System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring hobby / interest information from each end user terminal; means for storing the acquired hobby / interest information in a database; means for cleansing and normalizing the hobby / interest information stored in the database; means including generative artificial intelligence for calculating similarity of the cleansed and normalized hobby / interest information; means for grouping end users based on the similarity and automatically generating a circle; means for notifying a corresponding end user terminal of a newly generated circle; and means for receiving an intention to participate in the circle from the end user.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] In large companies, connections between employees tend to be weak, and lack of communication is an issue. In particular, there are few opportunities for new employees and employees from different departments to come into contact with each other, and there is a need to promote communication to improve cooperation and efficiency throughout the company. In addition, there is a lack of opportunities for employees to interact based on their individual hobbies and interests, which affects their ability to refresh themselves outside of work and improve their motivation. [Means for solving the problem]

[0005] The present invention is a system that includes a means for acquiring hobby and interest information from each end user terminal and storing it in a database, a means for cleansing and normalizing the acquired hobby and interest information, a means including a generating artificial intelligence for calculating the similarity of the normalized information, a means for grouping end users based on the similarity and automatically generating circles, a means for notifying the corresponding end user terminal of the newly generated circle, and a means for accepting an intention from the end user to join the circle.

[0006] This system allows employees to automatically connect with other employees who share the same hobbies and interests, creating new opportunities for communication. As a result, it is expected that connections between employees will be strengthened, work efficiency will be improved, motivation will increase, and cooperation will be promoted throughout the company.

[0007] "End User Device" means an electronic device, such as a computer, smartphone, or tablet, that a User uses to enter their Hobbies and Interests Information.

[0008] "Hobbies and Interests Information" refers to information about personal interests and activities entered by the End User, such as reading, sports, watching movies, etc.

[0009] "Database" means an information storage system that organizes and stores collected hobbies and interests information for later access and manipulation.

[0010] "Cleansing" is the process of modifying, removing, or transforming data to ensure its consistency, accuracy, and completeness.

[0011] "Normalization" is the process of converting data into a uniform format to ensure data consistency and compatibility.

[0012] "Generative artificial intelligence" is a program that uses techniques such as machine learning and natural language processing to analyze data and automatically perform specific tasks.

[0013] "Similarity" is an index that measures how similar two or more pieces of data (hobbies and interests) are, and evaluates whether they have common characteristics or elements.

[0014] "Grouping" is the process of integrating the hobbies and interests of different users to form a common group (circle) based on similarity.

[0015] A "circle" is a small group of end users who share common hobbies and interests and who come together to interact and exchange information.

[0016] "Notification" is the process by which the system transmits information such as the creation or modification of a circle to the end user terminal.

[0017] "Intention to participate" is an act by an end user expressing their intention to participate in a newly created circle. [Brief explanation of the drawings]

[0018] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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, a 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), and an APU (Accelerated Processing Unit).

[0022] 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.

[0023] 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.

[0024] 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), Bluetooth (registered trademark), etc.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] 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.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses this information to automatically create circles with members who share the same interests. Below are the methods for implementing this system and specific examples.

[0040] Obtaining information about hobbies and interests

[0041] First, a user inputs information about their hobbies and interests on their device (PC, smartphone, tablet, etc.). For example, User A inputs "reading" and "hiking" as their hobbies. Next, the device sends this input information to the server.

[0042] Storage in the database

[0043] The server stores the received hobby and interest information in a database, which stores each user's ID and the corresponding hobby and interest information.

[0044] Data cleansing and normalization

[0045] Periodically, the server reads all user interest information from the database and performs cleansing and normalization to ensure the data is consistent and accurate, for example by correcting spelling and unifying synonyms.

[0046] Similarity calculation using generative artificial intelligence

[0047] Next, the server passes the normalized hobby and interest information to a generation AI that calculates the similarity between each user. This generation AI uses a machine learning model to evaluate the similarity of hobbies. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[0048] Automatic circle generation

[0049] The server then pairs users who meet a certain threshold based on the calculated similarity and automatically creates circles, such as reading and writing circles.

[0050] Circle Notifications

[0051] When a new circle is created, the server sends a circle creation notification to the user, who then displays the notification on the device to notify the user.

[0052] Acceptance of participation intention

[0053] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[0054] Specific examples

[0055] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[0056] The system helps employees automatically build new relationships, promotes communication in the workplace, and helps create a vibrant work environment.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] Users input their hobbies and interests into their devices (PCs, smartphones, tablets, etc.) This information includes the user's favorite activities and areas of interest, such as "reading" or "hiking."

[0060] Step 2:

[0061] The device transmits the entered hobbies and interests to a server using a secure communication protocol.

[0062] Step 3:

[0063] The server validates the received hobbies and interests information and stores it in a database. The validation process ensures that the input data is in the correct format, for example, checking for incorrect formatting or invalid data.

[0064] Step 4:

[0065] The server periodically reads all users' hobbies and interests from the database and cleanses and normalizes them. Cleansing is the process of modifying or deleting data to keep it consistent and accurate, while normalization is the process of standardizing the data into a standard format.

[0066] Step 5:

[0067] The server generates hobby vectors for each user using the normalized hobby and interest information, and calculates the similarity between these vectors using a generative AI. The generative AI uses a machine learning model to evaluate the similarity of hobbies.

[0068] Step 6:

[0069] The server automatically pairs users who have similarities above a certain threshold based on the similarity matrix and creates circles. For example, it groups users A and B, who have similarities, into a single reading / writing circle.

[0070] Step 7:

[0071] After a new circle is created, the server notifies the affected users that a new circle has been created, either by email or via the application's in-app notification system.

[0072] Step 8:

[0073] The device displays the received notification, which includes details about the new circle, and asks the user to confirm their intention to join the new circle.

[0074] Step 9:

[0075] The user confirms the notification and sends their intention to join the circle to the server via their device, where it is recorded in the database.

[0076] Step 10:

[0077] The server saves the updated member list of the circle in its database, and prepares to start circle activities. This officially launches the new circle.

[0078] Through this processing step, the system can create new networking opportunities among employees, resulting in a more vibrant work environment.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Previous systems for strengthening connections between employees had problems with grouping based on individual hobbies and interests, and were unable to automatically generate circles with the right members. Furthermore, manually creating circles required a great deal of effort and time, and did not guarantee appropriate matching between employees. This resulted in ineffective promotion of communication and the building of new relationships.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; and means for accepting intentions to join the new circles from end user terminals. This enables appropriate grouping based on employees' hobbies and interests, and enables the automatic generation and notification of circles and the acceptance of intentions to join to be performed in a consistent manner, thereby promoting communication between employees and building new relationships more effectively.

[0084] "Each end user terminal" is an information technology device used by a user (e.g., a PC, a smartphone, a tablet, etc.).

[0085] "Hobbies and interests information" is data entered by the user about their own hobbies and interests.

[0086] "Database" means the information technology infrastructure for storing and managing Hobbies and Interests Information.

[0087] "Cleansing" is the process of correcting and shaping data to ensure its consistency and accuracy.

[0088] "Normalization" refers to the standardization of data through the unification of different notations and the integration of synonyms.

[0089] "Generative AI" is an AI technology that uses algorithms such as machine learning models to process and analyze data.

