System

Abstract

An object of the system according to the embodiment is to propose a creative matching proposal by utilizing data of a specific company group and a specific data provider.SOLUTION: A system according to an embodiment includes a data collection unit, a word vector calculation unit, a similarity difference calculation unit, and a matching proposal suggestion unit. The data collection unit collects data of a specific company group and a specific data provider. The word vector calculation unit calculates a word vector based on the data collected by the data collection unit. The similarity difference calculation unit calculates a similarity difference between the word vector calculated by the word vector calculation unit and a general word vector. The matching proposal proposing unit proposes a matching proposal for a corporate issue focusing on a word having a large similarity difference calculated by the similarity difference calculating unit.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 technologies do not adequately utilize specific company data to propose original matching proposals, and there is room for improvement.

[0005] The system according to the embodiment aims to propose original matching proposals by utilizing data from a specific company group and a specific data provider. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, a word vector calculation unit, a similarity difference calculation unit, and a matching proposal proposal unit. The data collection unit collects data on a specific company group and a specific data provider. The word vector calculation unit calculates word vectors based on the data collected by the data collection unit. The similarity difference calculation unit calculates the similarity difference between the word vectors calculated by the word vector calculation unit and general word vectors. The matching proposal proposal unit proposes matching proposals for company issues, focusing on words with large similarity differences calculated by the similarity difference calculation unit. [Effects of the Invention]

[0007] The system according to the embodiment can utilize data from a specific company group and a specific data provider to propose original matching proposals. [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) The generative AI system according to an embodiment of the present invention utilizes data held by the SB Group and LINE Yahoo! to propose original and innovative matching, thereby enabling companies to discover new business opportunities and improve their competitiveness.

[0029] The generative AI system according to the embodiment includes a data collection unit, a word vector calculation unit, a similarity difference calculation unit, and a matching proposal proposal unit. The data collection unit collects data from SB Group and LINE Yahoo!. For example, it collects customer purchase history, search history, and user post content and browsing history. The data collection unit also converts this data into a format that is easy for the generative AI to analyze. The word vector calculation unit calculates word vectors based on the collected data. For example, it generates word vectors using algorithms such as Word2Vec or GloVe. The word vector calculation unit also calculates general word vectors from widely used datasets (for example, Wikipedia or news articles). The similarity difference calculation unit calculates the similarity difference between the calculated word vector and the general word vector. For example, it calculates the similarity difference using cosine similarity or Euclidean distance. The similarity difference calculation unit also identifies words with large differences. The matching proposal proposal unit proposes matching proposals for corporate issues based on the identified words with large differences. For example, it proposes new ideas and solutions using unique words in corporate marketing strategies and product development. As a result, the generative AI system according to the embodiment can utilize data from the SB Group and LINE Yahoo! to propose highly original and innovative matches, which can help companies discover new business opportunities and improve their competitiveness.

[0030] The data collection unit incorporates real-time behavioral data of the user to generate more dynamic word vectors. The data collection unit, for example, collects real-time location information from the user's smartphone and generates word vectors based on that data. For example, it analyzes the places the user has visited and the routes they have taken and weights related words. The data collection unit also collects website browsing history and app usage status in real time and generates word vectors based on that data. For example, it analyzes the pages the user has viewed and the content of the apps they have used and weights related words. The data collection unit also collects real-time purchasing behavior data and generates word vectors based on that data. For example, it analyzes information about products and services purchased by the user and weights related words. In this way, by incorporating real-time behavioral data of the user, more dynamic word vectors can be generated.

[0031] The data collection unit can take in a user's voice input or image data and generate a multimodal word vector. The data collection unit, for example, converts the user's voice input into text and generates a word vector based on the text data. For example, the data collection unit analyzes the user's utterances using voice recognition technology. The data collection unit also analyzes the user's image data and generates a word vector based on the content. For example, the data collection unit uses image recognition technology to analyze objects and scenes in the image and weight related words. The data collection unit also takes in both voice input and image data and generates a multimodal word vector. For example, the data collection unit analyzes both voice and image data and generates a word vector by integrating information obtained from each data. In this way, multimodal word vectors can be generated by taking in a user's voice input and image data.

