System

Abstract

An object of a system according to an embodiment is to improve the quality of questionnaires by excluding respondents who answer appropriately.SOLUTION: A system includes an answer tendency determination part, a questionnaire transmission restriction part, an attention arousing part, and a sentence generation part. The answer tendency determination unit determines an answer tendency of the answerer. The questionnaire transmission restriction unit does not transmit a questionnaire to a respondent who is determined to have appropriately responded by the response tendency determination unit. The attention calling unit calls attention to the answerer who is determined to be appropriately answering by the answer tendency determination unit. The sentence generation unit generates a sentence based on a keyword input by an answerer.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] The conventional techniques have room for improvement in terms of efficiently eliminating respondents who give random answers and improving the quality of the questionnaire.

[0005] The system according to the embodiment aims to eliminate respondents who give random answers and improve the quality of the questionnaire. [Means for solving the problem]

[0006] The system according to the embodiment includes an answer tendency determination unit, a questionnaire transmission restriction unit, a warning unit, and a sentence generation unit. The answer tendency determination unit determines the answer tendency of respondents. The questionnaire transmission restriction unit does not send questionnaires to respondents who are determined by the answer tendency determination unit to be answering appropriately. The warning unit warns respondents who are determined by the answer tendency determination unit to be answering appropriately. The sentence generation unit generates sentences based on keywords entered by respondents. [Effects of the Invention]

[0007] The system according to the embodiment can eliminate respondents who give random answers and improve the quality of the questionnaire. [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 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) The questionnaire system according to the embodiment of the present invention uses AI to determine the tendency of respondents to answer questions and eliminate respondents who answer randomly. This allows the questionnaire system to improve the quality of the questionnaire and collect highly reliable data.

[0029] A questionnaire system according to an embodiment includes a response tendency determination unit, a questionnaire transmission restriction unit, a warning unit, and a sentence generation unit. The response tendency determination unit determines a respondent's response tendency. For example, the generation AI analyzes past questionnaire response data to determine the respondent's response tendency. The generation AI receives inputs including response data and prompts containing instructions for analyzing the data, and the generation AI performs analysis based on the prompts. The questionnaire transmission restriction unit does not send questionnaires to respondents determined by the response tendency determination unit to be answering questions casually. For example, the generation AI prevents subsequent questionnaires from being sent to respondents determined by the response tendency determination unit to be answering questions casually. The warning unit warns respondents who tend to answer questions casually based on the response tendency determination unit. For example, the generation AI sends a warning message to respondents who tend to answer questions casually in advance. The sentence generation unit generates sentences based on keywords entered by the respondent. For example, if a respondent enters keywords such as "service," "improvement," and "quickly," the generation AI generates a sentence such as "I hope that service improvements will be made quickly." This enables the questionnaire system to improve the quality of questionnaires and collect reliable data.

[0030] The answer tendency determination unit analyzes the respondent's past online behavior data and can determine answer tendencies more precisely. The answer tendency determination unit, for example, analyzes the respondent's past website browsing history and evaluates the respondent's level of interest in a specific topic. For example, it predicts answer tendencies based on the categories of frequently visited sites. This allows for more precise determination of answer tendencies.

[0031] The answer tendency determination unit analyzes the answering time of the respondent and can determine that a respondent with an extremely short answering time is answering inappropriately. The answer tendency determination unit, for example, records the answering time for each question and compares it with the average answering time. It determines that a respondent with an extremely short answering time is answering inappropriately. This makes it possible to determine that a respondent with an extremely short answering time is answering inappropriately.

[0032] When analyzing the answering tendencies of respondents, the answering tendency determination unit also includes voice input and handwritten input in the analysis target, making it possible to determine tendencies from a wider variety of data. The answering tendency determination unit, for example, analyzes voice input data and determines answering tendencies based on the content and tone of the respondent's remarks. For example, the remarks are converted into text using voice recognition technology and analyzed. In this way, by including voice input and handwritten input in the analysis target, it is possible to determine tendencies from a wider variety of data.

[0033] The answer tendency determination unit can compare answer tendencies for different questionnaire formats and identify patterns of appropriate answering. The answer tendency determination unit, for example, compares answer tendencies for multiple-choice questionnaires and free-form questionnaires and identify patterns of appropriate answering. For example, it identifies respondents who give inconsistent answers in multiple-choice questionnaires. This makes it possible to compare answer tendencies for different questionnaire formats and identify patterns of appropriate answering.