[0090] "Similarity" is an index that numerically evaluates the commonality or closeness between different data.

[0091] "Grouping" refers to classifying multiple users into a set based on similarity.

[0092] A "circle" is a group made up of users who share common hobbies and interests.

[0093] "Notification" is a means of communication to inform users of information about a newly created circle.

[0094] "Intention to join" is an act by a user indicating their intention to join a newly created circle.

[0095] MODE FOR CARRYING OUT THE INVENTION

[0096] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between employees, and based on that information, a generative AI automatically creates circles with members who share the same interests. The specific method for implementing this system and its details are described below.

[0097] Obtaining information about hobbies and interests

[0098] First, a user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. Then, they enter information about their hobbies and interests. For example, User A enters "reading" and "hiking" as their hobbies. Next, the device sends this entered information to the server as a POST request.

[0099] Storage in the database

[0100] The server analyzes the received POST request and extracts the hobby and interest information. The information is stored in a database (e.g., MongoDB or PostgreSQL). The database stores each user's ID and the corresponding hobby and interest information.

[0101] Data cleansing and normalization

[0102] The server periodically reads all users' hobby and interest information from the database and cleanses it using Python's Pandas library. This cleansing process involves correcting spelling and standardizing synonyms to ensure consistency and accuracy of the data. For example, "cycling" is normalized as "Cycling."

[0103] Similarity calculation using generative artificial intelligence

[0104] The server passes the cleansed hobby and interest information to a generative AI model in a machine learning framework (e.g., TensorFlow or PyTorch) to calculate the similarity between each user. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between these vectors. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[0105] Automatic circle generation

[0106] The server pairs users who exceed a certain threshold based on the calculated similarity and automatically creates circles with users who share the same hobbies and interests. For example, users who share a high similarity between reading and writing are selected as a pair to create a reading / writing circle.

[0107] Circle Notifications

[0108] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification can be sent by push notification, email, or in-app notification. The device receives this notification and displays it to the user. For example, a notification saying "A new reading and writing circle has been created" will be displayed on User A's smartphone.

[0109] Acceptance of participation intention

[0110] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join to the server. The server records the received intention to join in its database and updates the circle member list.

[0111] Specific examples

[0112] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[0113] Prompt Sentence Examples

[0114] "Please tell me the specific process flow of a system that uses a generative AI model to automatically generate circles based on employees' hobbies and interests and notify them."

[0115] The system is designed to promote communication among employees and enhance the vibrancy of the work environment.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1: Enter and submit your hobbies and interests

[0118] A user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. The user enters information about their hobbies and interests. For example, User A enters their hobbies of "reading" and "hiking." The entered data is temporarily saved within the device. Next, when the user clicks the submit button, the device sends this information to the server as a POST request in JSON format. The input is the user's hobbies and interests, and the output is a POST request to the server.

[0119] Step 2: Store in the database

[0120] The server analyzes the received POST request and extracts hobby and interest information. The extracted information is stored in a database. For example, user IDs and their corresponding hobby information are stored in a table. Databases such as MongoDB and PostgreSQL are used. The input is the hobby and interest information received by the server, and the output is the information stored in the database. Specifically, the server extracts the received data and executes an INSERT query on the database.

[0121] Step 3: Cleanse and normalize the data

[0122] The server periodically reads all users' hobby and interest information from the database. The read data is cleansed using Python's Pandas library, among other tools. This process involves correcting spelling and unifying synonyms. For example, "cycling" and "cycling" are unified as the same hobby. The input is hobby and interest information retrieved from the database, and the output is cleansed and normalized data. Specifically, the server executes a data query and performs data formatting on the retrieved data.

[0123] Step 4: Similarity calculation by generative AI

[0124] The server passes the cleansed hobby and interest information to a generative AI model created using a machine learning framework such as TensorFlow or PyTorch. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between those vectors. For example, it rates the similarity between User A, who likes "reading," and User B, who likes "writing," as high. The input is the cleansed and normalized hobby and interest information, and the output is the calculated similarity score. Specifically, the server passes the data to the generative AI model and obtains the calculation results.

[0125] Step 5: Automatic circle generation

[0126] Based on the calculated similarity score, the server pairs users who exceed a certain threshold and creates new circles with users who share common hobbies and interests. For example, users who share a high similarity between reading and writing are selected to create a reading / writing circle. The input is the similarity score, and the output is the newly created circle information. Specifically, the server applies a grouping algorithm based on the similarity score to create the circle information.

[0127] Step 6: Circle Notifications

[0128] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification is sent via push notification, email, in-app notification, etc. The device receives this notification and displays it to the user. For example, "A new reading and writing circle has been created" is displayed on User A's smartphone. The input is the newly created circle information, and the output is a notification to the user. Specifically, the server generates a notification message and sends it via the notification service.

[0129] Step 7: Accepting participation

[0130] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join information to the server. The server records the received intention to join information in a database and updates the circle member list. The input is the user's intention to join information, and the output is the updated database information. Specifically, the server analyzes the received data and executes an UPDATE query on the database.

[0131] (Application example 1)

[0132] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0133] In modern society, there is little interaction between customers in physical stores, making it difficult to improve customer satisfaction and repeat customer rates. In particular, there are few opportunities for customers with common hobbies or interests to naturally interact with each other, which can lead to a decline in the quality of the store experience. For this reason, there is a need for a system that promotes connections between customers and forms communities within physical stores.

[0134] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0135] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; means for accepting intentions from end users to join the circles; and means for connecting customers with similar hobbies and interests in real time and automatically forming in-store communities. This allows customers to easily meet other customers with common hobbies, enabling the formation of active communities within the physical store.

[0136] An "end user terminal" is a device used by a user to input and receive information, including a smartphone, PC, tablet, etc.

[0137] "Hobbies and Interests Information" refers to information that expresses a user's hobbies and interests, including specific activities, themes, preferences, etc.

[0138] A "database" is an information management system that systematically stores acquired data and makes it easy to search and access.

[0139] "Cleansing" is the process of eliminating errors and redundancies and standardizing data to ensure consistency and accuracy.

[0140] "Normalization" is the process of standardizing data into a uniform format, making it easier to compare and process.

[0141] "Generative AI" refers to AI that uses machine learning models to generate useful information and patterns from input data.

[0142] "Similarity" is an index that indicates how similar two or more data points are, and in this case, it particularly evaluates the commonality of users' hobbies and interests.

[0143] A "circle" is a group of users who share common hobbies or interests, and is a gathering for interacting and sharing information.

[0144] A "notification" is a message or alert that the system uses to inform the user of new information or actions.

[0145] "Intention to participate" is information indicating the user's intention to join a particular circle or group.

[0146] "Real-time" refers to a state in which information is processed immediately and results are reflected almost instantly.

[0147] An "in-store community" is a group formed within a specific physical store that promotes interaction between customers who share common hobbies and interests.

[0148] This invention provides a system that automatically connects customers in a physical store and forms an in-store community. This system is implemented using hardware and software such as a server, end-user terminals, a database, and generative artificial intelligence.

[0149] System Configuration

[0150] The system consists of the following main components:

[0151] 1. End-user Devices

[0152] A device such as a smartphone, PC, or tablet that allows users to input and receive information about their hobbies and interests.