[0032] The data collection unit can integrate datasets from different industries to generate more diverse word vectors. For example, the data collection unit integrates medical data and financial data to generate word vectors. For example, medical terms and financial terms are combined to create new word vectors. The data collection unit also integrates educational data and entertainment data to generate word vectors. For example, education-related terms and entertainment-related terms are combined to create new word vectors. The data collection unit also integrates datasets from different industries to generate more diverse word vectors. For example, datasets from multiple industries are combined to create new word vectors. In this way, more diverse word vectors can be generated by integrating datasets from different industries.

[0033] The data collection unit can incorporate the user's social media activity and generate word vectors that take social influence into consideration. The data collection unit, for example, collects the user's social media posting content and generates word vectors based on that data. For example, it analyzes the frequency of posts and the topics of the content. The data collection unit also collects the user's social media engagement data and generates word vectors based on that data. For example, it analyzes the number of likes and shares and weights related words. The data collection unit also takes the user's number of followers and influence into consideration and generates word vectors based on that data. For example, it places importance on the content posted by users with a large number of followers and weights related words. In this way, by incorporating the user's social media activity, it is possible to generate word vectors that take social influence into consideration.

[0034] The similarity difference calculation unit can also calculate the difference between past data and current data, taking into account fluctuations over time. The similarity difference calculation unit, for example, compares past data with current data and calculates the similarity difference taking into account fluctuations over time. For example, data from the past year is compared with current data. The similarity difference calculation unit also calculates the similarity difference taking into account fluctuations on a daily, weekly, or monthly basis. For example, data from the past week is compared with current data. The similarity difference calculation unit also analyzes fluctuations between past data and current data, and calculates the similarity difference based on the fluctuations. For example, the trend of past data is compared with the trend of current data. In this way, the difference between past and current data can be calculated by taking into account fluctuations over time.

[0035] The similarity difference calculation unit can integrate word vectors of different languages ​​and perform multilingual difference calculations. The similarity difference calculation unit, for example, integrates word vectors of different languages ​​and calculates similarity differences in multiple languages. For example, it integrates word vectors of English and Japanese. The similarity difference calculation unit also integrates word vectors of multiple languages ​​and calculates similarity differences based on the integrated vector. For example, it integrates word vectors of English, Japanese, and Chinese. The similarity difference calculation unit also integrates word vectors of different languages ​​and calculates similarity differences in multiple languages ​​based on the integrated vector. For example, it integrates word vectors of English and French. In this way, by integrating word vectors of different languages, multilingual difference calculations become possible.

[0036] The similarity difference calculation unit can integrate different data sources and calculate a wider range of differences. For example, the similarity difference calculation unit integrates social media data and news data and calculates the similarity difference. For example, it compares Twitter posts with news articles. The similarity difference calculation unit also integrates web data and social media data and calculates the similarity difference. For example, it compares blog posts with Facebook posts. The similarity difference calculation unit also integrates different data sources and calculates the similarity difference based on the integrated data. For example, it compares online forum posts with news articles. This makes it possible to calculate a wider range of differences by integrating different data sources.

[0037] The similarity difference calculation unit can calculate a difference based on a behavioral pattern by taking into account the user's behavioral history. The similarity difference calculation unit, for example, analyzes the user's past behavioral history and calculates a similarity difference based on the behavioral pattern. For example, past purchase history and search history are taken into account. The similarity difference calculation unit also analyzes the user's behavioral pattern and calculates a similarity difference based on the pattern. For example, it analyzes the tendency to take specific actions during specific time periods. The similarity difference calculation unit also analyzes fluctuations in the behavioral pattern based on the user's behavioral history and calculates a similarity difference based on the fluctuations. For example, it compares past behavioral patterns with current behavioral patterns. This makes it possible to calculate a difference based on a behavioral pattern by taking into account the user's behavioral history.