[0034] The survey transmission restriction unit can track the respondent's past survey response history over the long term and evaluate whether the respondent is consistently providing appropriate responses. The survey transmission restriction unit, for example, stores the respondent's past survey response history in a database and builds a system for long-term tracking. For example, it records the content of past responses and the time of response. This allows the respondent's past survey response history to be tracked over the long term and evaluates whether the respondent is consistently providing appropriate responses.

[0035] The survey transmission restriction unit can analyze the content of the respondent's answers and determine appropriate answers based on the frequency of specific keywords and phrases. The survey transmission restriction unit, for example, performs text analysis on the content of the respondent's answers and measures the frequency of specific keywords and phrases. For example, it detects meaningless character strings and repetition of the same phrases. This allows the content of the answers to be analyzed and appropriate answers to be determined based on the frequency of specific keywords and phrases.

[0036] The survey transmission restriction unit can not only eliminate inappropriate respondents but also provide special incentives to respondents who provide appropriate answers. The survey transmission restriction unit builds a system that provides special incentives to respondents who provide appropriate answers, for example, by offering points or gift cards. This provides special incentives to respondents who provide appropriate answers, thereby improving the quality of their answers.

[0037] The survey transmission restriction unit can share appropriate response tendencies of respondents between different survey platforms and apply similar restrictions on other platforms. The survey transmission restriction unit, for example, builds a system that shares appropriate response tendencies of respondents between different survey platforms. For example, it develops an API for sharing respondent data. This allows appropriate response tendencies to be shared between different survey platforms and apply similar restrictions on other platforms.

[0038] The attention-reminder unit can provide feedback indicating specific areas for improvement based on past answer history to respondents who tend to give inappropriate answers. The attention-reminder unit, for example, analyzes past answer history and builds a system that provides feedback indicating specific areas for improvement. For example, if there are many meaningless answers, the attention-reminder unit presents specific areas for improvement. In this way, by providing feedback indicating specific areas for improvement, it is possible to reduce inappropriate answers.

[0039] The alert unit can send individually customized alert messages based on the respondent's profile information. The alert unit builds a system for sending individually customized alert messages based on the respondent's profile information, such as the respondent's age, occupation, and interests. For example, casual messages are sent to younger generations. This makes it easier to attract the respondent's attention by sending individually customized alert messages.

[0040] When sending a warning message, the warning unit can use a video message and an infographic to make a visual appeal. The warning unit, for example, sends the warning message as a video message to build a system that makes a visual appeal. For example, the warning is made using a short video. Also, the warning message is sent as an infographic to build a system that makes a visual appeal. For example, an infographic is created based on the type of design or the type of information. This makes it possible to enhance the effectiveness of the warning by making a visual appeal using a video message or an infographic.

[0041] The warning unit automatically generates warning messages corresponding to different languages ​​and cultural spheres, making it possible to respond to respondents globally. The warning unit, for example, builds a system that automatically generates warning messages corresponding to different languages. For example, it translates the messages into multiple languages ​​such as English, French, and Chinese. It also builds a system that automatically generates warning messages corresponding to different cultural spheres. For example, it generates messages tailored to the cultures of Asia, Europe, and the United States. In this way, by automatically generating warning messages corresponding to different languages ​​and cultural spheres, it is possible to respond to respondents globally.

[0042] The sentence generation unit can generate more specific sentences based on keywords entered by the respondent and related past free comment data. The sentence generation unit, for example, builds a system that searches related past free comment data based on keywords entered by the respondent and generates specific sentences. For example, it extracts similar comments from a past database. This makes it possible to generate more specific sentences by referencing past free comment data.

[0043] The sentence generation unit can encourage respondents to post higher quality free comments based on related suggested keywords when they input keywords. The sentence generation unit, for example, builds a system that presents related suggested keywords to respondents when they input keywords. For example, related keywords are automatically displayed while they are being input. In this way, by presenting suggested keywords, it is possible to encourage respondents to post higher quality free comments.