[0153] 2. Server

[0154] It is a central computer system that takes hobbies and interests information, stores it in a database, and processes the data using artificial intelligence to generate it.

[0155] 3. Database

[0156] An information management system for effectively storing, retrieving, and accessing acquired hobbies and interests information.

[0157] 4. Generative Artificial Intelligence

[0158] Uses machine learning models to calculate the similarity of hobbies and interests and group users. Based on cosine similarity calculation.

[0159] Detailed Description of the Invention

[0160] 1. Acquiring information about hobbies and interests

[0161] Users use their own devices to enter information about their hobbies and interests. For example, User A registers "mystery novels" and "literature" as his or her hobbies.

[0162] 2. Storage in the database

[0163] The hobby and interest information acquired by the device is sent to the server, which stores the information in a database.

[0164] 3. Data cleansing and normalization

[0165] The server periodically retrieves all users' hobbies and interests from the database and performs spelling corrections and synonym unification.

[0166] 4. Similarity calculation using generative artificial intelligence

[0167] The server passes the cleansed and normalized data to a generative AI model, which uses cosine similarity to calculate the similarity of hobbies and interests between users.

[0168] 5. Automatic circle generation

[0169] Users with similar interests are grouped together and automatically created into circles, such as a "mystery novel club" or a "literature club."

[0170] 6. Circle Notifications

[0171] The server notifies the relevant end user terminal of the newly created circle and notifies the user.

[0172] 7. Acceptance of participation intention

[0173] The end user receives the notification and sends their intention to join the circle to the server via their device. The server records this information in a database and updates the circle member list.

[0174] Specific examples

[0175] For example, if a user at a bookstore registers "mystery novels" and "literature" as their hobbies, the server will use this information to match them with other users at the same bookstore and automatically create a "mystery novel club." Users will receive a notification about this club and can join the in-store community by indicating their intention to join.

[0176] Prompt Sentence Examples

[0177] "User A has registered 'mystery novels' and 'literature' as his hobbies. Compare this with the hobbies of other users and automatically group users with the same hobbies into circles."

[0178] This system allows customers to easily meet other customers with common interests and form active communities within the physical store.

[0179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0180] Step 1:

[0181] Enter and submit information about your hobbies and interests

[0182] Users enter their hobbies and interests using their own devices (smartphones, PCs, tablets, etc.). The devices acquire the entered information and send it to the server. For example, User A enters "mystery novels" and "literature."

[0183] Input: Hobbies and interests entered by the user into the device

[0184] Output: Sending hobby and interest information from the device to the server

[0185] Step 2:

[0186] Storage in the database

[0187] The server stores the hobby and interest information received from the device in a database. This database stores each user's ID and the corresponding hobby and interest information.

[0188] Input: Hobbies and interests sent from your device

[0189] Output: Hobbies and interests stored in a database

[0190] Step 3:

[0191] Data cleansing and normalization

[0192] The server periodically reads the hobbies and interests information from the database and cleanses and normalizes it, correcting spelling errors and standardizing synonyms to ensure the data is consistent and accurate.

[0193] Input: Hobbies and interests read from the database

[0194] Output: Cleansed and normalized hobbies and interests

[0195] Step 4:

[0196] Similarity calculation

[0197] The server passes the cleansed and normalized hobby and interest information to the generative AI model, which then calculates the similarity, using cosine similarity to evaluate the commonality of interests between users.

[0198] Input: Cleansed and normalized hobbies and interests

[0199] Output: Similarity scores between each user

[0200] Step 5:

[0201] Automatic circle generation

[0202] The server then groups users who exceed a certain threshold based on the calculated similarity and automatically generates circles, such as a "mystery novel club" or a "literature lovers club."

[0203] Input: Similarity score between each user

[0204] Output: A list of generated circles

[0205] Step 6:

[0206] Circle Notifications

[0207] The server notifies the corresponding end user terminal of the newly created circle, and the user receives a notification of the circle creation.

[0208] Input: A list of generated circles

[0209] Output: Sending a circle creation notification to the device

[0210] Step 7:

[0211] Acceptance of participation intention

[0212] When a user receives the notification of the creation of a circle, they send their intention to join the circle to the server via their device. The server records this information in its database and updates the circle member list.

[0213] Input: User's participation intention information

[0214] Output: Join intentions stored in the database and an updated list of circle members

[0215] These steps enable the system to automatically foster connections between customers within the physical store and create an active in-store community.

[0216] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0217] This invention combines a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses that information to automatically create circles with members who share the same interests using a generation AI, with an emotion engine that recognizes the user's emotions. Specific methods and examples for implementing this system are shown below.

[0218] Acquiring Hobbies and Interests Information and Emotion Recognition

[0219] First, a user inputs their hobbies and interests on their device (PC, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "excited" or "relaxed").

[0220] Data transmission and storage

[0221] The device transmits the entered hobbies and interests and the recorded emotional state to the server using a secure communication protocol.

[0222] Storage in the database

[0223] The server stores the received hobby / interest information and emotional state in a database, which stores each user's ID and their corresponding hobby / interest information and emotional state.

[0224] Data cleansing and normalization

[0225] Periodically, the server reads all users' interests and emotional states from the database, cleansing and normalizing them.

[0226] Similarity calculation using generative artificial intelligence

[0227] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generation AI. The generation AI uses a machine learning model to evaluate the similarity of hobbies and emotions. For example, it calculates that User A, who likes "reading" and finds "relaxing," and User B, who likes "writing" and finds "relaxing" have a high similarity.

[0228] Automatic circle generation

[0229] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[0230] Circle Notifications

[0231] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[0232] Acceptance of participation intention

[0233] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[0234] Specific examples

[0235] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and similarity is calculated. Because the similarity between reading and writing and the emotional state of being relaxed is high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[0236] This system not only allows employees to automatically build new relationships, but also allows for deeper, more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[0237] The processing flow will be explained below.

[0238] Step 1:

[0239] Users enter their hobbies and interests into their devices (PC, smartphone, tablet, etc.) Specifically, they register hobbies such as "reading" or "hiking" using a dedicated form or application.

[0240] Step 2:

[0241] As the device receives information about hobbies and interests, it activates an emotion engine to recognize the user's emotional state. For example, it uses cameras and sensors to analyze the user's facial expressions and voice to determine emotional states such as "relaxed" or "excited."

[0242] Step 3:

[0243] The device transmits the input information about hobbies and interests and the recognized emotional state to a server using a secure communication protocol to prevent unauthorized access and information leaks.

[0244] Step 4:

[0245] The server validates the received hobbies, interests, and emotional state information to ensure that it is in the correct format, e.g., by checking for incorrect data formatting or inappropriate information.

[0246] Step 5:

[0247] The server stores the verified data in a database, which stores each user's ID and corresponding hobbies, interests, and emotional state.

[0248] Step 6:

[0249] The server periodically reads all users' interests and emotional states from the database and performs cleansing and normalization, correcting spelling and removing unnecessary data to ensure consistency and accuracy of the data.

[0250] Step 7:

[0251] The server uses the normalized information to generate interest vectors and emotion vectors for each user, and uses a generative AI to calculate the similarity between these vectors. The machine learning model evaluates the similarity between interest and emotion.

