System

Abstract

An object of a system according to an embodiment is to specify an appropriate questionnaire target person and efficiently implement a questionnaire.SOLUTION: A system includes a questionnaire target specification part, a questionnaire generation part, a questionnaire distribution part, a questionnaire result collection part, a questionnaire result analysis part, and a questionnaire result report part. A questionnaire target specification part specifies a questionnaire target by using the generated AI. The questionnaire generation unit generates a questionnaire for the questionnaire target identified by the questionnaire target identification unit. The questionnaire distribution unit distributes the questionnaire generated by the questionnaire generation unit to questionnaire target persons. The questionnaire result collection part collects questionnaire answers from questionnaire object persons. The questionnaire result analysis unit analyzes the questionnaire responses collected by the questionnaire result collection unit. The questionnaire result report part reports the result analyzed by the questionnaire result analysis part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem that it is difficult for companies wanting to conduct surveys to find suitable survey subjects.

[0005] The system according to the embodiment aims to identify appropriate survey subjects and efficiently conduct the survey. [Means for solving the problem]

[0006] The system according to the embodiment includes a survey target identification unit, a survey generation unit, a survey distribution unit, a survey result collection unit, a survey result analysis unit, and a survey result reporting unit. The survey target identification unit identifies survey target individuals using a generation AI. The survey generation unit generates a survey for the survey target individuals identified by the survey target identification unit. The survey distribution unit distributes the survey generated by the survey generation unit to the survey target individuals. The survey result collection unit collects survey responses from the survey target individuals. The survey result analysis unit analyzes the survey responses collected by the survey result collection unit. The survey result reporting unit reports the results analyzed by the survey result analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can identify appropriate survey subjects and efficiently conduct the survey. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single 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 coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a 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 symbol is an interface including a communication processor, 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), and Bluetooth (registered trademark).

[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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] 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. 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 (for example, 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 (see FIG. 2) acquires the data indicating the user input.

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various 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 smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A survey system according to an embodiment of the present invention is a system in which a company efficiently identifies survey recipients, a generation AI generates and distributes surveys, and collects, analyzes, and reports the results. This allows the survey system to efficiently conduct surveys and saves companies the trouble of finding recipients.

[0029] A survey system according to an embodiment includes a survey target identification unit, a survey generation unit, a survey distribution unit, a survey result collection unit, a survey result analysis unit, and a survey result reporting unit. The survey target identification unit uses a generation AI to identify appropriate survey target individuals based on the purpose and content of a survey provided by a company. For example, if a company wants to conduct a survey for the purpose of "market research on a new product," the generation AI identifies target individuals suitable for the market research. The generation AI identifies target individuals based on pre-learned data and prompts. The survey generation unit generates an appropriate survey for the identified survey target individuals. For example, the generation AI generates questions related to "market research on a new product" and sends them to the target individuals. The generation AI generates the survey based on pre-learned data and prompts. The survey distribution unit distributes the generated survey to the identified target individuals. For example, the generation AI sends the survey via email or a messenger app. The generation AI distributes the survey based on pre-learned data and prompts. The survey result collection unit collects responses to the distributed survey. For example, the generation AI collects response data and provides useful information to companies. The generation AI collects responses based on pre-learned data and prompts. The survey result analysis unit analyzes the collected survey responses. For example, the generation AI analyzes the response data and provides useful information to the company. The generation AI performs analysis based on pre-learned data and prompts. The survey result reporting unit reports the analysis results to the company. For example, the generation AI compiles the analysis results in a report and provides it to the company. The generation AI reports based on pre-learned data and prompts. As a result, the survey system according to the embodiment enables companies to conduct surveys efficiently and eliminates the need to find subjects. For example, it can quickly conduct market research for new products and collect consumer opinions. Furthermore, by analyzing the survey results, companies can understand market needs and use this information in product development and marketing strategies.

[0030] The survey target identification unit can analyze the past survey response history of survey targets and identify the most suitable targets based on response trends. For example, the generation AI retrieves the target's past survey response history from a database and analyzes the response trends. For example, it identifies targets who have shown a high interest in surveys about a specific product in the past. The generation AI also analyzes response history patterns in the survey target identification unit to extract targets with specific response trends. For example, it identifies targets who consistently respond to specific themes. The generation AI also analyzes the target's attributes based on the response history to identify the most suitable targets. For example, it identifies targets based on attributes such as age, gender, and occupation. This makes it possible to identify the most suitable targets based on past response history.

[0031] The survey target identification unit can analyze social media activity data and identify targets that fit the purpose of the survey. For example, the generation AI in the survey target identification unit analyzes social media post content and hashtags to identify targets who are interested in a particular topic. For example, it identifies users who post frequently about environmental issues. The generation AI in the survey target identification unit also analyzes the number of followers and likes on social media to identify influential targets. For example, it identifies influencers with many followers. The generation AI in the survey target identification unit also analyzes social media activity history to identify targets with specific behavioral patterns. For example, it identifies users who frequently participate in specific events. This makes it possible to identify the optimal targets based on social media activity data.