[0044] The sentence generation unit can automatically translate free comments into different languages ​​when generating sentences for free comments, thereby generating free comments that support multiple languages. The sentence generation unit, for example, builds a system that automatically translates free comments into different languages ​​when generating sentences for free comments. For example, it translates into multiple languages ​​such as English, French, and Chinese. This allows free comments to be generated in multiple languages ​​by automatically translating into different languages.

[0045] The sentence generation unit can provide a function of automatically attaching related images and videos based on keywords selected by a respondent when the keywords are entered. The sentence generation unit, for example, builds a system that automatically attaches related images and videos based on keywords selected by a respondent when the keywords are entered. For example, it searches for and attaches images related to the keywords. This allows the respondent's intention to be conveyed more specifically by automatically attaching related images and videos based on the keywords.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The survey system can also provide personalized surveys based on respondent profile information. For example, it can tailor questions based on age, gender, occupation, and other information. This can provide more relevant questions to respondents and improve the quality of their responses. It can also add questions based on specific interests to more easily capture respondents' attention. It can also refer to the respondent's past response history and generate follow-up questions based on previous answers.

[0048] Survey systems can also use social media data to analyze respondent response trends. For example, they can analyze respondents' Twitter and Facebook posts to assess their interest in specific topics. This allows for more extensive collection of online behavioral data from respondents and allows for more precise determination of response trends. Using social media data also makes it possible to understand respondents' latest interests and adjust survey content in a timely manner.

[0049] Survey systems can also take into account respondent device information when analyzing response times. For example, they can compare response times from mobile devices like smartphones and tablets with those from desktops and laptops. This allows for differences in response times between devices and more accurately determines whether respondents are responding appropriately. It can also improve the quality of responses by adjusting the way questions are presented depending on the device.

[0050] The survey system can also take into account the cultural background of respondents when comparing response trends for different survey formats. For example, it can provide culturally appropriate question formats to respondents from different cultures. This allows for accurate identification of response trends according to cultural background. It can also provide feedback based on cultural background to deepen respondents' understanding and improve the quality of their responses. Furthermore, cross-cultural comparative analysis can provide insights from a global perspective.

[0051] The survey system can also take into account the respondent's life event information when tracking the respondent's past survey response history over the long term. For example, it can evaluate the impact of life events such as marriage, childbirth, and job change on response trends. This allows for accurate understanding of changes in response trends in response to life events and makes it possible to determine whether the respondent is responding appropriately. In addition, adding questions based on life events can make it easier to attract the respondent's attention. Furthermore, providing feedback according to life events can increase respondent satisfaction.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The response tendency determination unit determines the respondent's response tendency. For example, the generation AI analyzes past survey response data and determines the respondent's response tendency. The input to the generation AI is a prompt containing the response data and instructions for analyzing it, and the generation AI performs analysis based on the prompt. Step 2: The survey sending restriction unit does not send surveys to respondents who are determined by the answer tendency determination unit to be answering casually. For example, respondents who are determined by the generation AI to be answering casually will not be sent subsequent surveys. Step 3: The warning unit warns respondents who tend to give careless answers based on the answer tendency determination unit. For example, the generation AI sends a warning message in advance to respondents who tend to give careless answers. Step 4: The sentence generation unit generates sentences based on the keywords entered by the respondent. For example, if a respondent enters keywords such as "service," "improvement," and "quickly," the generation AI will generate a sentence such as "We hope that service improvements will be made quickly."

[0054] (Example 2) The questionnaire system according to the embodiment of the present invention uses AI to determine the tendency of respondents to answer questions and eliminate respondents who answer randomly. This allows the questionnaire system to improve the quality of the questionnaire and collect highly reliable data.

[0055] A questionnaire system according to an embodiment includes a response tendency determination unit, a questionnaire transmission restriction unit, a warning unit, and a sentence generation unit. The response tendency determination unit determines a respondent's response tendency. For example, the generation AI analyzes past questionnaire response data to determine the respondent's response tendency. The generation AI receives inputs including response data and prompts containing instructions for analyzing the data, and the generation AI performs analysis based on the prompts. The questionnaire transmission restriction unit does not send questionnaires to respondents determined by the response tendency determination unit to be answering questions casually. For example, the generation AI prevents subsequent questionnaires from being sent to respondents determined by the response tendency determination unit to be answering questions casually. The warning unit warns respondents who tend to answer questions casually based on the response tendency determination unit. For example, the generation AI sends a warning message to respondents who tend to answer questions casually in advance. The sentence generation unit generates sentences based on keywords entered by the respondent. For example, if a respondent enters keywords such as "service," "improvement," and "quickly," the generation AI generates a sentence such as "I hope that service improvements will be made quickly." This enables the questionnaire system to improve the quality of questionnaires and collect reliable data.