[0252] Step 8:

[0253] The server pairs users who exceed a certain threshold based on the calculated similarity matrix and automatically generates circles with common hobbies and emotional states. For example, if there is a user whose hobbies are "reading" and "writing" and who is in a "relaxed" state, a reading / writing circle will be generated.

[0254] Step 9:

[0255] The server notifies the corresponding users of the newly created circle information via email or the notification function within the application.

[0256] Step 10:

[0257] The device displays the received notification and provides the user with details about the new circle, which the user can then review and express their intention to join.

[0258] Step 11:

[0259] Users can send their intention to join a circle to the server via their device by clicking an approval button or sending a message requesting participation.

[0260] Step 12:

[0261] The server records the intention to join in its database and updates the circle's member list, so the newly created circle is ready to officially begin its activities.

[0262] Specific examples

[0263] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as "relaxed" by the emotion engine, and similarly user B registers "writing" and "cycling" as hobbies and is recognized as "relaxed," the server stores this data in the database. After cleansing and normalization, the similarity of hobbies and emotions is calculated, and a reading / writing circle is automatically created. A notification of the new circle is sent to user A and user B, and after they confirm their intention to join, the circle member list is updated and the circle is officially launched.

[0264] This system can improve the quality of communication in the workplace by strengthening connections between employees and enabling deeper interactions that take into account their emotional states.

[0265] Example 2

[0266] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0267] Strengthening connections between employees and improving the quality of communication within a company is an important issue in many workplaces. Promoting interaction between employees with similar hobbies and interests is particularly expected to build deeper relationships of trust. However, conventional methods often involve manually ascertaining employees' hobbies and interests and grouping them based on that information, making it difficult to implement efficiently. Furthermore, creating groups without considering the user's emotional state can sometimes hinder smooth interaction. The present invention aims to solve these problems.

[0268] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each user's terminal, means for the terminal to recognize and record the user's emotional state, means for transmitting the acquired hobby and interest information and emotional state data to the server, means for storing the transmitted data in a database, means for cleansing and normalizing the data stored in the database, means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information and emotional state, means for grouping users based on the similarity and automatically generating a circle, means for notifying the corresponding user terminal of the newly generated circle, and means for accepting the user's intention to join the circle. This allows users to be appropriately grouped based on their hobby and interest information and emotional state, enabling interaction that enhances emotional empathy.

[0269] "User's device" refers to a device used by a user to input information or perform emotion recognition, such as a personal computer, smartphone, or tablet.

[0270] An "emotion engine" refers to software or hardware that uses a camera or microphone to analyze a user's facial expressions and tone of voice to recognize and record their emotional state in real time.

[0271] "Database" refers to a collection of hobbies, interests, and emotional state data stored in a structured, searchable, and manipulable form.

[0272] "Cleansing" refers to the process of correcting or removing incomplete, redundant, or erroneous data to ensure data accuracy and consistency.

[0273] "Normalization" refers to the process of converting data into a consistent format to facilitate comparison and analysis.

[0274] "Generative AI" refers to an AI system that uses techniques such as machine learning and natural language processing to generate and analyze meaningful information from input data.

[0275] "Similarity" is a numerical representation of the relevance and commonalities between data, and in this system it is an index that evaluates the degree of commonality in hobby and interest information and emotional states in particular.

[0276] A "Circle" is a collection of users automatically grouped together based on shared hobbies, interests, and emotional states.

[0277] "Notification" refers to the means by which a user is notified that a new Circle has been created, such as an email or in-app message.

[0278] "Intention to participate" refers to a user's expression of intent to join a circle, and the circle member list is updated based on this.

[0279] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and based on that information, a generation AI automatically creates circles with members who share the same interests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it enables deeper and more empathetic interactions.

[0280] Acquiring Hobbies and Interests Information and Emotion Recognition

[0281] First, a user inputs information about their hobbies and interests on their device (personal computer, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. The emotion engine can use, for example, the API of Microsoft Azure Cognitive Services. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "relaxed").

[0282] Data transmission and storage

[0283] The device transmits the acquired hobbies, interests, and emotional state to a server using a secure communication protocol (e.g., HTTPS). The transmitted data also includes the user's ID.

[0284] Storage in the database

[0285] The server stores the received hobby / interest information and emotional state in a database. The stored data is saved corresponding to the user ID.

[0286] Data cleansing and normalization

[0287] The server periodically reads all user data from the database and cleanses and normalizes it. Cleansing is the process of correcting or removing incomplete or redundant data. Normalization is the process of transforming data into a consistent form.

[0288] Similarity calculation using generative artificial intelligence

[0289] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generative AI (e.g., a machine learning model such as GPT-4).

[0290] Example prompt sentence:

[0291] "User A: Reading, relaxing; User B: Writing, relaxing. Do they have the same interests?"

[0292] Automatic circle generation

[0293] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[0294] Circle Notifications

[0295] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[0296] Acceptance of participation intention

[0297] The user confirms the notification and sends their intention to join the circle to the server via their device. The server stores the intention to join in the database and updates the circle member list.

[0298] Specific example explanation

[0299] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and a similarity calculation is performed by the generation AI. Because the similarity between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle is sent to users A and B. Upon receiving the notification, users A and B decide to join the circle.

[0300] This system not only allows employees to automatically build new relationships, but also allows for more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Step 1:

[0303] The user inputs information about their hobbies and interests into their device and activates the device's emotion recognition engine. For example, the user inputs hobby information such as "reading" or "hiking," and their emotional state (e.g., "relaxed") is recorded in real time using the device's camera and microphone. The device then prepares data based on the hobby and interest information entered by the user and the emotional state detected by the emotion recognition engine.

[0304] Input: User-entered hobbies and interests, and emotional state captured by the device's camera and microphone.

[0305] Output: Prepared data containing hobbies, interests, and emotional states.

[0306] Step 2:

[0307] The device sends the prepared data to the server using a secure communication protocol (e.g., HTTPS). The data sent includes the user's ID. This communication process ensures that the data is sent safely while protecting the user's privacy.

[0308] Input: Hobbies and interests, emotional state, user ID.

[0309] Output: User information data sent to the server.

[0310] Step 3:

[0311] The server verifies the received data and stores it in the database. Specifically, it creates a new entry corresponding to the user ID and stores the hobbies, interests, and emotional state. The data is stored in the database to ensure data consistency and access efficiency.

[0312] Input: User information data sent from the device.

[0313] Output: User information stored in the database.

[0314] Step 4:

[0315] The server periodically reads all user data from the database, cleansing and normalizing it. Cleansing corrects incomplete or incorrect data, and normalization converts it into a uniform format to ensure data consistency. This is done using libraries such as Python's pandas.

[0316] Input: User data stored in the database.

[0317] Output: Cleansed and normalized user data.

[0318] Step 5:

[0319] The server generates hobby vectors and emotion vectors for each user based on the cleansed and normalized data. The generated vectors are input into a generative AI model (e.g., GPT-4) to calculate the similarity between each vector. This quantifies the commonality and degree of interest agreement between users.

[0320] Input: Cleansed and normalized user data.

[0321] Output: The calculated similarity score between users.

[0322] Step 6:

[0323] The server automatically groups users who exceed a certain threshold based on the calculated similarity score and creates new circles. The server also takes into account emotional states in the similarity score, ensuring that users who can empathize with each other gather together.