[0032] The questionnaire generation unit can generate individually customized questions based on the subject's past response data. In the questionnaire generation unit, for example, the generation AI analyzes the subject's past response data and generates individually customized questions. For example, questions are created based on topics that the subject has shown interest in in the past. In addition, the questionnaire generation unit customizes questions based on the subject's attribute data. For example, questions are generated according to age, gender, and occupation. In addition, the questionnaire generation unit adjusts the difficulty of questions based on the subject's response history. For example, difficult questions are generated based on past responses. This makes it possible to generate individually customized questions.

[0033] The survey generation unit automatically generates questions that incorporate the latest industry trends, allowing the survey content to be kept up to date at all times. For example, the survey generation unit's generation AI automatically collects the latest industry trends and generates questions based on that information. For example, it creates questions that reflect the latest technological trends and market needs. The survey generation unit's generation AI also analyzes news articles and industry reports to generate questions based on trends. For example, it creates questions related to recent news. The survey generation unit's generation AI also analyzes social media topics to generate questions based on trends. For example, it creates questions related to trending hashtags. This allows the survey content to be kept up to date at all times.

[0034] The survey distribution unit can analyze the optimal contact method for the subject and distribute the survey in the most effective way. For example, the generation AI in the survey distribution unit analyzes the subject's contact method history and identifies the optimal contact method. For example, it selects the optimal method from email, SMS, messenger app, etc. The generation AI in the survey distribution unit also analyzes the frequency with which the subject uses the contact method and identifies the optimal method. For example, it selects a frequently used contact method. The generation AI in the survey distribution unit also analyzes the effectiveness of the subject's contact method and identifies the optimal method. For example, it selects an effective method based on past survey distribution results. This allows the survey to be distributed using the optimal contact method, thereby improving the response rate.

[0035] The survey distribution unit can optimize distribution timing and send the survey at the time when it is easiest for the subject to respond. For example, the generation AI in the survey distribution unit analyzes the subject's past response times and identifies the time when it is easiest for the subject to respond. For example, the generation AI in the survey distribution unit analyzes the subject's active hours and identifies the optimal distribution timing. For example, the generation AI in the survey distribution unit sends the survey during the day to subjects who are more active during the day. For example, the generation AI in the survey distribution unit analyzes the subject's schedule data and identifies the optimal distribution timing. For example, the generation AI in the survey distribution unit sends the survey during a specific time period to subjects who have a high response rate during that time period. In this way, the response rate can be improved by selecting the optimal distribution timing.

[0036] The survey result collection unit can collect response data in real time and analyze it immediately. The survey result collection unit, for example, builds a system in which a generation AI collects response data in real time and analyzes it immediately. For example, the data is analyzed each time a response is submitted and the results are displayed immediately. The survey result collection unit also has a generation AI collect data in real time and immediately feed back the analysis results. For example, the analysis results are notified to the company each time a response is submitted. The survey result collection unit also has a generation AI collect data in real time and immediately display the analysis results on a dashboard. For example, the analysis results can be checked through a dashboard that is updated in real time. This allows response data to be collected in real time and analyzed immediately, enabling rapid feedback.

[0037] The survey result analysis unit can analyze the response data from multiple angles and extract useful information from multiple perspectives. For example, the survey result analysis unit constructs a system in which the generation AI analyzes the response data from multiple angles and extracts useful information from multiple perspectives. For example, the response data is analyzed from different perspectives to provide multiple insights. In addition, the generation AI analyzes the data using statistical analysis and text mining. For example, it analyzes the statistical trends of the response data and the sentiment of the text. In addition, the generation AI analyzes the data using sentiment analysis. For example, it extracts positive and negative sentiment from the response data. In this way, useful information can be extracted from multiple perspectives by analyzing the response data from multiple angles.

[0038] The survey result reporting unit can automatically compile the analysis results into a report format and provide it to companies. For example, the survey result reporting unit builds a system in which the generation AI automatically compiles the analysis results into a report format and provides it to companies. For example, the analysis results are automatically compiled into a report and provided to companies. In addition, the survey result reporting unit has the generation AI automatically generate a PDF report and provide it to companies. For example, the analysis results are compiled in PDF format and sent to companies. In addition, the survey result reporting unit has the generation AI automatically generate an online dashboard and provide it to companies. For example, a dashboard is provided that displays the analysis results in real time. In this way, the analysis results can be automatically compiled into a report format and provided to companies quickly.