[0038] When identifying words with large differences, the matching suggestion proposal unit can take into account temporal fluctuations and the differences between past data and current data. The matching suggestion proposal unit, for example, compares past data with current data and identifies words with large differences by taking temporal fluctuations into account. For example, it compares data from the past year with current data. The matching suggestion proposal unit also identifies words with large differences by taking daily, weekly, and monthly fluctuations into account. For example, it compares data from the past week with current data. The matching suggestion proposal unit also analyzes fluctuations between past data and current data and identifies words with large differences based on the fluctuations. For example, it compares trends in past data with trends in current data. In this way, by taking temporal fluctuations into account, it becomes possible to identify words that take into account differences between past and current data.

[0039] When identifying words with large differences, the matching suggestion proposal unit can integrate word vectors of different languages ​​to identify words with large differences in multilingual support. For example, the matching suggestion proposal unit integrates word vectors of different languages ​​to identify words with large differences in multilingual support. For example, it integrates word vectors of English and Japanese. Furthermore, the matching suggestion proposal unit integrates word vectors of multiple languages ​​and identifies words with large differences in multilingual support based on the integrated vector. For example, it integrates word vectors of English, Japanese, and Chinese. Furthermore, the matching suggestion proposal unit integrates word vectors of different languages ​​and identifies words with large differences in multilingual support based on the integrated vector. For example, it integrates word vectors of English and French. In this way, by integrating word vectors of different languages, it becomes possible to identify words with multilingual support.

[0040] When identifying words with large differences, the matching suggestion unit can integrate different data sources to identify more extensive words. For example, the matching suggestion unit integrates social media data and news data to identify words with large differences. For example, it compares Twitter posts with news articles. The matching suggestion unit also integrates web data and social media data to identify words with large differences. For example, it compares blog posts with Facebook posts. The matching suggestion unit also integrates different data sources and identifies words with large differences based on the integrated data. For example, it compares online forum posts with news articles. In this way, by integrating different data sources, it is possible to identify a wider range of words.

[0041] When identifying words with large differences, the matching suggestion unit can take into account the user's behavioral history and identify words with large differences based on the behavioral patterns. The matching suggestion unit, for example, analyzes the user's past behavioral history and identifies words with large differences based on the behavioral patterns. For example, past purchase history and search history are taken into account. The matching suggestion unit also analyzes the user's behavioral patterns and identifies words with large differences based on the patterns. For example, it analyzes the tendency to take specific actions during specific time periods. The matching suggestion unit also analyzes fluctuations in behavioral patterns based on the user's behavioral history and identifies words with large differences based on the fluctuations. For example, it compares past behavioral patterns with current behavioral patterns. In this way, by taking the user's behavioral history into account, it is possible to identify words based on behavioral patterns.

[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 generative AI system can also collect the user's health data and suggest matching suggestions based on their health status. For example, it can collect data from the user's fitness tracker to analyze their exercise habits and sleep patterns. It can also collect the user's food records and calorie intake to suggest healthy lifestyle habits. It can also collect the user's medical records to suggest preventive measures for specific health risks. This makes it possible to provide matching suggestions that take the user's health status into account.

[0044] The generative AI system can also propose matching suggestions based on the user's hobbies and interests. For example, it can collect the user's music streaming service history and analyze their favorite music genres and artists. It can also collect the user's reading history and identify their favorite books and authors. It can also collect the user's movie and TV viewing history and analyze their favorite genres and actors. This makes it possible to provide matching suggestions that take the user's hobbies and interests into account.

[0045] The generative AI system can also analyze a user's social network and make suggestions to strengthen social connections. For example, it can analyze a user's social media friendships and suggest friends with common hobbies and interests. It can also analyze a user's relationships with colleagues at work and suggest team-building activities at the workplace. It can also analyze the activities of a user's local community and suggest local events and volunteer activities. This makes it possible to make suggestions to strengthen a user's social connections.

[0046] The generative AI system can also analyze a user's purchasing history to make personalized shopping suggestions. For example, it can analyze a user's past purchasing history to identify their favorite products and brands. It can also analyze the user's purchasing patterns to suggest products suited to specific seasons or events. It can also suggest related products and services based on the user's purchasing history. This makes it possible to make personalized shopping suggestions that take into account the user's purchasing history.