[0056] The answer tendency determination unit analyzes the respondent's past online behavior data and can determine answer tendencies more precisely. The answer tendency determination unit, for example, analyzes the respondent's past website browsing history and evaluates the respondent's level of interest in a specific topic. For example, it predicts answer tendencies based on the categories of frequently visited sites. This allows for more precise determination of answer tendencies.

[0057] The answer tendency determination unit analyzes the answering time of the respondent and can determine that a respondent with an extremely short answering time is answering inappropriately. The answer tendency determination unit, for example, records the answering time for each question and compares it with the average answering time. It determines that a respondent with an extremely short answering time is answering inappropriately. This makes it possible to determine that a respondent with an extremely short answering time is answering inappropriately.

[0058] The answer tendency determination unit uses the emotion estimation function to analyze the emotional state of the respondent, and can determine that the respondent is answering casually if the respondent has strong negative emotions. The answer tendency determination unit, for example, analyzes the respondent's facial expression and calculates an emotion score. If the negative emotion score is high, it determines that the respondent is likely to be answering casually. This makes it possible to determine that the respondent is likely to be answering casually if the respondent has strong negative emotions.

[0059] When analyzing the answering tendencies of respondents, the answering tendency determination unit also includes voice input and handwritten input in the analysis target, making it possible to determine tendencies from a wider variety of data. The answering tendency determination unit, for example, analyzes voice input data and determines answering tendencies based on the content and tone of the respondent's remarks. For example, the remarks are converted into text using voice recognition technology and analyzed. In this way, by including voice input and handwritten input in the analysis target, it is possible to determine tendencies from a wider variety of data.

[0060] The answer tendency determination unit can compare answer tendencies for different questionnaire formats and identify patterns of appropriate answering. The answer tendency determination unit, for example, compares answer tendencies for multiple-choice questionnaires and free-form questionnaires and identify patterns of appropriate answering. For example, it identifies respondents who give inconsistent answers in multiple-choice questionnaires. This makes it possible to compare answer tendencies for different questionnaire formats and identify patterns of appropriate answering.

[0061] The answer tendency determination unit uses the emotion estimation function to monitor the emotions of respondents when they answer questionnaires in real time, and can provide immediate feedback if it is determined that the respondents are answering inappropriately.The answer tendency determination unit, for example, analyzes the respondent's facial expressions in real time and calculates an emotion score.If the respondent has a strong negative emotion, it provides immediate feedback.This makes it possible to monitor emotions in real time and provide immediate feedback if there is a possibility that the respondent is answering inappropriately.

[0062] The survey transmission restriction unit can track the respondent's past survey response history over the long term and evaluate whether the respondent is consistently providing appropriate responses. The survey transmission restriction unit, for example, stores the respondent's past survey response history in a database and builds a system for long-term tracking. For example, it records the content of past responses and the time of response. This allows the respondent's past survey response history to be tracked over the long term and evaluates whether the respondent is consistently providing appropriate responses.

[0063] The survey transmission restriction unit can analyze the content of the respondent's answers and determine appropriate answers based on the frequency of specific keywords and phrases. The survey transmission restriction unit, for example, performs text analysis on the content of the respondent's answers and measures the frequency of specific keywords and phrases. For example, it detects meaningless character strings and repetition of the same phrases. This allows the content of the answers to be analyzed and appropriate answers to be determined based on the frequency of specific keywords and phrases.

[0064] The survey transmission restriction unit uses the emotion estimation function to check the emotional state of respondents who give inappropriate answers before sending the survey, and can not send the survey if it is determined that the respondent has a strong negative emotion. The survey transmission restriction unit, for example, analyzes the respondent's facial expression and calculates an emotion score. If the respondent has a strong negative emotion, the survey is not sent. In this way, by not sending the survey if the respondent has a strong negative emotion, inappropriate answers can be prevented.

