnaire. The response generation unit 294C causes the data generation model 58 to generate questionnaire responses by a large number of virtual characters.

[0041] The answer generation unit 294C requests the data generation model 58 to output the questionnaire answers of virtual characters. As an example of the answer, in addition to the conclusion: Shampoo B, the reason: "I am a 35-year-old male working for a telecommunications company. I have a busy daily life, and products that can be easily purchased are attractive. Also, I live in an apartment in Shinjuku-ku, Tokyo, and it is convenient to access the drugstore. Shampoo is something used daily, and the price of 600 yen is relatively affordable. The feature of being able to wash hair cleanly is also attractive and suitable for daily hair care. Among long commutes and a stressful job, a relaxing drive is one of my hobbies. Since the purchase of shampoo can also be done when stopping by the drugstore, ease of use is also an important point. For the above reasons, Shampoo B is the product I most want to purchase.", it outputs not only the conclusion but also the reason. In this way, according to the request of the answer generation unit 294C, the data generation model 58 outputs questionnaire answers by multiple virtual characters.

[0042] Also, based on the questionnaire answer results output from the data generation model 58, the output unit 296 totals the answer results and outputs the totaled results of the questionnaire answers to the user 60. In the totaling, for example, the number of virtual characters who selected each product is represented by a pie chart.

[0043] The output unit 296 transmits the result of the specific process to the smart device 14 (see Figure 2). In the smart device 14, the control unit 46A causes the output device 40 (see Figure 1) to output the result of the specific process. The microphone 38B acquires the voice indicating the user's input with respect to the result of the specific process. Note that the control unit 46A transmits the voice data indicating the user's 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] Next, the operation of the data processing system 10 in the first embodiment will be described.

[0045] An example of the flow of a specific process will be described with reference to FIGS. 4, 5, and 6. Note that the flow of the specific process shown in FIG. 5 is an example of the "data processing method" according to the technology of the present disclosure.

[0046] In the specific process in this embodiment, as shown in the sequence diagram of FIG. 4, when the user 60 inputs information on the subject of the questionnaire survey to the data processing apparatus 12, the specific processing unit 290 executes the generation process 300.

[0047] For example, when information such as "I want to conduct a questionnaire survey on products A to E" input by the user 60 is transmitted to the data processing apparatus 12, the specific processing unit 290 executes the generation process 300 to be described later. In the specific processing unit 290, by sending a predetermined request to the external tool 16 as a command, information on the items of attributes that are the subjects of the questionnaire survey and virtual person information that concretizes the attributes is acquired from the external tool 16. When the processing of the generation process 300 is completed, subsequently, in the data processing apparatus 12, the response process 400 to be described later is executed. In the response process 400, by sending a predetermined request to the external tool 16 as a command, response results to the questionnaire survey by each virtual person are acquired from the external tool 16.

[0048] When the response process 400 is completed, the output unit 296 of the data processing apparatus 12 totals the questionnaire responses and outputs the result to the user 60, ending the specific process.

[0049] Next, the generation process 300 will be described in detail with reference to FIG. 5. First, in step S300, the reception unit 292 receives information on the subject of the questionnaire survey.

[0050] In step S301, the attribute generation unit 294A requests the external tool 16 to generate items of attributes according to the subject of the questionnaire survey by the data generation model 58.

[0051] In step S302, the attribute generation unit 294A acquires the items of attributes generated from the external tool 16.

[0052] In step S303, the attribute generation unit 294A determines whether the generated attribute items meet a predetermined requirement. Examples of the "predetermined requirement" include the bias or dispersion degree of items (such as age, gender, region, etc.) included in the attribute. When the attribute generation unit 294A determines that the attribute items meet the predetermined requirement (step S303: YES), the process proceeds to step S304. On the other hand, when the attribute generation unit 294A determines that the attribute items do not meet the predetermined requirement (step S303: NO), the process returns to step S301. Note that instead of this determination process, the user 60 may determine the suitability of the attribute items.

[0053] In step S304, the virtual character generation unit 294B requests the data generation model 58 to generate a plurality of virtual characters that embody the attributes.

[0054] In step S305, the virtual character generation unit 294B acquires the virtual characters generated by the embodiment.