[0039] The survey result reporting unit reports the analysis results in multiple languages, making it possible to accommodate international companies. For example, the generation AI in the survey result reporting unit reports the analysis results in multiple languages, building a system that can accommodate international companies. For example, the analysis results are reported in multiple languages, such as English, French, and Chinese. In addition, the generation AI in the survey result reporting unit translates the analysis results into multiple languages ​​using an automatic translation function. For example, the analysis results are automatically translated and provided in multiple languages. In addition, the generation AI in the survey result reporting unit automatically generates a report that supports multiple languages. For example, a report summarizing the analysis results in multiple languages ​​is provided. In this way, the analysis results can be reported in multiple languages, making it possible to accommodate international companies.

[0040] The survey result reporting unit can provide the analysis results in an interactive dashboard format, allowing companies to freely manipulate the data. For example, the survey result reporting unit builds a system in which the generation AI provides the analysis results in an interactive dashboard format, allowing companies to freely manipulate the data. For example, it provides a dashboard that allows data filtering and graph customization. In addition, the survey result reporting unit provides a dashboard that is updated in real time by the generation AI. For example, it displays the analysis results in real time, allowing companies to freely manipulate the data. In addition, in the survey result reporting unit, the generation AI provides interactive data visualization. For example, it makes the analysis results easier to understand through visual display of data. This allows companies to freely manipulate the data by providing it in an interactive dashboard format.

[0041] The survey result reporting department can customize the analysis results for different departments and provide the most appropriate information to each department. For example, the survey result reporting department will build a system in which the generation AI customizes the analysis results for different departments and provides the most appropriate information to each department. For example, it will provide market trends to the marketing department and technology trends to the product development department. In addition, the generation AI in the survey result reporting department will automatically generate reports according to the needs of each department. For example, it will provide customer feedback to the sales department and strategic insights to the management department. In addition, the generation AI in the survey result reporting department will filter the data for each department and provide the most appropriate information. For example, it will extract only data related to a specific department and reflect it in the report. In this way, the analysis results can be customized for each department, allowing the most appropriate information to be provided to each department.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The survey target identification unit can also analyze the purchasing history of subjects and identify subjects who fit the purpose of the survey. For example, the generation AI retrieves the subjects' past purchasing history from a database and identifies subjects who have shown interest in specific products or services. The generation AI also analyzes patterns in purchasing history and extracts subjects with specific purchasing tendencies. For example, it identifies subjects who show consistent purchasing behavior toward specific brands or categories. The generation AI also analyzes the attributes of subjects based on their purchasing history and identifies the most suitable subjects. For example, it identifies subjects based on attributes such as age, gender, and income. This makes it possible to identify the most suitable subjects based on their purchasing history.

[0044] The survey generation unit can also generate questions based on the subject's hobbies and interests. For example, the generation AI analyzes the subject's social media profile and posts to create questions related to their hobbies and interests. The survey generation unit also customizes questions based on the subject's online activity history. For example, it generates questions based on the browsing history and search history of specific websites. The survey generation unit also customizes questions based on the subject's purchasing history. For example, it creates questions related to products and services purchased in the past. This makes it possible to generate questions that are individually customized based on the subject's hobbies and interests.

[0045] The survey distribution unit can also analyze the geographic location information of the subjects and select the optimal distribution method. For example, the generation AI obtains the subject's location information and selects the optimal distribution method for each region. For example, email may be effective in certain regions, while SMS may be effective in other regions. The generation AI also adjusts the distribution timing based on the subject's location information. For example, it may send the survey at the optimal time to subjects in different time zones. The generation AI also selects a distribution method that suits the culture and customs of each region based on the location information. For example, it may distribute surveys to coincide with specific holidays in certain regions. This allows the response rate to be improved by selecting the optimal distribution method based on geographic location information.

[0046] The survey result collection unit can also anonymize the response data and collect it while protecting privacy. For example, when the generation AI collects the response data, it deletes any information that could identify individuals and collects anonymized data. The survey result collection unit also encrypts the response data and collects it securely. For example, the response data is encrypted before transmission to prevent unauthorized access by third parties. The survey result collection unit also protects privacy by having the generation AI store the response data in a distributed database. For example, blockchain technology is used to manage data in a distributed manner and prevent tampering. This allows the response data to be anonymized and collected while protecting privacy.