[0047] The generative AI system can also analyze a user's learning history and make personalized learning suggestions. For example, it can analyze a user's online course history and suggest courses based on their interests and skills. It can also analyze a user's reading history and suggest related learning materials and books. It can also analyze a user's learning patterns and suggest effective learning methods and schedules. This makes it possible to make personalized learning suggestions that take into account the user's learning history.

[0048] The generative AI system can also analyze a user's travel history to make personalized travel suggestions. For example, it can analyze a user's past travel history to identify their preferred travel destinations and activities. It can also analyze the user's travel patterns to suggest travel destinations that match specific seasons or events. It can also suggest related travel destinations and activities based on the user's travel history. This makes it possible to make personalized travel suggestions that take into account the user's travel history.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The data collection unit collects data from the SB Group and LINE Yahoo!. For example, it collects customer purchase history, search history, user postings, and browsing history. The data collection unit also converts this data into a format that is easy for the generation AI to analyze. Step 2: The word vector calculation unit calculates word vectors based on the collected data. For example, word vectors are generated using algorithms such as Word2Vec or GloVe. The word vector calculation unit also calculates general word vectors from widely used datasets (e.g., Wikipedia or news articles). Step 3: The similarity difference calculation unit calculates the similarity difference between the calculated word vector and a general word vector. For example, the similarity difference is calculated using cosine similarity or Euclidean distance. The similarity difference calculation unit also identifies words with large differences. Step 4: The matching proposal proposal section proposes matching proposals for corporate issues based on the identified words with large differences. For example, it proposes new ideas and solutions using unique words for corporate marketing strategies and product development.

[0051] (Example 2) The generative AI system according to an embodiment of the present invention utilizes data held by the SB Group and LINE Yahoo! to propose original and innovative matching, thereby enabling companies to discover new business opportunities and improve their competitiveness.

[0052] The generative AI system according to the embodiment includes a data collection unit, a word vector calculation unit, a similarity difference calculation unit, and a matching proposal proposal unit. The data collection unit collects data from SB Group and LINE Yahoo!. For example, it collects customer purchase history, search history, and user post content and browsing history. The data collection unit also converts this data into a format that is easy for the generative AI to analyze. The word vector calculation unit calculates word vectors based on the collected data. For example, it generates word vectors using algorithms such as Word2Vec or GloVe. The word vector calculation unit also calculates general word vectors from widely used datasets (for example, Wikipedia or news articles). The similarity difference calculation unit calculates the similarity difference between the calculated word vector and the general word vector. For example, it calculates the similarity difference using cosine similarity or Euclidean distance. The similarity difference calculation unit also identifies words with large differences. The matching proposal proposal unit proposes matching proposals for corporate issues based on the identified words with large differences. For example, it proposes new ideas and solutions using unique words in corporate marketing strategies and product development. As a result, the generative AI system according to the embodiment can utilize data from the SB Group and LINE Yahoo! to propose highly original and innovative matches, which can help companies discover new business opportunities and improve their competitiveness.

[0053] The data collection unit incorporates real-time behavioral data of the user to generate more dynamic word vectors. The data collection unit, for example, collects real-time location information from the user's smartphone and generates word vectors based on that data. For example, it analyzes the places the user has visited and the routes they have taken and weights related words. The data collection unit also collects website browsing history and app usage status in real time and generates word vectors based on that data. For example, it analyzes the pages the user has viewed and the content of the apps they have used and weights related words. The data collection unit also collects real-time purchasing behavior data and generates word vectors based on that data. For example, it analyzes information about products and services purchased by the user and weights related words. In this way, by incorporating real-time behavioral data of the user, more dynamic word vectors can be generated.

[0054] The word vector calculation unit can estimate the user's emotional state and weight words based on that emotion. The word vector calculation unit, for example, performs emotion analysis on the user's posted content and comments and weights words based on the emotion score. For example, it weights words with a strong positive emotion highly. The word vector calculation unit also captures the user's facial expression with a camera and estimates the emotional state using facial expression recognition technology. For example, it analyzes smiling and angry facial expressions and weights words based on the emotion score. The word vector calculation unit also records the user's voice and estimates the emotional state using voice analysis technology. For example, it analyzes the tone and speed of the voice and weights words based on the emotion score. This enables more appropriate word weighting by taking the user's emotional state into consideration.