[0324] Input: Similarity score.

[0325] Output: Auto-generated circle information.

[0326] Step 7:

[0327] The server notifies the user terminal of the new circle information that has been created. This notification is sent by email or within an application, informing the user that a new circle has been created.

[0328] Input: Auto-generated circle information.

[0329] Output: Notification message to the user's terminal.

[0330] Step 8:

[0331] The user receives the notification and sends their intention to join the circle to the server via their device. The server confirms the intention and updates the database entry to update the circle's member list.

[0332] Input: User's willingness to participate.

[0333] Output: Updated circle member list.

[0334] (Application example 2)

[0335] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0336] There is a need to promote communication between workers in factories, improve the work environment, and provide efficient work support.The purpose of this invention is to provide a system that utilizes information on workers' hobbies and interests and their emotional states to strengthen connections between workers and improve the quality of their refreshment time.

[0337] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each end user terminal, means for storing the acquired hobby and interest information and the user's emotional state in a database, and means for cleansing and normalizing the hobby and interest information and emotional state stored in the database. This enables workers in a factory to find colleagues who share common hobbies and interests and similar emotional states, and to more actively enjoy their refreshment time and work time.

[0338] "End-user device" means an electronic device used by a user to input and check information on hobbies, interests, and emotional states, including smartphones, PCs, tablets, etc.

[0339] "Hobbies and interests" refers to information about activities and themes that interest a user, and is stored in a database as part of the user's profile.

[0340] "Emotional state" is information that indicates the user's current emotional state, and is analyzed and recorded using an emotion recognition engine.

[0341] "Database" refers to an information storage system for storing and managing acquired hobby and interest information and emotional states.

[0342] "Cleansing" is the process of formatting information stored in a database and converting it into an accurate and usable format.

[0343] "Normalization" is the process of converting data of different formats into a consistent standard format to facilitate calculations and analysis.

[0344] "Similarity" is an index that numerically indicates the similarity between different data, and is calculated using a method such as cosine similarity.

[0345] "Generative AI" is an AI system that uses machine learning models to calculate the similarity of data and output analysis results.

[0346] A "circle" is a group formed by users who share common hobbies and interests, with the aim of engaging in hobby activities and interacting with others.

[0347] "Notification" is a function that sends information from the server to the end user terminal to notify the user of the creation of new circles and other important information.

[0348] "Intention to participate" is an expression of a user's desire to participate in a circle, and is transmitted to the server via the end user terminal.

[0349] This invention relates to a system for improving communication and work efficiency among workers in a factory. Specifically, it is a system that recognizes information about the hobbies and interests of workers and their emotional states, and automatically generates circles based on this information.

[0350] First, a user enters their hobbies and interests using their device. At the same time, the device activates an emotion engine to recognize the user's emotional state. For example, the device uses the camera and sensors of a smartphone or tablet to analyze the user's facial expressions and tone of voice and record their current emotional state.

[0351] The acquired hobby / interest information and emotional state are sent to the server via a secure communication protocol. The server stores this information in a database. The database stores each user's ID and their corresponding hobby / interest information and emotional state.

[0352] Next, the server periodically reads all users' data from the database and performs cleansing and normalization processes. Based on the normalized data, the server uses generative artificial intelligence to generate each user's interest vector and emotion vector, and calculates the similarity between these vectors. This similarity is calculated using cosine similarity in particular.

[0353] Based on the results of the similarity calculation, the server pairs users who have a high similarity level above a certain threshold and automatically generates a circle. This circle brings together users who share common hobbies and interests and who are in a similar emotional state. For example, users who enjoy reading or hiking and who enjoy relaxation will be given priority.

[0354] When a new circle is created, the server sends a notification to the end-user device of the user. The user can then express their intention to join the circle through a dedicated interface. Once the intention to join is sent to the server, the information is also saved in the database and the circle member list is updated.

[0355] In this way, the present invention allows workers in a factory to find other workers who share common hobbies and interests and work together, thereby realizing a better working environment and communication.

[0356] As a specific example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in a database. The data is then cleansed and normalized, and similarities are calculated. Because the similarities between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[0357] An example of a prompt sentence is, "If user A enjoys reading and hiking and is in a relaxed state, please find other users with similar hobbies and create a circle."

[0358] This invention utilizes generative AI models and emotion recognition technology to promote communication between workers in factories, improve production efficiency, and provide a comfortable working environment.

[0359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0360] Step 1:

[0361] The user uses the end-user device to input information about their hobbies and interests. The input data can be information about hobbies such as reading or hiking. At the same time, the device uses a camera and microphone to record the user's facial expressions and tone of voice, which are then analyzed by the emotion engine. For example, it can determine whether the user is relaxed.

[0362] Step 2:

[0363] The device sends the acquired hobby / interest information and emotional state to the server. The sent data includes the user ID, hobby / interest information, and emotional state. The server receives this data and stores it in a database. For example, User A's hobby information of reading and hiking and his / her emotional state of relaxation are registered in the database.

[0364] Step 3:

[0365] The server periodically reads all users' hobbies, interests, and emotional states from the database, and cleanses and normalizes the data. For example, it converts information in the same hobby category into a unified format and sorts out duplicate data. This ensures that the data is consistent.

[0366] Step 4:

[0367] The server uses the generative AI model to calculate the similarity between the cleansed and normalized hobby / interest information and emotional states. This calculation is performed using cosine similarity to quantify the similarity between each user's hobby vector and emotional vector. For example, the similarity between reading and writing, and the similarity between the relaxed emotional state are calculated.

[0368] Step 5:

[0369] Based on the similarity calculation results, the server pairs users with high similarities and automatically generates circles. For example, users who share the hobbies of reading and writing and are in a relaxed emotional state are grouped into a circle.

[0370] Step 6:

[0371] The server notifies the target end user device of the newly created circle. For example, a notification that a reading / writing circle has been created is sent to the devices of user A and user B.

[0372] Step 7:

[0373] Users receive the circle creation notification and use their end-user devices to express their intention to join the circle. The user's intention to join is sent from the device to the server, which records the intention to join in the database and updates the circle member list. For example, it is recorded that User A and User B will join a reading and writing circle.

[0374] This allows users to effectively interact with other users who share common hobbies and interests, improving the quality of communication within the factory.

[0375] 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.

[0376] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0377] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0378] [Second embodiment]

[0379] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0380] 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.

[0381] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0382] 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.

[0383] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0384] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0385] 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. 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.

[0386] 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.

[0387] 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 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.

[0388] 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.

[0389] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0390] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0391] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses this information to automatically create circles with members who share the same interests. Below are the methods for implementing this system and specific examples.

[0392] Obtaining information about hobbies and interests

[0393] First, a user inputs information about their hobbies and interests on their device (PC, smartphone, tablet, etc.). For example, User A inputs "reading" and "hiking" as their hobbies. Next, the device sends this input information to the server.

[0394] Storage in the database

[0395] The server stores the received hobby and interest information in a database, which stores each user's ID and the corresponding hobby and interest information.

[0396] Data cleansing and normalization

[0397] Periodically, the server reads all user interest information from the database and performs cleansing and normalization to ensure the data is consistent and accurate, for example by correcting spelling and unifying synonyms.