[0047] The survey result analysis unit can also visualize the response data and provide it in a visually easy-to-understand format. For example, the generation AI converts the response data into graphs and charts to visually display the analysis results. The survey result analysis unit can also convert the response data into infographics and provide it in a visually appealing format. For example, the response data can be visually represented using icons and illustrations. The survey result analysis unit can also plot the response data on a map to visually display the geographical distribution. For example, the response data can be displayed color-coded by region. This makes it possible to visualize the response data and provide it in a visually easy-to-understand format.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The survey target identification unit uses the generation AI to identify appropriate survey targets based on the purpose and content of the survey provided by the company. For example, if a company wants to conduct a survey for the purpose of "market research on a new product," the generation AI will identify targets suitable for the market research. The generation AI will identify targets based on pre-trained data and prompts. Step 2: The survey generator generates an appropriate survey for the identified survey recipients. For example, the generation AI generates questions related to "market research for a new product" and sends them to the recipients. The generation AI generates the survey based on the data and prompts it has learned in advance. Step 3: The survey distribution unit distributes the generated survey to the specified target audience. For example, the generation AI sends the survey via email or a messenger app. The generation AI distributes the survey based on the data and prompts it has learned in advance. Step 4: The survey result collection unit collects the responses to the distributed survey. For example, the generation AI collects the response data and provides useful information to the company. The generation AI collects responses based on pre-learned data and prompts. Step 5: The survey result analysis unit analyzes the collected survey responses. For example, the generation AI analyzes the response data and provides useful information to the company. The generation AI performs analysis based on the data and prompts it has learned in advance. Step 6: The survey result reporting department reports the analysis results to the company. For example, the generation AI compiles the analysis results in a report format and provides it to the company. The generation AI reports based on the data and prompts it has learned in advance.

[0050] (Example 2) A survey system according to an embodiment of the present invention is a system in which a company efficiently identifies survey recipients, a generation AI generates and distributes surveys, and collects, analyzes, and reports the results. This allows the survey system to efficiently conduct surveys and saves companies the trouble of finding recipients.

[0051] A survey system according to an embodiment includes a survey target identification unit, a survey generation unit, a survey distribution unit, a survey result collection unit, a survey result analysis unit, and a survey result reporting unit. The survey target identification unit uses a generation AI to identify appropriate survey target individuals based on the purpose and content of a survey provided by a company. For example, if a company wants to conduct a survey for the purpose of "market research on a new product," the generation AI identifies target individuals suitable for the market research. The generation AI identifies target individuals based on pre-learned data and prompts. The survey generation unit generates an appropriate survey for the identified survey target individuals. For example, the generation AI generates questions related to "market research on a new product" and sends them to the target individuals. The generation AI generates the survey based on pre-learned data and prompts. The survey distribution unit distributes the generated survey to the identified target individuals. For example, the generation AI sends the survey via email or a messenger app. The generation AI distributes the survey based on pre-learned data and prompts. The survey result collection unit collects responses to the distributed survey. For example, the generation AI collects response data and provides useful information to companies. The generation AI collects responses based on pre-learned data and prompts. The survey result analysis unit analyzes the collected survey responses. For example, the generation AI analyzes the response data and provides useful information to the company. The generation AI performs analysis based on pre-learned data and prompts. The survey result reporting unit reports the analysis results to the company. For example, the generation AI compiles the analysis results in a report and provides it to the company. The generation AI reports based on pre-learned data and prompts. As a result, the survey system according to the embodiment enables companies to conduct surveys efficiently and eliminates the need to find subjects. For example, it can quickly conduct market research for new products and collect consumer opinions. Furthermore, by analyzing the survey results, companies can understand market needs and use this information in product development and marketing strategies.

[0052] The survey target identification unit can analyze the past survey response history of survey targets and identify the most suitable targets based on response trends. For example, the generation AI retrieves the target's past survey response history from a database and analyzes the response trends. For example, it identifies targets who have shown a high interest in surveys about a specific product in the past. The generation AI also analyzes response history patterns in the survey target identification unit to extract targets with specific response trends. For example, it identifies targets who consistently respond to specific themes. The generation AI also analyzes the target's attributes based on the response history to identify the most suitable targets. For example, it identifies targets based on attributes such as age, gender, and occupation. This makes it possible to identify the most suitable targets based on past response history.

[0053] The survey target identification unit can analyze social media activity data and identify targets that fit the purpose of the survey. For example, the generation AI in the survey target identification unit analyzes social media post content and hashtags to identify targets who are interested in a particular topic. For example, it identifies users who post frequently about environmental issues. The generation AI in the survey target identification unit also analyzes the number of followers and likes on social media to identify influential targets. For example, it identifies influencers with many followers. The generation AI in the survey target identification unit also analyzes social media activity history to identify targets with specific behavioral patterns. For example, it identifies users who frequently participate in specific events. This makes it possible to identify the optimal targets based on social media activity data.

[0054] The survey subject identification unit uses an emotion estimation function to estimate the subject's current emotional state, and can preferentially identify subjects with positive emotions. In the survey subject identification unit, for example, the generation AI analyzes the subject's social media posts and message content and evaluates the current emotional state using the emotion estimation function. For example, it identifies subjects who post many posts that show positive emotions. In the survey subject identification unit, the generation AI analyzes the subject's voice data and evaluates the emotional state using the emotion estimation function. For example, it identifies subjects with a positive tone of voice. In the survey subject identification unit, the generation AI analyzes the subject's facial expression data and evaluates the emotional state using the emotion estimation function. For example, it identifies subjects who smile many times. This makes it possible to preferentially identify subjects with positive emotions.