[0055] The data collection unit can take in a user's voice input or image data and generate a multimodal word vector. The data collection unit, for example, converts the user's voice input into text and generates a word vector based on the text data. For example, the data collection unit analyzes the user's utterances using voice recognition technology. The data collection unit also analyzes the user's image data and generates a word vector based on the content. For example, the data collection unit uses image recognition technology to analyze objects and scenes in the image and weight related words. The data collection unit also takes in both voice input and image data and generates a multimodal word vector. For example, the data collection unit analyzes both voice and image data and generates a word vector by integrating information obtained from each data. In this way, multimodal word vectors can be generated by taking in a user's voice input and image data.

[0056] The data collection unit can integrate datasets from different industries to generate more diverse word vectors. For example, the data collection unit integrates medical data and financial data to generate word vectors. For example, medical terms and financial terms are combined to create new word vectors. The data collection unit also integrates educational data and entertainment data to generate word vectors. For example, education-related terms and entertainment-related terms are combined to create new word vectors. The data collection unit also integrates datasets from different industries to generate more diverse word vectors. For example, datasets from multiple industries are combined to create new word vectors. In this way, more diverse word vectors can be generated by integrating datasets from different industries.

[0057] The data collection unit can incorporate the user's social media activity and generate word vectors that take social influence into consideration. The data collection unit, for example, collects the user's social media posting content and generates word vectors based on that data. For example, it analyzes the frequency of posts and the topics of the content. The data collection unit also collects the user's social media engagement data and generates word vectors based on that data. For example, it analyzes the number of likes and shares and weights related words. The data collection unit also takes the user's number of followers and influence into consideration and generates word vectors based on that data. For example, it places importance on the content posted by users with a large number of followers and weights related words. In this way, by incorporating the user's social media activity, it is possible to generate word vectors that take social influence into consideration.

[0058] The similarity difference calculation unit can also calculate the difference between past data and current data, taking into account fluctuations over time. The similarity difference calculation unit, for example, compares past data with current data and calculates the similarity difference taking into account fluctuations over time. For example, data from the past year is compared with current data. The similarity difference calculation unit also calculates the similarity difference taking into account fluctuations on a daily, weekly, or monthly basis. For example, data from the past week is compared with current data. The similarity difference calculation unit also analyzes fluctuations between past data and current data, and calculates the similarity difference based on the fluctuations. For example, the trend of past data is compared with the trend of current data. In this way, the difference between past and current data can be calculated by taking into account fluctuations over time.

[0059] The similarity difference calculation unit can estimate the emotional state of the user and adjust the difference based on the fluctuations in that emotion. The similarity difference calculation unit, for example, estimates the emotional state of the user in real time and adjusts the similarity difference based on the emotion. For example, the difference is increased when the positive emotion is strong. The similarity difference calculation unit also adjusts the similarity difference based on the user's emotional score. For example, the difference is increased when the emotional score is high. The similarity difference calculation unit also analyzes the emotional fluctuations of the user and adjusts the similarity difference based on the fluctuations. For example, the difference is increased when the emotional fluctuations are large. This makes it possible to adjust the difference based on emotional fluctuations by taking the emotional state of the user into consideration.

[0060] The similarity difference calculation unit can integrate word vectors of different languages ​​and perform multilingual difference calculations. The similarity difference calculation unit, for example, integrates word vectors of different languages ​​and calculates similarity differences in multiple languages. For example, it integrates word vectors of English and Japanese. The similarity difference calculation unit also integrates word vectors of multiple languages ​​and calculates similarity differences based on the integrated vector. For example, it integrates word vectors of English, Japanese, and Chinese. The similarity difference calculation unit also integrates word vectors of different languages ​​and calculates similarity differences in multiple languages ​​based on the integrated vector. For example, it integrates word vectors of English and French. In this way, by integrating word vectors of different languages, multilingual difference calculations become possible.