[0398] Similarity calculation using generative artificial intelligence

[0399] Next, the server passes the normalized hobby and interest information to a generation AI that calculates the similarity between each user. This generation AI uses a machine learning model to evaluate the similarity of hobbies. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[0400] Automatic circle generation

[0401] The server then pairs users who meet a certain threshold based on the calculated similarity and automatically creates circles, such as reading and writing circles.

[0402] Circle Notifications

[0403] When a new circle is created, the server sends a circle creation notification to the user, who then displays the notification on the device to notify the user.

[0404] Acceptance of participation intention

[0405] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[0406] Specific examples

[0407] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[0408] The system helps employees automatically build new relationships, promotes communication in the workplace, and helps create a vibrant work environment.

[0409] The processing flow will be explained below.

[0410] Step 1:

[0411] Users input their hobbies and interests into their devices (PCs, smartphones, tablets, etc.) This information includes the user's favorite activities and areas of interest, such as "reading" or "hiking."

[0412] Step 2:

[0413] The device transmits the entered hobbies and interests to a server using a secure communication protocol.

[0414] Step 3:

[0415] The server validates the received hobbies and interests information and stores it in a database. The validation process ensures that the input data is in the correct format, for example, checking for incorrect formatting or invalid data.

[0416] Step 4:

[0417] The server periodically reads all users' hobbies and interests from the database and cleanses and normalizes them. Cleansing is the process of modifying or deleting data to keep it consistent and accurate, while normalization is the process of standardizing the data into a standard format.

[0418] Step 5:

[0419] The server generates hobby vectors for each user using the normalized hobby and interest information, and calculates the similarity between these vectors using a generative AI. The generative AI uses a machine learning model to evaluate the similarity of hobbies.

[0420] Step 6:

[0421] The server automatically pairs users who have similarities above a certain threshold based on the similarity matrix and creates circles. For example, it groups users A and B, who have similarities, into a single reading / writing circle.

[0422] Step 7:

[0423] After a new circle is created, the server notifies the affected users that a new circle has been created, either by email or via the application's in-app notification system.

[0424] Step 8:

[0425] The device displays the received notification, which includes details about the new circle, and asks the user to confirm their intention to join the new circle.

[0426] Step 9:

[0427] The user confirms the notification and sends their intention to join the circle to the server via their device, where it is recorded in the database.

[0428] Step 10:

[0429] The server saves the updated member list of the circle in its database, and prepares to start circle activities. This officially launches the new circle.

[0430] Through this processing step, the system can create new networking opportunities among employees, resulting in a more vibrant work environment.

[0431] Example 1

[0432] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0433] Previous systems for strengthening connections between employees had problems with grouping based on individual hobbies and interests, and were unable to automatically generate circles with the right members. Furthermore, manually creating circles required a great deal of effort and time, and did not guarantee appropriate matching between employees. This resulted in ineffective promotion of communication and the building of new relationships.

[0434] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0435] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; and means for accepting intentions to join the new circles from end user terminals. This enables appropriate grouping based on employees' hobbies and interests, and enables the automatic generation and notification of circles and the acceptance of intentions to join to be performed in a consistent manner, thereby promoting communication between employees and building new relationships more effectively.

[0436] "Each end user terminal" is an information technology device used by a user (e.g., a PC, a smartphone, a tablet, etc.).

[0437] "Hobbies and interests information" is data entered by the user about their own hobbies and interests.

[0438] "Database" means the information technology infrastructure for storing and managing Hobbies and Interests Information.

[0439] "Cleansing" is the process of correcting and shaping data to ensure its consistency and accuracy.

[0440] "Normalization" refers to the standardization of data through the unification of different notations and the integration of synonyms.

[0441] "Generative AI" is an AI technology that uses algorithms such as machine learning models to process and analyze data.

[0442] "Similarity" is an index that numerically evaluates the commonality or closeness between different data.

[0443] "Grouping" refers to classifying multiple users into a set based on similarity.

[0444] A "circle" is a group made up of users who share common hobbies and interests.

[0445] "Notification" is a means of communication to inform users of information about a newly created circle.

[0446] "Intention to join" is an act by a user indicating their intention to join a newly created circle.

[0447] MODE FOR CARRYING OUT THE INVENTION

[0448] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between employees, and based on that information, a generative AI automatically creates circles with members who share the same interests. The specific method for implementing this system and its details are described below.

[0449] Obtaining information about hobbies and interests

[0450] First, a user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. Then, they enter information about their hobbies and interests. For example, User A enters "reading" and "hiking" as their hobbies. Next, the device sends this entered information to the server as a POST request.

[0451] Storage in the database

[0452] The server analyzes the received POST request and extracts the hobby and interest information. The information is stored in a database (e.g., MongoDB or PostgreSQL). The database stores each user's ID and the corresponding hobby and interest information.

[0453] Data cleansing and normalization

[0454] The server periodically reads all users' hobby and interest information from the database and cleanses it using Python's Pandas library. This cleansing process involves correcting spelling and standardizing synonyms to ensure consistency and accuracy of the data. For example, "cycling" is normalized as "Cycling."

[0455] Similarity calculation using generative artificial intelligence

[0456] The server passes the cleansed hobby and interest information to a generative AI model in a machine learning framework (e.g., TensorFlow or PyTorch) to calculate the similarity between each user. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between these vectors. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[0457] Automatic circle generation

[0458] The server pairs users who exceed a certain threshold based on the calculated similarity and automatically creates circles with users who share the same hobbies and interests. For example, users who share a high similarity between reading and writing are selected as a pair to create a reading / writing circle.

[0459] Circle Notifications

[0460] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification can be sent by push notification, email, or in-app notification. The device receives this notification and displays it to the user. For example, a notification saying "A new reading and writing circle has been created" will be displayed on User A's smartphone.

[0461] Acceptance of participation intention

[0462] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join to the server. The server records the received intention to join in its database and updates the circle member list.

[0463] Specific examples

[0464] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[0465] Prompt Sentence Examples

[0466] "Please tell me the specific process flow of a system that uses a generative AI model to automatically generate circles based on employees' hobbies and interests and notify them."

[0467] The system is designed to promote communication among employees and enhance the vibrancy of the work environment.

[0468] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0469] Step 1: Enter and submit your hobbies and interests

[0470] A user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. The user enters information about their hobbies and interests. For example, User A enters their hobbies of "reading" and "hiking." The entered data is temporarily saved within the device. Next, when the user clicks the submit button, the device sends this information to the server as a POST request in JSON format. The input is the user's hobbies and interests, and the output is a POST request to the server.

[0471] Step 2: Store in the database

[0472] The server analyzes the received POST request and extracts hobby and interest information. The extracted information is stored in a database. For example, user IDs and their corresponding hobby information are stored in a table. Databases such as MongoDB and PostgreSQL are used. The input is the hobby and interest information received by the server, and the output is the information stored in the database. Specifically, the server extracts the received data and executes an INSERT query on the database.

[0473] Step 3: Cleanse and normalize the data

[0474] The server periodically reads all users' hobby and interest information from the database. The read data is cleansed using Python's Pandas library, among other tools. This process involves correcting spelling and unifying synonyms. For example, "cycling" and "cycling" are unified as the same hobby. The input is hobby and interest information retrieved from the database, and the output is cleansed and normalized data. Specifically, the server executes a data query and performs data formatting on the retrieved data.