[0055] The questionnaire generation unit can generate individually customized questions based on the subject's past response data. In the questionnaire generation unit, for example, the generation AI analyzes the subject's past response data and generates individually customized questions. For example, questions are created based on topics that the subject has shown interest in in the past. In addition, the questionnaire generation unit customizes questions based on the subject's attribute data. For example, questions are generated according to age, gender, and occupation. In addition, the questionnaire generation unit adjusts the difficulty of questions based on the subject's response history. For example, difficult questions are generated based on past responses. This makes it possible to generate individually customized questions.

[0056] The survey generation unit automatically generates questions that incorporate the latest industry trends, allowing the survey content to be kept up to date at all times. For example, the survey generation unit's generation AI automatically collects the latest industry trends and generates questions based on that information. For example, it creates questions that reflect the latest technological trends and market needs. The survey generation unit's generation AI also analyzes news articles and industry reports to generate questions based on trends. For example, it creates questions related to recent news. The survey generation unit's generation AI also analyzes social media topics to generate questions based on trends. For example, it creates questions related to trending hashtags. This allows the survey content to be kept up to date at all times.

[0057] The questionnaire generation unit uses the emotion estimation function to generate questions that correspond to the emotional state of the subject, thereby improving the response rate. In the questionnaire generation unit, for example, the generation AI analyzes the emotional state of the subject in real time and generates questions based on the results. For example, it creates positive questions for subjects with positive emotions. In addition, the generation AI in the questionnaire generation unit adjusts the tone of the questions based on the subject's emotional data. For example, it creates questions with a gentle tone for subjects with negative emotions. In addition, the generation AI in the questionnaire generation unit customizes the content of the questions based on the subject's emotional state. For example, it creates relaxing questions for subjects who are feeling stressed. In this way, the response rate can be improved by generating questions that correspond to the emotional state.

[0058] The survey distribution unit can analyze the optimal contact method for the subject and distribute the survey in the most effective way. For example, the generation AI in the survey distribution unit analyzes the subject's contact method history and identifies the optimal contact method. For example, it selects the optimal method from email, SMS, messenger app, etc. The generation AI in the survey distribution unit also analyzes the frequency with which the subject uses the contact method and identifies the optimal method. For example, it selects a frequently used contact method. The generation AI in the survey distribution unit also analyzes the effectiveness of the subject's contact method and identifies the optimal method. For example, it selects an effective method based on past survey distribution results. This allows the survey to be distributed using the optimal contact method, thereby improving the response rate.

[0059] The survey distribution unit can optimize distribution timing and send the survey at the time when it is easiest for the subject to respond. For example, the generation AI in the survey distribution unit analyzes the subject's past response times and identifies the time when it is easiest for the subject to respond. For example, the generation AI in the survey distribution unit analyzes the subject's active hours and identifies the optimal distribution timing. For example, the generation AI in the survey distribution unit sends the survey during the day to subjects who are more active during the day. For example, the generation AI in the survey distribution unit analyzes the subject's schedule data and identifies the optimal distribution timing. For example, the generation AI in the survey distribution unit sends the survey during a specific time period to subjects who have a high response rate during that time period. In this way, the response rate can be improved by selecting the optimal distribution timing.

[0060] The survey distribution unit uses the emotion estimation function to select a distribution method according to the emotional state of the subject, thereby improving the response rate. For example, the generation AI in the survey distribution unit analyzes the emotional state of the subject in real time and selects a distribution method based on the results. For example, a positive message is sent to a subject with positive emotions. The generation AI in the survey distribution unit also adjusts the distribution method based on the subject's emotional data. For example, a message in a gentle tone is sent to a subject with negative emotions. The generation AI in the survey distribution unit also adjusts the distribution timing based on the subject's emotional state. For example, a survey is sent to a subject who is feeling stressed at a time when they are able to relax. In this way, the response rate can be improved by selecting a distribution method according to the subject's emotional state.

[0061] The survey result collection unit can collect response data in real time and analyze it immediately. The survey result collection unit, for example, builds a system in which a generation AI collects response data in real time and analyzes it immediately. For example, the data is analyzed each time a response is submitted and the results are displayed immediately. The survey result collection unit also has a generation AI collect data in real time and immediately feed back the analysis results. For example, the analysis results are notified to the company each time a response is submitted. The survey result collection unit also has a generation AI collect data in real time and immediately display the analysis results on a dashboard. For example, the analysis results can be checked through a dashboard that is updated in real time. This allows response data to be collected in real time and analyzed immediately, enabling rapid feedback.