[0061] The similarity difference calculation unit can integrate different data sources and calculate a wider range of differences. For example, the similarity difference calculation unit integrates social media data and news data and calculates the similarity difference. For example, it compares Twitter posts with news articles. The similarity difference calculation unit also integrates web data and social media data and calculates the similarity difference. For example, it compares blog posts with Facebook posts. The similarity difference calculation unit also integrates different data sources and calculates the similarity difference based on the integrated data. For example, it compares online forum posts with news articles. This makes it possible to calculate a wider range of differences by integrating different data sources.

[0062] The similarity difference calculation unit can calculate a difference based on a behavioral pattern by taking into account the user's behavioral history. The similarity difference calculation unit, for example, analyzes the user's past behavioral history and calculates a similarity difference based on the behavioral pattern. For example, past purchase history and search history are taken into account. The similarity difference calculation unit also analyzes the user's behavioral pattern and calculates a similarity difference based on the pattern. For example, it analyzes the tendency to take specific actions during specific time periods. The similarity difference calculation unit also analyzes fluctuations in the behavioral pattern based on the user's behavioral history and calculates a similarity difference based on the fluctuations. For example, it compares past behavioral patterns with current behavioral patterns. This makes it possible to calculate a difference based on a behavioral pattern by taking into account the user's behavioral history.

[0063] The similarity difference calculation unit uses the emotion estimation function to calculate a similarity difference based on the user's emotion, and can identify words that are likely to resonate emotionally. The similarity difference calculation unit, for example, uses the emotion estimation function to calculate a similarity difference based on the user's emotion. For example, a higher weight is assigned to words with stronger positive emotions. The similarity difference calculation unit also identifies words that are likely to resonate emotionally based on the user's emotion score. For example, words with high emotion scores are preferentially selected. The similarity difference calculation unit also analyzes fluctuations in the user's emotion and identifies words that are likely to resonate emotionally based on the fluctuations. For example, words with large emotional fluctuations are identified. This makes it possible to calculate a difference based on the user's emotion, and identify words that are likely to resonate emotionally.

[0064] When identifying words with large differences, the matching suggestion proposal unit can estimate the user's emotional state and prioritize identifying emotionally positive words. The matching suggestion proposal unit, for example, estimates the user's emotional state in real time and prioritizes identifying words with strong positive emotions. For example, it prioritizes selecting words with high emotional scores. The matching suggestion proposal unit also identifies emotionally positive words based on the user's emotional score. For example, it prioritizes selecting words with high emotional scores. The matching suggestion proposal unit also analyzes fluctuations in the user's emotions and identifies emotionally positive words based on the fluctuations. For example, it prioritizes selecting words with large emotional fluctuations. In this way, it is possible to prioritize identifying emotionally positive words by taking the user's emotional state into consideration.

[0065] When identifying words with large differences, the matching suggestion proposal unit can take into account temporal fluctuations and the differences between past data and current data. The matching suggestion proposal unit, for example, compares past data with current data and identifies words with large differences by taking temporal fluctuations into account. For example, it compares data from the past year with current data. The matching suggestion proposal unit also identifies words with large differences by taking daily, weekly, and monthly fluctuations into account. For example, it compares data from the past week with current data. The matching suggestion proposal unit also analyzes fluctuations between past data and current data and identifies words with large differences based on the fluctuations. For example, it compares trends in past data with trends in current data. In this way, by taking temporal fluctuations into account, it becomes possible to identify words that take into account differences between past and current data.

[0066] When identifying words with large differences, the matching suggestion proposal unit can integrate word vectors of different languages ​​to identify words with large differences in multilingual support. For example, the matching suggestion proposal unit integrates word vectors of different languages ​​to identify words with large differences in multilingual support. For example, it integrates word vectors of English and Japanese. Furthermore, the matching suggestion proposal unit integrates word vectors of multiple languages ​​and identifies words with large differences in multilingual support based on the integrated vector. For example, it integrates word vectors of English, Japanese, and Chinese. Furthermore, the matching suggestion proposal unit integrates word vectors of different languages ​​and identifies words with large differences in multilingual support based on the integrated vector. For example, it integrates word vectors of English and French. In this way, by integrating word vectors of different languages, it becomes possible to identify words with multilingual support.