[0055] In step S306, the virtual character generation unit 294B determines whether the number of generated virtual characters and the generation content (in other words, the degree of embodiment of the attributes) are sufficient. When the virtual character generation unit 294B determines that the virtual characters are sufficient (step S306: YES), the process ends. On the other hand, when the virtual character generation unit 294B determines that the virtual characters are not sufficient (step S306: NO), the process returns to step S304.

[0056] Subsequently, the answer process 400 will be described in detail with reference to FIG. 6. In step S400, the answer generation unit 294C requests the external tool 16 to generate an answer to the questionnaire by the data generation model 58.

[0057] In step S401, the answer generation unit 294C acquires from the external tool 16 the answer result of the questionnaire by the virtual characters generated by the data generation model 58.

[0058] In step S402, the response generation unit 294C determines whether the response generated by the data generation model 58 is sufficient. Whether it is sufficient means, for example, whether the amount of the response content is sufficient, or for example, whether the content of the response content shows a significant difference according to the attributes. When the response generation unit 294C determines that the response is sufficient (step S402: YES), the process ends. On the other hand, when the response generation unit 294C determines that the response is not sufficient (step S402: NO), the process returns to step S400.

[0059] FIG. 7 is a diagram showing an example of a screen 70 for a user 60 to input information on an object for which a questionnaire survey is desired. The screen 70 is created, for example, by the reception device 38 of the smart device 14.

[0060] As shown in FIG. 7, the user 60 inputs, in the form 71, text, an image, or the like, the content for which a questionnaire survey is desired. Note that the input may also be by voice. After the user 60 inputs to the form 71 and presses the send button 72, a specific process is executed, and the questionnaire response result is output to the screen (not shown). In addition, since the past questionnaire response results are displayed in a list in the history 73, they can be queried from the screen.

[0061] As described above, according to the first embodiment, the user 60 can obtain the aggregated result of the questionnaire responses only by inputting the information on the questionnaire survey object to the data processing device 12 or the smart device 14. That is, labor and time for the questionnaire survey can be saved and speeded up. In particular, in this embodiment, by conducting a questionnaire survey on virtual characters having various attributes, the significance of the questionnaire can be ensured. And according to this embodiment, the user 60 can not only predict the best-seller of the product that is the object of the questionnaire survey, but also perform target analysis based on the attribute information of the persona (that is, the virtual character) who selected the product. Also, the questionnaire targeted in the specific process is not limited to the above example, and all questionnaires in the world can be targeted.

[0062] (Second Embodiment) In the second embodiment, the processing of the specific processing unit 290 when the data processing device 12 performs specific processing for generating a virtual person obtained by learning a real person will be described. Note that parts having the same configuration as those in the first embodiment are denoted by the same reference numerals and the description thereof will be omitted.

[0063] FIG. 8 is a conceptual diagram showing an overview of the second embodiment. In the second embodiment, a clone 60C which is a virtual person obtained by learning a user 60 who is a real person is generated. As shown in FIG. 8, in the second embodiment, the same questions are asked to the user 60 and the clone 60C, and the result of comparing the answers is fed back to the data generation model 58, and the data generation model 58 updates the personality generation of the clone 60C.

[0064] In the specific processing in the second embodiment, as shown in FIG. 9, the specific processing unit 290 includes a reception unit 292, a generation unit 294, an output unit 296, and a learning unit 298. Similar to the first embodiment, the generation unit 294 includes an attribute generation unit 294A, a virtual person generation unit 294B, and an answer generation unit 294C.

[0065] Here, the learning unit 298 uses the answers to the questionnaires asked to real people as correct data, and in the data generation model 58, learns a real person as a virtual person (hereinafter, the virtual person is referred to as a "clone"). Further, the learning unit 298 asks the same questions to the real person and the learned clone, inputs their respective answers to the data generation model 58, performs comparison and the like, and feeds back to the data generation model 58. The data generation model 58 further updates the learned clone based on the feedback. In this way, the clone can reproduce the answers of real people. That is, in the second embodiment, the generation and answer accuracy of the virtual person of the data generation model 58 can be improved.