[0062] The survey result analysis unit can analyze the response data from multiple angles and extract useful information from multiple perspectives. For example, the survey result analysis unit constructs a system in which the generation AI analyzes the response data from multiple angles and extracts useful information from multiple perspectives. For example, the response data is analyzed from different perspectives to provide multiple insights. In addition, the generation AI analyzes the data using statistical analysis and text mining. For example, it analyzes the statistical trends of the response data and the sentiment of the text. In addition, the generation AI analyzes the data using sentiment analysis. For example, it extracts positive and negative sentiment from the response data. In this way, useful information can be extracted from multiple perspectives by analyzing the response data from multiple angles.

[0063] The survey result analysis unit can use an emotion estimation function to analyze the emotional aspects of the response data and provide emotion-based insights. In the survey result analysis unit, for example, the generation AI uses the emotion estimation function to analyze the emotional aspects of the response data. For example, it extracts positive and negative emotions from the response data and provides emotion-based insights. In addition, in the survey result analysis unit, the generation AI uses text analysis to evaluate the emotion of the response data. For example, it calculates an emotion score for the response text and provides emotion-based insights. In addition, in the survey result analysis unit, the generation AI uses voice analysis to evaluate the emotion of the response data. For example, it analyzes the tone and speed of the response voice and provides emotion-based insights. In this way, it is possible to provide emotion-based insights by analyzing the emotional aspects.

[0064] The survey result reporting unit can automatically compile the analysis results into a report format and provide it to companies. For example, the survey result reporting unit builds a system in which the generation AI automatically compiles the analysis results into a report format and provides it to companies. For example, the analysis results are automatically compiled into a report and provided to companies. In addition, the survey result reporting unit has the generation AI automatically generate a PDF report and provide it to companies. For example, the analysis results are compiled in PDF format and sent to companies. In addition, the survey result reporting unit has the generation AI automatically generate an online dashboard and provide it to companies. For example, a dashboard is provided that displays the analysis results in real time. In this way, the analysis results can be automatically compiled into a report format and provided to companies quickly.

[0065] The survey result reporting unit reports the analysis results in multiple languages, making it possible to accommodate international companies. For example, the generation AI in the survey result reporting unit reports the analysis results in multiple languages, building a system that can accommodate international companies. For example, the analysis results are reported in multiple languages, such as English, French, and Chinese. In addition, the generation AI in the survey result reporting unit translates the analysis results into multiple languages ​​using an automatic translation function. For example, the analysis results are automatically translated and provided in multiple languages. In addition, the generation AI in the survey result reporting unit automatically generates a report that supports multiple languages. For example, a report summarizing the analysis results in multiple languages ​​is provided. In this way, the analysis results can be reported in multiple languages, making it possible to accommodate international companies.

[0066] The survey result reporting unit can use the emotion estimation function to emphasize the emotional aspects of the analysis results and provide emotion-based insights to companies. In the survey result reporting unit, for example, the generation AI uses the emotion estimation function to emphasize the emotional aspects of the analysis results. For example, it extracts positive and negative emotions from the response data and provides emotion-based insights. In addition, in the survey result reporting unit, the generation AI uses text analysis to evaluate the emotions of the analysis results. For example, it calculates an emotion score for the response text and provides emotion-based insights. In addition, in the survey result reporting unit, the generation AI uses voice analysis to evaluate the emotions of the analysis results. For example, it analyzes the tone and speed of the response voice and provides emotion-based insights. In this way, by emphasizing the emotional aspects, emotion-based insights can be provided to companies.

[0067] The survey result reporting unit can provide the analysis results in an interactive dashboard format, allowing companies to freely manipulate the data. For example, the survey result reporting unit builds a system in which the generation AI provides the analysis results in an interactive dashboard format, allowing companies to freely manipulate the data. For example, it provides a dashboard that allows data filtering and graph customization. In addition, the survey result reporting unit provides a dashboard that is updated in real time by the generation AI. For example, it displays the analysis results in real time, allowing companies to freely manipulate the data. In addition, in the survey result reporting unit, the generation AI provides interactive data visualization. For example, it makes the analysis results easier to understand through visual display of data. This allows companies to freely manipulate the data by providing it in an interactive dashboard format.

[0068] The survey result reporting department can customize the analysis results for different departments and provide the most appropriate information to each department. For example, the survey result reporting department will build a system in which the generation AI customizes the analysis results for different departments and provides the most appropriate information to each department. For example, it will provide market trends to the marketing department and technology trends to the product development department. In addition, the generation AI in the survey result reporting department will automatically generate reports according to the needs of each department. For example, it will provide customer feedback to the sales department and strategic insights to the management department. In addition, the generation AI in the survey result reporting department will filter the data for each department and provide the most appropriate information. For example, it will extract only data related to a specific department and reflect it in the report. In this way, the analysis results can be customized for each department, allowing the most appropriate information to be provided to each department.