[0067] When identifying words with large differences, the matching suggestion unit can integrate different data sources to identify more extensive words. For example, the matching suggestion unit integrates social media data and news data to identify words with large differences. For example, it compares Twitter posts with news articles. The matching suggestion unit also integrates web data and social media data to identify words with large differences. For example, it compares blog posts with Facebook posts. The matching suggestion unit also integrates different data sources and identifies words with large differences based on the integrated data. For example, it compares online forum posts with news articles. In this way, by integrating different data sources, it is possible to identify a wider range of words.

[0068] When identifying words with large differences, the matching suggestion unit can take into account the user's behavioral history and identify words with large differences based on the behavioral patterns. The matching suggestion unit, for example, analyzes the user's past behavioral history and identifies words with large differences based on the behavioral patterns. For example, past purchase history and search history are taken into account. The matching suggestion unit also analyzes the user's behavioral patterns and identifies words with large differences based on the patterns. For example, it analyzes the tendency to take specific actions during specific time periods. The matching suggestion unit also analyzes fluctuations in behavioral patterns based on the user's behavioral history and identifies words with large differences based on the fluctuations. For example, it compares past behavioral patterns with current behavioral patterns. In this way, by taking the user's behavioral history into account, it is possible to identify words based on behavioral patterns.

[0069] The matching proposal proposal unit can use the emotion estimation function to identify words with large differences based on the user's emotion and propose matching proposals that are likely to resonate emotionally. The matching proposal proposal unit, for example, uses the emotion estimation function to identify words with large differences based on the user's emotion. For example, it preferentially selects words with strong positive emotions. The matching proposal proposal unit also proposes matching proposals that are likely to resonate emotionally based on the user's emotion score. For example, it generates matching proposals based on words with high emotion scores. The matching proposal proposal unit also analyzes fluctuations in the user's emotion and proposes matching proposals that are likely to resonate emotionally based on the fluctuations. For example, it generates matching proposals based on words with large emotional fluctuations. This makes it possible to calculate differences based on the user's emotion and propose matching proposals that are likely to resonate emotionally.

[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 generative AI system can also collect the user's health data and suggest matching suggestions based on their health status. For example, it can collect data from the user's fitness tracker to analyze their exercise habits and sleep patterns. It can also collect the user's food records and calorie intake to suggest healthy lifestyle habits. It can also collect the user's medical records to suggest preventive measures for specific health risks. This makes it possible to provide matching suggestions that take the user's health status into account.

[0072] The generative AI system can also propose matching suggestions based on the user's hobbies and interests. For example, it can collect the user's music streaming service history and analyze their favorite music genres and artists. It can also collect the user's reading history and identify their favorite books and authors. It can also collect the user's movie and TV viewing history and analyze their favorite genres and actors. This makes it possible to provide matching suggestions that take the user's hobbies and interests into account.

[0073] The generative AI system can also estimate the user's emotional state and make suggestions for relaxation and stress relief based on that emotion. For example, it can analyze the user's music streaming service history to suggest relaxing music. It can also analyze the user's reading history to suggest books that are useful for stress relief. It can also analyze the user's movie and TV viewing history to suggest relaxing movies and programs. This makes it possible to make suggestions for relaxation and stress relief that take the user's emotional state into account.

[0074] The generative AI system can also analyze a user's social network and make suggestions to strengthen social connections. For example, it can analyze a user's social media friendships and suggest friends with common hobbies and interests. It can also analyze a user's relationships with colleagues at work and suggest team-building activities at the workplace. It can also analyze the activities of a user's local community and suggest local events and volunteer activities. This makes it possible to make suggestions to strengthen a user's social connections.

[0075] The generative AI system can also estimate a user's emotional state and provide mental health support based on that emotion. For example, it can analyze a user's social media posts and suggest relaxation methods if the user is feeling stressed or anxious. It can also analyze a user's voice input to estimate their emotional state and suggest consulting a mental health professional if necessary. It can also analyze a user's behavioral patterns and provide mental health support based on emotional fluctuations. This makes it possible to provide mental health support that takes into account the user's emotional state.