[0066] Also, like in the first embodiment, the responses to the questionnaire of the target to be surveyed may be made by the learned clone. Specifically, when the reception unit 292 receives the input of the information of the questionnaire survey target from the user 60 and the generation unit 294 generates a virtual person, the learned clone is added or replaced. The generation unit 294 uses the data generation model 58 to generate responses to the questionnaire for the virtual person and the clone. The output unit 296 aggregates the generated questionnaire responses and outputs them to the user 60. As described above, the user 60 can obtain responses that are the same as or close to the questionnaire response results of real people just by inputting the information of the questionnaire survey target into the data processing device 12 or the smart device 14.

[0067] Next, the operation of the data processing system 10 in the second embodiment will be described.

[0068] An example of the flow of the specific process in the second embodiment will be described with reference to FIGS. 10 and 11. Note that the flow of the specific process shown in FIG. 11 is an example of the "data processing method" according to the technology of the present disclosure.

[0069] In the specific process in this embodiment, as shown in the sequence diagram of FIG. 10, in advance, the learning unit 298 of the data processing device 12 uses the data generation model 58 to generate a clone as a virtual person who has learned a real person, and the specific processing unit 290 executes the following learning process 500.

[0070] For example, when the user 60 instructs the data processing device 12 to generate a clone 60C that has learned the user 60, the specific processing unit 290 causes the data generation model 58 to execute the generation of the clone 60C for the following learning process 500. Specifically, in the specific processing unit 290, a predetermined request is sent to the external tool 16 as a command, so that the clone 60C is generated in the data generation model 58 of the external tool 16, and the data processing device 12 acquires the clone 60C generated from the external tool 16.

[0071] After the learning process 500 is completed in advance, as shown in FIG. 10, when information input by the user 60 saying "I want to conduct a questionnaire survey on products A to E" is transmitted to the data processing device 12, the specific processing unit 290 executes the generation process 300 described above. When the virtual person generation unit 294B requests the data generation model 58 to generate a plurality of virtual persons with their attributes specified, it also requests the clone 60C learned by the learning unit 298 to be added or replaced as a virtual person.

[0072] After the generation process 300 is completed, subsequently, in the data processing device 12, the response process 400 described above is executed. The response generation unit 294C obtains the questionnaire response results from the virtual persons including the clone 60C generated by the data generation model 58.

[0073] After the response process 400 is completed, the output unit 296 of the data processing device 12 aggregates the questionnaire responses and outputs the results to the user 60, ending the specific process.

[0074] Next, the learning process 500 will be described in detail with reference to FIG. 11. In the learning process 500, the process is executed in the steps shown in FIG. 11. Specifically, first, in step S500, the learning unit 298 requests the external tool 16 to generate a clone 60C of an actual person as a virtual person by the data generation model 58.

[0075] In step S501, the learning unit 298 uses the questions actually received by the actual person on which the clone 60C is based and the information on the answers to those questions as correct data to train the clone 60C generated by the external tool 16. When the actual person is a famous person, the questions actually received by the famous person and the answers to those questions can be easily collected through the Internet.

[0076] In step S502, the learning unit 298 determines whether the learning of the clone 60C is sufficient. If the learning unit 298 determines that the learning of the clone 60C is sufficient (step S502: YES), the process proceeds to step S503. On the other hand, if the learning unit 298 determines that the learning of the clone 60C is not sufficient (step S502: NO), the process returns to step S501.

[0077] In step S503, the learning unit 298 sets questions common to those asked of real people for the clone 60C, compares the answers of the real people with the answers of the clone 60C, and feeds back the results to the data generation model 58, which updates the clone 60C. Then, the learning process 500 ends.

[0078] As described above, according to the second embodiment, in addition to the effects of the first embodiment, the following effects can be obtained. That is, the user 60 can obtain not only a large number of aggregated results of questionnaire answers but also answers as if they were given by real people, simply by inputting the information of the questionnaire subjects into the data processing device 12 or the smart device 14. In particular, by updating the clone 60C that has learned real people through the specific process according to the second embodiment, the accuracy of questionnaire answers can be improved.

[0079] As described above, the system according to the present disclosure has been mainly described in terms of the functions of the data processing device 12. However, the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program that operates on a personal computer or as an application that operates on a smartphone or the like. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0080] In the above embodiment, an example of a form in which specific processing is performed by a single computer 22 has been given. However, the technology of the present disclosure is not limited to this, and distributed processing for specific processing by a plurality of computers including the computer 22 may be performed.