[0069] The survey result reporting unit can use the emotion estimation function to evaluate the emotional impact of the analysis results and propose an emotion-based action plan to the company. In the survey result reporting unit, for example, the generation AI uses the emotion estimation function to evaluate the emotional impact of the analysis results. For example, it extracts the impact of positive and negative emotions from the response data and proposes an emotion-based action plan. In addition, in the survey result reporting unit, the generation AI uses text analysis to evaluate the emotional impact. For example, it calculates an emotion score for the response text and proposes an emotion-based action plan. In addition, in the survey result reporting unit, the generation AI uses voice analysis to evaluate the emotional impact. For example, it analyzes the tone and speed of the response voice and proposes an emotion-based action plan. In this way, by evaluating the emotional impact, it is possible to propose an emotion-based action plan to the company.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The survey target identification unit can also analyze the purchasing history of subjects and identify subjects who fit the purpose of the survey. For example, the generation AI retrieves the subjects' past purchasing history from a database and identifies subjects who have shown interest in specific products or services. The generation AI also analyzes patterns in purchasing history and extracts subjects with specific purchasing tendencies. For example, it identifies subjects who show consistent purchasing behavior toward specific brands or categories. The generation AI also analyzes the attributes of subjects based on their purchasing history and identifies the most suitable subjects. For example, it identifies subjects based on attributes such as age, gender, and income. This makes it possible to identify the most suitable subjects based on their purchasing history.

[0072] The survey generation unit can also generate questions based on the subject's hobbies and interests. For example, the generation AI analyzes the subject's social media profile and posts to create questions related to their hobbies and interests. The survey generation unit also customizes questions based on the subject's online activity history. For example, it generates questions based on the browsing history and search history of specific websites. The survey generation unit also customizes questions based on the subject's purchasing history. For example, it creates questions related to products and services purchased in the past. This makes it possible to generate questions that are individually customized based on the subject's hobbies and interests.

[0073] The survey distribution unit can also analyze the geographic location information of the subjects and select the optimal distribution method. For example, the generation AI obtains the subject's location information and selects the optimal distribution method for each region. For example, email may be effective in certain regions, while SMS may be effective in other regions. The generation AI also adjusts the distribution timing based on the subject's location information. For example, it may send the survey at the optimal time to subjects in different time zones. The generation AI also selects a distribution method that suits the culture and customs of each region based on the location information. For example, it may distribute surveys to coincide with specific holidays in certain regions. This allows the response rate to be improved by selecting the optimal distribution method based on geographic location information.

[0074] The survey result collection unit can also anonymize the response data and collect it while protecting privacy. For example, when the generation AI collects the response data, it deletes any information that could identify individuals and collects anonymized data. The survey result collection unit also encrypts the response data and collects it securely. For example, the response data is encrypted before transmission to prevent unauthorized access by third parties. The survey result collection unit also protects privacy by having the generation AI store the response data in a distributed database. For example, blockchain technology is used to manage data in a distributed manner and prevent tampering. This allows the response data to be anonymized and collected while protecting privacy.

[0075] The survey result analysis unit can also visualize the response data and provide it in a visually easy-to-understand format. For example, the generation AI converts the response data into graphs and charts to visually display the analysis results. The survey result analysis unit can also convert the response data into infographics and provide it in a visually appealing format. For example, the response data can be visually represented using icons and illustrations. The survey result analysis unit can also plot the response data on a map to visually display the geographical distribution. For example, the response data can be displayed color-coded by region. This makes it possible to visualize the response data and provide it in a visually easy-to-understand format.

[0076] The survey target identification unit can also use an emotion estimation function to estimate the emotional state of the target and avoid targets with negative emotions. For example, the generation AI analyzes the target's social media posts and message content and excludes targets with many posts that show negative emotions. The generation AI also analyzes the target's voice data and excludes targets with negative voice tones. For example, targets with many angry or sad tones are identified. The generation AI also analyzes the target's facial expression data and excludes targets with many negative facial expressions. For example, targets with many angry or sad facial expressions are identified. This makes it possible to avoid targets with negative emotions.

[0077] The questionnaire generation unit can also use the emotion estimation function to provide feedback according to the emotional state of the subject. For example, the generation AI analyzes the emotional state of the subject in real time and generates feedback based on the results. For example, it provides positive feedback to a subject with positive emotions. The questionnaire generation unit also adjusts the tone of the feedback based on the subject's emotional data. For example, it provides gentle feedback to a subject with negative emotions. The questionnaire generation unit also customizes the content of the feedback based on the subject's emotional state. For example, it provides relaxing feedback to a subject who is feeling stressed. In this way, respondent satisfaction can be improved by providing feedback according to the subject's emotional state.

[0078] The survey distribution unit can also use the emotion estimation function to send reminders according to the emotional state of the subject. For example, the generation AI analyzes the emotional state of the subject in real time and generates reminders based on the results. For example, it sends a positive reminder to a subject with positive emotions. The generation AI in the survey distribution unit also adjusts the tone of the reminder based on the subject's emotional data. For example, it sends a gentle reminder to a subject with negative emotions. The generation AI in the survey distribution unit also customizes the content of the reminder based on the subject's emotional state. For example, it sends a relaxing reminder to a subject who is feeling stressed. In this way, by sending reminders according to the subject's emotional state, it is possible to improve the response rate.