[0065] The survey transmission restriction unit can not only eliminate inappropriate respondents but also provide special incentives to respondents who provide appropriate answers. The survey transmission restriction unit builds a system that provides special incentives to respondents who provide appropriate answers, for example, by offering points or gift cards. This provides special incentives to respondents who provide appropriate answers, thereby improving the quality of their answers.

[0066] The survey transmission restriction unit can share appropriate response tendencies of respondents between different survey platforms and apply similar restrictions on other platforms. The survey transmission restriction unit, for example, builds a system that shares appropriate response tendencies of respondents between different survey platforms. For example, it develops an API for sharing respondent data. This allows appropriate response tendencies to be shared between different survey platforms and apply similar restrictions on other platforms.

[0067] The survey transmission restriction unit can use the emotion estimation function to send a message that elicits positive emotions to respondents who are giving inappropriate answers before sending the survey, thereby encouraging them to give appropriate answers. For example, the survey transmission restriction unit can use the emotion estimation function to analyze the emotional state of the respondent and send a message that elicits positive emotions. For example, it can send an encouraging message. In this way, by sending a message that elicits positive emotions, it is possible to encourage appropriate answers.

[0068] The attention-reminder unit can provide feedback indicating specific areas for improvement based on past answer history to respondents who tend to give inappropriate answers. The attention-reminder unit, for example, analyzes past answer history and builds a system that provides feedback indicating specific areas for improvement. For example, if there are many meaningless answers, the attention-reminder unit presents specific areas for improvement. In this way, by providing feedback indicating specific areas for improvement, it is possible to reduce inappropriate answers.

[0069] The alert unit can send individually customized alert messages based on the respondent's profile information. The alert unit builds a system for sending individually customized alert messages based on the respondent's profile information, such as the respondent's age, occupation, and interests. For example, casual messages are sent to younger generations. This makes it easier to attract the respondent's attention by sending individually customized alert messages.

[0070] The attention-request unit uses the emotion estimation function to generate an attention-request message according to the respondent's emotional state, thereby eliciting positive emotions. The attention-request unit, for example, uses the emotion estimation function to analyze the respondent's emotional state and generate an attention-request message that elicits positive emotions. For example, it sends an encouraging message. This allows the attention-request message according to the emotional state to be generated and elicit positive emotions.

[0071] When sending a warning message, the warning unit can use a video message and an infographic to make a visual appeal. The warning unit, for example, sends the warning message as a video message to build a system that makes a visual appeal. For example, the warning is made using a short video. Also, the warning message is sent as an infographic to build a system that makes a visual appeal. For example, an infographic is created based on the type of design or the type of information. This makes it possible to enhance the effectiveness of the warning by making a visual appeal using a video message or an infographic.

[0072] The warning unit automatically generates warning messages corresponding to different languages ​​and cultural spheres, making it possible to respond to respondents globally. The warning unit, for example, builds a system that automatically generates warning messages corresponding to different languages. For example, it translates the messages into multiple languages ​​such as English, French, and Chinese. It also builds a system that automatically generates warning messages corresponding to different cultural spheres. For example, it generates messages tailored to the cultures of Asia, Europe, and the United States. In this way, by automatically generating warning messages corresponding to different languages ​​and cultural spheres, it is possible to respond to respondents globally.

[0073] The warning unit uses the emotion estimation function to monitor the effectiveness of the warning message in real time, and can immediately adjust the message content if it is determined that the message is ineffective. The warning unit, for example, uses the emotion estimation function to build a system that monitors the effectiveness of the warning message in real time. For example, it analyzes the emotion score after sending the message. Also, it builds a system that immediately adjusts the message content if it is determined that the message is ineffective. For example, it changes the message content if the emotion score is low. This makes it possible to monitor the effectiveness of the warning message in real time, and immediately adjust the message content if it is determined that the message is ineffective.

[0074] The sentence generation unit can generate more specific sentences based on keywords entered by the respondent and related past free comment data. The sentence generation unit, for example, builds a system that searches related past free comment data based on keywords entered by the respondent and generates specific sentences. For example, it extracts similar comments from a past database. This makes it possible to generate more specific sentences by referencing past free comment data.