[0475] Step 4: Similarity calculation by generative AI

[0476] The server passes the cleansed hobby and interest information to a generative AI model created using a machine learning framework such as TensorFlow or PyTorch. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between those vectors. For example, it rates the similarity between User A, who likes "reading," and User B, who likes "writing," as high. The input is the cleansed and normalized hobby and interest information, and the output is the calculated similarity score. Specifically, the server passes the data to the generative AI model and obtains the calculation results.

[0477] Step 5: Automatic circle generation

[0478] Based on the calculated similarity score, the server pairs users who exceed a certain threshold and creates new circles with users who share common hobbies and interests. For example, users who share a high similarity between reading and writing are selected to create a reading / writing circle. The input is the similarity score, and the output is the newly created circle information. Specifically, the server applies a grouping algorithm based on the similarity score to create the circle information.

[0479] Step 6: Circle Notifications

[0480] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification is sent via push notification, email, in-app notification, etc. The device receives this notification and displays it to the user. For example, "A new reading and writing circle has been created" is displayed on User A's smartphone. The input is the newly created circle information, and the output is a notification to the user. Specifically, the server generates a notification message and sends it via the notification service.

[0481] Step 7: Accepting participation

[0482] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join information to the server. The server records the received intention to join information in a database and updates the circle member list. The input is the user's intention to join information, and the output is the updated database information. Specifically, the server analyzes the received data and executes an UPDATE query on the database.

[0483] (Application example 1)

[0484] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0485] In modern society, there is little interaction between customers in physical stores, making it difficult to improve customer satisfaction and repeat customer rates. In particular, there are few opportunities for customers with common hobbies or interests to naturally interact with each other, which can lead to a decline in the quality of the store experience. For this reason, there is a need for a system that promotes connections between customers and forms communities within physical stores.

[0486] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0487] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; means for accepting intentions from end users to join the circles; and means for connecting customers with similar hobbies and interests in real time and automatically forming in-store communities. This allows customers to easily meet other customers with common hobbies, enabling the formation of active communities within the physical store.

[0488] An "end user terminal" is a device used by a user to input and receive information, including a smartphone, PC, tablet, etc.

[0489] "Hobbies and Interests Information" refers to information that expresses a user's hobbies and interests, including specific activities, themes, preferences, etc.

[0490] A "database" is an information management system that systematically stores acquired data and makes it easy to search and access.

[0491] "Cleansing" is the process of eliminating errors and redundancies and standardizing data to ensure consistency and accuracy.

[0492] "Normalization" is the process of standardizing data into a uniform format, making it easier to compare and process.

[0493] "Generative AI" refers to AI that uses machine learning models to generate useful information and patterns from input data.

[0494] "Similarity" is an index that indicates how similar two or more data points are, and in this case, it particularly evaluates the commonality of users' hobbies and interests.

[0495] A "circle" is a group of users who share common hobbies or interests, and is a gathering for interacting and sharing information.

[0496] A "notification" is a message or alert that the system uses to inform the user of new information or actions.

[0497] "Intention to participate" is information indicating the user's intention to join a particular circle or group.

[0498] "Real-time" refers to a state in which information is processed immediately and results are reflected almost instantly.

[0499] An "in-store community" is a group formed within a specific physical store that promotes interaction between customers who share common hobbies and interests.

[0500] This invention provides a system that automatically connects customers in a physical store and forms an in-store community. This system is implemented using hardware and software such as a server, end-user terminals, a database, and generative artificial intelligence.

[0501] System Configuration

[0502] The system consists of the following main components:

[0503] 1. End-user Devices

[0504] A device such as a smartphone, PC, or tablet that allows users to input and receive information about their hobbies and interests.

[0505] 2. Server

[0506] It is a central computer system that takes hobbies and interests information, stores it in a database, and processes the data using artificial intelligence to generate it.

[0507] 3. Database

[0508] An information management system for effectively storing, retrieving, and accessing acquired hobbies and interests information.

[0509] 4. Generative Artificial Intelligence

[0510] Uses machine learning models to calculate the similarity of hobbies and interests and group users. Based on cosine similarity calculation.

[0511] Detailed Description of the Invention

[0512] 1. Acquiring information about hobbies and interests

[0513] Users use their own devices to enter information about their hobbies and interests. For example, User A registers "mystery novels" and "literature" as his or her hobbies.

[0514] 2. Storage in the database

[0515] The hobby and interest information acquired by the device is sent to the server, which stores the information in a database.

[0516] 3. Data cleansing and normalization

[0517] The server periodically retrieves all users' hobbies and interests from the database and performs spelling corrections and synonym unification.

[0518] 4. Similarity calculation using generative artificial intelligence

[0519] The server passes the cleansed and normalized data to a generative AI model, which uses cosine similarity to calculate the similarity of hobbies and interests between users.

[0520] 5. Automatic circle generation

[0521] Users with similar interests are grouped together and automatically created into circles, such as a "mystery novel club" or a "literature club."

[0522] 6. Circle Notifications

[0523] The server notifies the relevant end user terminal of the newly created circle and notifies the user.

[0524] 7. Acceptance of participation intention

[0525] The end user receives the notification and sends their intention to join the circle to the server via their device. The server records this information in a database and updates the circle member list.

[0526] Specific examples

[0527] For example, if a user at a bookstore registers "mystery novels" and "literature" as their hobbies, the server will use this information to match them with other users at the same bookstore and automatically create a "mystery novel club." Users will receive a notification about this club and can join the in-store community by indicating their intention to join.

[0528] Prompt Sentence Examples

[0529] "User A has registered 'mystery novels' and 'literature' as his hobbies. Compare this with the hobbies of other users and automatically group users with the same hobbies into circles."

[0530] This system allows customers to easily meet other customers with common interests and form active communities within the physical store.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] Enter and submit information about your hobbies and interests

[0534] Users enter their hobbies and interests using their own devices (smartphones, PCs, tablets, etc.). The devices acquire the entered information and send it to the server. For example, User A enters "mystery novels" and "literature."

[0535] Input: Hobbies and interests entered by the user into the device

[0536] Output: Sending hobby and interest information from the device to the server

[0537] Step 2:

[0538] Storage in the database

[0539] The server stores the hobby and interest information received from the device in a database. This database stores each user's ID and the corresponding hobby and interest information.

[0540] Input: Hobbies and interests sent from your device

[0541] Output: Hobbies and interests stored in a database

[0542] Step 3:

[0543] Data cleansing and normalization

[0544] The server periodically reads the hobbies and interests information from the database and cleanses and normalizes it, correcting spelling errors and standardizing synonyms to ensure the data is consistent and accurate.

[0545] Input: Hobbies and interests read from the database

[0546] Output: Cleansed and normalized hobbies and interests

[0547] Step 4:

[0548] Similarity calculation

[0549] The server passes the cleansed and normalized hobby and interest information to the generative AI model, which then calculates the similarity, using cosine similarity to evaluate the commonality of interests between users.

[0550] Input: Cleansed and normalized hobbies and interests

[0551] Output: Similarity scores between each user

[0552] Step 5:

[0553] Automatic circle generation

[0554] The server then groups users who exceed a certain threshold based on the calculated similarity and automatically generates circles, such as a "mystery novel club" or a "literature lovers club."