[0079] The survey result analysis unit can also use the emotion estimation function to analyze the emotional trends in the response data and propose emotion-based marketing strategies to companies. For example, the generation AI analyzes the emotional trends in the response data and identifies products and services for which positive emotions are increasing. The generation AI then proposes a marketing strategy based on the emotion scores of the response data. For example, it could implement a specific campaign for subjects with positive emotions. The generation AI then customizes the marketing strategy based on the emotional insights in the response data. For example, it could propose improvement measures for subjects with negative emotions. This makes it possible to propose emotion-based marketing strategies by analyzing emotional trends.

[0080] The survey result reporting unit can also use the emotion estimation function to emphasize the emotional aspects of the analysis results and provide emotion-based insights to companies. For example, the generation AI extracts positive and negative emotions from the response data and provides emotion-based insights. In addition, the generation AI in the survey result reporting unit uses text analysis to evaluate the emotions of the analysis results. For example, it calculates an emotion score for the response text and provides emotion-based insights. In addition, the generation AI in the survey result reporting unit uses voice analysis to evaluate the emotions of the analysis results. For example, it analyzes the tone and speed of the response voice and provides emotion-based insights. In this way, by emphasizing the emotional aspects, emotion-based insights can be provided to companies.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The survey target identification unit uses the generation AI to identify appropriate survey targets based on the purpose and content of the survey provided by the company. For example, if a company wants to conduct a survey for the purpose of "market research on a new product," the generation AI will identify targets suitable for the market research. The generation AI will identify targets based on pre-trained data and prompts. Step 2: The survey generator generates an appropriate survey for the identified survey recipients. For example, the generation AI generates questions related to "market research for a new product" and sends them to the recipients. The generation AI generates the survey based on the data and prompts it has learned in advance. Step 3: The survey distribution unit distributes the generated survey to the specified target audience. For example, the generation AI sends the survey via email or a messenger app. The generation AI distributes the survey based on the data and prompts it has learned in advance. Step 4: The survey result collection unit collects the responses to the distributed survey. For example, the generation AI collects the response data and provides useful information to the company. The generation AI collects responses based on pre-learned data and prompts. Step 5: The survey result analysis unit analyzes the collected survey responses. For example, the generation AI analyzes the response data and provides useful information to the company. The generation AI performs analysis based on the data and prompts it has learned in advance. Step 6: The survey result reporting department reports the analysis results to the company. For example, the generation AI compiles the analysis results in a report format and provides it to the company. The generation AI reports based on the data and prompts it has learned in advance.

[0083] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0084] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN and / or a LAN.

[0089] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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 microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0090] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0093] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, 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.

[0094] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0097] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN and / or a LAN.

[0104] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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 microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, 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.

[0109] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN and / or a LAN.

[0119] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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 microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0124] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, 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.

[0125] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0127] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0133] FIG. 9 illustrates 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0134] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically 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.

[0135] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0137] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0138] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, 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. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0139] 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.

[0140] 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 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 in accordance with the specific processing program 56.

[0141] Alternatively, 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 in response to a request from the data processing device 12.

[0142] 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.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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.

[0145] As an example of a system configured with a single 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 system that uses a processor that realizes the functions of an 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.

[0146] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0147] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0148] The above-described description and illustrations are a detailed explanation 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, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects 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-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a survey target identification unit that identifies survey target persons using a generation AI; a questionnaire generation unit that generates a questionnaire for the survey subjects identified by the survey subject identification unit; a questionnaire distribution unit that distributes the questionnaire generated by the questionnaire generation unit to the survey subjects; a survey result collection unit that collects survey responses from the survey subjects; a survey result analysis unit that analyzes the survey responses collected by the survey result collection unit; a survey result reporting unit that reports the results analyzed by the survey result analysis unit. A system characterized by:

2. The survey target identification unit Analyze social media activity data to identify subjects who fit the purpose of the survey.

2. The system of claim 1.

3. The questionnaire generation unit Generate personalized questions based on the subject's past responses 2. The system of claim 1.

4. The survey distribution unit Analyze the best way to contact the target audience and distribute the survey in the most effective way 2. The system of claim 1.

5. The survey result collection unit Collect response data in real time and perform the above analysis immediately 2. The system of claim 1.

6. The questionnaire result analysis unit Analyze the emotional aspects of response data to provide sentiment-based insights 2. The system of claim 1.

7. The questionnaire result reporting unit Highlight the emotional aspects of analytical results and provide emotional insights to businesses 2. The system of claim 1.

8. The survey target identification unit Estimating the current emotional state of a subject and preferentially identifying said subjects with positive emotions 2. The system of claim 1.

Images