[0076] The generative AI system can also analyze a user's purchasing history to make personalized shopping suggestions. For example, it can analyze a user's past purchasing history to identify their favorite products and brands. It can also analyze the user's purchasing patterns to suggest products suited to specific seasons or events. It can also suggest related products and services based on the user's purchasing history. This makes it possible to make personalized shopping suggestions that take into account the user's purchasing history.

[0077] The generative AI system can also estimate the user's emotional state and suggest entertainment based on that emotion. For example, it can analyze the user's music streaming service history and suggest music that matches their emotional state. It can also analyze the user's movie and TV viewing history and suggest movies and programs that match their emotional state. It can also analyze the user's game play history and suggest games that match their emotional state. This makes it possible to suggest entertainment that takes the user's emotional state into account.

[0078] The generative AI system can also analyze a user's learning history and make personalized learning suggestions. For example, it can analyze a user's online course history and suggest courses based on their interests and skills. It can also analyze a user's reading history and suggest related learning materials and books. It can also analyze a user's learning patterns and suggest effective learning methods and schedules. This makes it possible to make personalized learning suggestions that take into account the user's learning history.

[0079] The generative AI system can also estimate the user's emotional state and provide feedback based on that emotion. For example, it can analyze the user's social media posts and provide positive feedback. It can also analyze the user's voice input and provide encouraging words based on the user's emotional state. It can also analyze the user's behavioral patterns and provide appropriate feedback based on emotional fluctuations. This makes it possible to provide feedback that takes the user's emotional state into consideration.

[0080] The generative AI system can also analyze a user's travel history to make personalized travel suggestions. For example, it can analyze a user's past travel history to identify their preferred travel destinations and activities. It can also analyze the user's travel patterns to suggest travel destinations that match specific seasons or events. It can also suggest related travel destinations and activities based on the user's travel history. This makes it possible to make personalized travel suggestions that take into account the user's travel history.

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

[0082] Step 1: The data collection unit collects data from the SB Group and LINE Yahoo!. For example, it collects customer purchase history, search history, user postings, and browsing history. The data collection unit also converts this data into a format that is easy for the generation AI to analyze. Step 2: The word vector calculation unit calculates word vectors based on the collected data. For example, word vectors are generated using algorithms such as Word2Vec or GloVe. The word vector calculation unit also calculates general word vectors from widely used datasets (e.g., Wikipedia or news articles). Step 3: The similarity difference calculation unit calculates the similarity difference between the calculated word vector and a general word vector. For example, the similarity difference is calculated using cosine similarity or Euclidean distance. The similarity difference calculation unit also identifies words with large differences. Step 4: The matching proposal proposal section proposes matching proposals for corporate issues based on the identified words with large differences. For example, it proposes new ideas and solutions using unique words for corporate marketing strategies and product development.

[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, the 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 data collection unit that collects data from specific corporate groups and specific data providers; a word vector calculation unit that calculates word vectors based on the data collected by the data collection unit; a similarity difference calculation unit that calculates a similarity difference between the word vector calculated by the word vector calculation unit and a general word vector; a matching proposal proposal unit that proposes matching proposals for company issues, focusing on words with large similarity differences calculated by the similarity difference calculation unit; A system characterized by:

2. The data collection unit Incorporating real-time user behavior data to generate more dynamic word vectors 2. The system of claim 1.

3. The data collection unit Integrate datasets from different industries to generate more word vectors 2. The system of claim 1.

4. The similarity difference calculation unit The word vectors from different languages ​​are integrated to perform multilingual difference calculations.

2. The system of claim 1.

5. The matching proposal proposal unit When identifying the words with large differences, the emotional state of the user is estimated, and emotionally positive words are preferentially identified.

2. The system of claim 1.

6. The word vector calculation unit Estimating the user's emotional state and weighting the words based on that emotion 2. The system of claim 1.

7. The similarity difference calculation unit Estimate the user's emotional state and adjust the difference based on the emotional fluctuations 2. The system of claim 1.

8. The matching proposal proposal unit Identify words with large differences based on user sentiment and propose matching suggestions that are likely to resonate emotionally 2. The system of claim 1.

Images