[0075] The sentence generation unit can encourage respondents to post higher quality free comments based on related suggested keywords when they input keywords. The sentence generation unit, for example, builds a system that presents related suggested keywords to respondents when they input keywords. For example, related keywords are automatically displayed while they are being input. In this way, by presenting suggested keywords, it is possible to encourage respondents to post higher quality free comments.

[0076] The sentence generation unit uses the emotion estimation function to generate sentences according to the respondent's emotional state and can generate free comments that elicit positive emotions. The sentence generation unit, for example, uses the emotion estimation function to analyze the respondent's emotional state and builds a system that generates sentences that elicit positive emotions. For example, if the emotional score is low, it generates encouraging sentences. This allows for the generation of sentences according to the emotional state and the creation of free comments that elicit positive emotions.

[0077] The sentence generation unit can automatically translate free comments into different languages ​​when generating sentences for free comments, thereby generating free comments that support multiple languages. The sentence generation unit, for example, builds a system that automatically translates free comments into different languages ​​when generating sentences for free comments. For example, it translates into multiple languages ​​such as English, French, and Chinese. This allows free comments to be generated in multiple languages ​​by automatically translating into different languages.

[0078] The sentence generation unit can provide a function of automatically attaching related images and videos based on keywords selected by a respondent when the keywords are entered. The sentence generation unit, for example, builds a system that automatically attaches related images and videos based on keywords selected by a respondent when the keywords are entered. For example, it searches for and attaches images related to the keywords. This allows the respondent's intention to be conveyed more specifically by automatically attaching related images and videos based on the keywords.

[0079] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0080] The survey system can also provide personalized surveys based on respondent profile information. For example, it can tailor questions based on age, gender, occupation, and other information. This can provide more relevant questions to respondents and improve the quality of their responses. It can also add questions based on specific interests to more easily capture respondents' attention. It can also refer to the respondent's past response history and generate follow-up questions based on previous answers.

[0081] Survey systems can also use social media data to analyze respondent response trends. For example, they can analyze respondents' Twitter and Facebook posts to assess their interest in specific topics. This allows for more extensive collection of online behavioral data from respondents and allows for more precise determination of response trends. Using social media data also makes it possible to understand respondents' latest interests and adjust survey content in a timely manner.

[0082] Survey systems can also take into account respondent device information when analyzing response times. For example, they can compare response times from mobile devices like smartphones and tablets with those from desktops and laptops. This allows for differences in response times between devices and more accurately determines whether respondents are responding appropriately. It can also improve the quality of responses by adjusting the way questions are presented depending on the device.

[0083] The survey system can also use the respondent's emotion estimation function to adjust the difficulty of the survey based on the respondent's emotional state. For example, if the respondent has strong negative emotions, it can start with easy questions and gradually increase the difficulty, allowing the respondent to complete the survey without feeling stressed. On the other hand, if the respondent has strong positive emotions, it can add more detailed questions to gain deeper insights. Furthermore, it can also maintain the respondent's motivation by providing feedback according to their emotional state.

[0084] The questionnaire system can also use natural language processing technology to estimate emotions when analyzing the respondent's voice input or handwriting input, and evaluate the quality of the answers. For example, the system can analyze the tone of the voice input or the pressure of the handwriting input to estimate the respondent's emotional state. This makes it possible to determine whether the respondent is answering appropriately based on their emotional state. It is also possible to improve the quality of the answers by providing appropriate feedback to the respondent based on the emotion estimation results.

[0085] The survey system can also take into account the cultural background of respondents when comparing response trends for different survey formats. For example, it can provide culturally appropriate question formats to respondents from different cultures. This allows for accurate identification of response trends according to cultural background. It can also provide feedback based on cultural background to deepen respondents' understanding and improve the quality of their responses. Furthermore, cross-cultural comparative analysis can provide insights from a global perspective.

[0086] The survey system can also use emotion estimation to monitor the emotions of respondents in real time as they answer the survey and provide positive feedback at the appropriate time. For example, if a respondent shows positive emotions, an encouraging message can be sent. This can maintain the respondent's motivation and improve the quality of their responses. Also, if a respondent shows negative emotions, a relaxing message can be sent to reduce the respondent's stress. Furthermore, by providing incentives according to their emotional state, respondent satisfaction can be increased.