[0081] In the above embodiment, an example of a form in which the specific processing program 56 is stored in the storage 32 has been described. However, 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 USB (Universal Serial Bus) 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 according to the specific processing program 56.

[0082] Also, 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 in the computer 22 in response to a request from the data processing device 12.

[0083] Note that 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, and a part of the specific processing program 56 may be stored.

[0084] As hardware resources for executing specific processing, various types of processors shown below can be used. As the processor, for example, there is a CPU which is a general-purpose processor that functions as a hardware resource for executing specific processing by executing software, that is, a program. Also, as the processor, for example, there is a dedicated electric circuit which is a processor having a circuit configuration specifically designed for executing specific processing such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit). A memory is built in or connected to any of the processors, and any of the processors executes specific processing by using the memory.

[0085] The hardware resources for executing specific processing may be configured by one of these various types of processors, or may be configured by a combination of two or more processors of the same type or different types (for example, a combination of a plurality of FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resources for executing specific processing may be a single processor.

[0086] As an example of configuration by a single processor, firstly, there is a form in which one or more CPUs and software are combined to configure one processor, and this processor functions as a hardware resource for executing specific processing. Secondly, there is a form in which a processor that realizes the functions of the entire system including a plurality of hardware resources for executing specific processing in one IC chip, as represented by an SoC (System-on-a-chip), is used. Thus, specific processing is realized as a hardware resource by using one or more of the above various types of processors.

[0087] Furthermore, as the hardware structure of these various processors, more specifically, an electric circuit combining circuit elements such as semiconductor elements can be used. Also, the above specific processing is merely an example. Therefore, it goes without saying that within the scope not departing from the gist, unnecessary steps may be deleted, new steps may be added, or the processing order may be changed.

[0088] The description content and illustration content shown above are detailed descriptions of the part related to the technology of the present disclosure and are merely examples of the technology of the present disclosure. For example, the description regarding the above configuration, function, operation, and effect is an explanation of an example of the configuration, function, operation, and effect of the part related to the technology of the present disclosure. Therefore, it goes without saying that within the scope not departing from the gist of the technology of the present disclosure, the description content and illustration content shown above may be deleted of unnecessary parts, new elements may be added, or replacements may be made. Also, in order to avoid complication and facilitate the understanding of the part related to the technology of the present disclosure, in the description content and illustration content shown above, the description regarding common technical knowledge and the like that does not particularly require explanation for enabling the implementation of the technology of the present disclosure is omitted.

[0089] All documents, patent applications, and technical standards described in this specification are incorporated herein by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually stated to be incorporated by reference.

Explanation of Reference Signs

[0090] 10 Data processing system 12 Data processing device 14 Smart device 16 External tool 60 User 60C Clone 290 Specific processing unit 292 Reception unit 294 Generation unit 294A Attribute generation unit 294B Virtual character generation unit 294C Answer generation unit 296 Output section 298 Learning section

Claims

1. A reception unit that receives information on the survey target of the questionnaire, A generation unit that generates a plurality of virtual characters with dispersed attributes according to the survey target, An output unit that outputs the answers to the questionnaire obtained by asking questions to each of the generated virtual characters, A data processing device comprising the above.

2. The generation unit generates a plurality of virtual characters according to the category of the survey target, The data processing device according to claim 1.

3. The generation unit generates a plurality of the virtual characters by inputting the information to a generation AI, The output unit outputs the answer for each virtual character by asking a question assuming the case where each virtual character answers the questionnaire to the generation AI The data processing device according to claim 1.

4. A learning unit that uses the answers to questions for real people as correct data and trains the real people as the virtual characters, The learning unit inputs the answers to common questions for the real people and the trained virtual characters to the generation AI, and updates the virtual characters based on the obtained results. The data processing device according to claim 3.

5. Receiving information on the survey target of the questionnaire, Generating a plurality of virtual characters with dispersed attributes according to the survey target, A data processing method in which a computer executes a process of outputting the answers to the questionnaire obtained by asking questions to each of the generated virtual characters.

6. Receiving information on the survey target of the questionnaire, Generating a plurality of virtual characters with dispersed attributes according to the survey target, A data processing program that causes a computer to execute a process of outputting the answers to the questionnaire obtained by asking questions to each of the generated virtual characters. ​ ​

Images