[0087] The survey system can also take into account the respondent's life event information when tracking the respondent's past survey response history over the long term. For example, it can evaluate the impact of life events such as marriage, childbirth, and job change on response trends. This allows for accurate understanding of changes in response trends in response to life events and makes it possible to determine whether the respondent is responding appropriately. In addition, adding questions based on life events can make it easier to attract the respondent's attention. Furthermore, providing feedback according to life events can increase respondent satisfaction.

[0088] When analyzing the content of respondents' answers, the survey system can further estimate their emotions using natural language processing technology and determine appropriate answers. For example, the context of the answers can be analyzed to calculate an emotion score. If the negative emotion score is high, it can be determined that the answer is likely to be inappropriate. This makes it possible to determine appropriate answers based on the emotion estimation results. Furthermore, by providing feedback according to the respondent's emotional state, it is possible to maintain the respondent's motivation and improve the quality of their answers. Furthermore, it is also possible to provide appropriate incentives to respondents based on the emotion estimation results.

[0089] The questionnaire system can further use the emotion estimation function to send a message that elicits positive emotions to respondents who are giving inappropriate answers before sending the questionnaire, encouraging them to give appropriate answers. For example, the emotion estimation function can be used to analyze the respondent's emotional state and send a message that elicits positive emotions. In this way, by sending a message that elicits positive emotions, it is possible to encourage appropriate answers. It is also possible to increase the respondent's motivation by providing incentives according to their emotional state. Furthermore, it is possible to provide appropriate feedback to the respondent based on the emotion estimation results.

[0090] The processing flow of the second embodiment will be briefly explained below.

[0091] Step 1: The response tendency determination unit determines the respondent's response tendency. For example, the generation AI analyzes past survey response data and determines the respondent's response tendency. The input to the generation AI is a prompt containing the response data and instructions for analyzing it, and the generation AI performs analysis based on the prompt. Step 2: The survey sending restriction unit does not send surveys to respondents who are determined by the answer tendency determination unit to be answering casually. For example, respondents who are determined by the generation AI to be answering casually will not be sent subsequent surveys. Step 3: The warning unit warns respondents who tend to give careless answers based on the answer tendency determination unit. For example, the generation AI sends a warning message in advance to respondents who tend to give careless answers. Step 4: The sentence generation unit generates sentences based on the keywords entered by the respondent. For example, if a respondent enters keywords such as "service," "improvement," and "quickly," the generation AI will generate a sentence such as "We hope that service improvements will be made quickly."

[0092] 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.

[0093] 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.

[0094] 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.

[0095] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0096] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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).

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0111] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0146] 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."

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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]

[0159] 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. an answer tendency determination unit that determines the answer tendency of respondents; a survey transmission restriction unit that does not send surveys to respondents who are determined by the answer tendency determination unit to be answering appropriately; a warning unit that warns a respondent who is determined by the answer tendency determination unit to be giving an appropriate answer; A sentence generation unit that generates sentences based on keywords entered by respondents. A system characterized by:

2. The answer tendency determination unit is Analyze the respondents' past online behavior data to more precisely determine their response trends.

2. The system of claim 1.

3. The answer tendency determination unit is When analyzing the answering tendency of the respondent, voice input and handwritten input are also included in the analysis, and the tendency is determined from a wider variety of data.

2. The system of claim 1.

4. The questionnaire transmission restriction unit Track the respondent's past survey response history over time and evaluate whether they are continually providing appropriate responses.

2. The system of claim 1.

5. The attention drawing unit For respondents who tend to give inappropriate answers, provide feedback indicating specific areas for improvement based on past answer history.

2. The system of claim 1.

6. The sentence generation unit Based on the keywords entered by the respondent, and based on related past free comment data, a more specific sentence is generated.

2. The system of claim 1.

7. The answer tendency determination unit is Using an emotion estimation function, the emotional state of the respondent is analyzed, and if the respondent has strong negative emotions, it is determined that the respondent is responding inappropriately.

2. The system of claim 1.

8. The questionnaire transmission restriction unit Using the emotion estimation function, the emotional state of the respondent who gives an inappropriate answer is checked before sending the survey, and if it is determined that the respondent has a strong negative emotion, the survey will not be sent.

2. The system of claim 1.

Images