[0555] Input: Similarity score between each user

[0556] Output: A list of generated circles

[0557] Step 6:

[0558] Circle Notifications

[0559] The server notifies the corresponding end user terminal of the newly created circle, and the user receives a notification of the circle creation.

[0560] Input: A list of generated circles

[0561] Output: Sending a circle creation notification to the device

[0562] Step 7:

[0563] Acceptance of participation intention

[0564] When a user receives the notification of the creation of a circle, they send their intention to join the circle to the server via their device. The server records this information in its database and updates the circle member list.

[0565] Input: User's participation intention information

[0566] Output: Join intentions stored in the database and an updated list of circle members

[0567] These steps enable the system to automatically foster connections between customers within the physical store and create an active in-store community.

[0568] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0569] This invention combines a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses that information to automatically create circles with members who share the same interests using a generation AI, with an emotion engine that recognizes the user's emotions. Specific methods and examples for implementing this system are shown below.

[0570] Acquiring Hobbies and Interests Information and Emotion Recognition

[0571] First, a user inputs their hobbies and interests on their device (PC, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "excited" or "relaxed").

[0572] Data transmission and storage

[0573] The device transmits the entered hobbies and interests and the recorded emotional state to the server using a secure communication protocol.

[0574] Storage in the database

[0575] The server stores the received hobby / interest information and emotional state in a database, which stores each user's ID and their corresponding hobby / interest information and emotional state.

[0576] Data cleansing and normalization

[0577] Periodically, the server reads all users' interests and emotional states from the database, cleansing and normalizing them.

[0578] Similarity calculation using generative artificial intelligence

[0579] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generation AI. The generation AI uses a machine learning model to evaluate the similarity of hobbies and emotions. For example, it calculates that User A, who likes "reading" and finds "relaxing," and User B, who likes "writing" and finds "relaxing" have a high similarity.

[0580] Automatic circle generation

[0581] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[0582] Circle Notifications

[0583] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[0584] Acceptance of participation intention

[0585] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[0586] Specific examples

[0587] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and similarity is calculated. Because the similarity between reading and writing and the emotional state of being relaxed is high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[0588] This system not only allows employees to automatically build new relationships, but also allows for deeper, more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[0589] The processing flow will be explained below.

[0590] Step 1:

[0591] Users enter their hobbies and interests into their devices (PC, smartphone, tablet, etc.) Specifically, they register hobbies such as "reading" or "hiking" using a dedicated form or application.

[0592] Step 2:

[0593] As the device receives information about hobbies and interests, it activates an emotion engine to recognize the user's emotional state. For example, it uses cameras and sensors to analyze the user's facial expressions and voice to determine emotional states such as "relaxed" or "excited."

[0594] Step 3:

[0595] The device transmits the input information about hobbies and interests and the recognized emotional state to a server using a secure communication protocol to prevent unauthorized access and information leaks.

[0596] Step 4:

[0597] The server validates the received hobbies, interests, and emotional state information to ensure that it is in the correct format, e.g., by checking for incorrect data formatting or inappropriate information.

[0598] Step 5:

[0599] The server stores the verified data in a database, which stores each user's ID and corresponding hobbies, interests, and emotional state.

[0600] Step 6:

[0601] The server periodically reads all users' interests and emotional states from the database and performs cleansing and normalization, correcting spelling and removing unnecessary data to ensure consistency and accuracy of the data.

[0602] Step 7:

[0603] The server uses the normalized information to generate interest vectors and emotion vectors for each user, and uses a generative AI to calculate the similarity between these vectors. The machine learning model evaluates the similarity between interest and emotion.

[0604] Step 8:

[0605] The server pairs users who exceed a certain threshold based on the calculated similarity matrix and automatically generates circles with common hobbies and emotional states. For example, if there is a user whose hobbies are "reading" and "writing" and who is in a "relaxed" state, a reading / writing circle will be generated.

[0606] Step 9:

[0607] The server notifies the corresponding users of the newly created circle information via email or the notification function within the application.

[0608] Step 10:

[0609] The device displays the received notification and provides the user with details about the new circle, which the user can then review and express their intention to join.

[0610] Step 11:

[0611] Users can send their intention to join a circle to the server via their device by clicking an approval button or sending a message requesting participation.

[0612] Step 12:

[0613] The server records the intention to join in its database and updates the circle's member list, so the newly created circle is ready to officially begin its activities.

[0614] Specific examples

[0615] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as "relaxed" by the emotion engine, and similarly user B registers "writing" and "cycling" as hobbies and is recognized as "relaxed," the server stores this data in the database. After cleansing and normalization, the similarity of hobbies and emotions is calculated, and a reading / writing circle is automatically created. A notification of the new circle is sent to user A and user B, and after they confirm their intention to join, the circle member list is updated and the circle is officially launched.

[0616] This system can improve the quality of communication in the workplace by strengthening connections between employees and enabling deeper interactions that take into account their emotional states.

[0617] Example 2

[0618] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0619] Strengthening connections between employees and improving the quality of communication within a company is an important issue in many workplaces. Promoting interaction between employees with similar hobbies and interests is particularly expected to build deeper relationships of trust. However, conventional methods often involve manually ascertaining employees' hobbies and interests and grouping them based on that information, making it difficult to implement efficiently. Furthermore, creating groups without considering the user's emotional state can sometimes hinder smooth interaction. The present invention aims to solve these problems.

[0620] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each user's terminal, means for the terminal to recognize and record the user's emotional state, means for transmitting the acquired hobby and interest information and emotional state data to the server, means for storing the transmitted data in a database, means for cleansing and normalizing the data stored in the database, means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information and emotional state, means for grouping users based on the similarity and automatically generating a circle, means for notifying the corresponding user terminal of the newly generated circle, and means for accepting the user's intention to join the circle. This allows users to be appropriately grouped based on their hobby and interest information and emotional state, enabling interaction that enhances emotional empathy.

[0621] "User's device" refers to a device used by a user to input information or perform emotion recognition, such as a personal computer, smartphone, or tablet.

[0622] An "emotion engine" refers to software or hardware that uses a camera or microphone to analyze a user's facial expressions and tone of voice to recognize and record their emotional state in real time.

[0623] "Database" refers to a collection of hobbies, interests, and emotional state data stored in a structured, searchable, and manipulable form.

[0624] "Cleansing" refers to the process of correcting or removing incomplete, redundant, or erroneous data to ensure data accuracy and consistency.

[0625] "Normalization" refers to the process of converting data into a consistent format to facilitate comparison and analysis.

[0626] "Generative AI" refers to an AI system that uses techniques such as machine learning and natural language processing to generate and analyze meaningful information from input data.

[0627] "Similarity" is a numerical representation of the relevance and commonalities between data, and in this system it is an index that evaluates the degree of commonality in hobby and interest information and emotional states in particular.

[0628] A "Circle" is a collection of users automatically grouped together based on shared hobbies, interests, and emotional states.

[0629] "Notification" refers to the means by which a user is notified that a new Circle has been created, such as an email or in-app message.

[0630] "Intention to participate" refers to a user's expression of intent to join a circle, and the circle member list is updated based on this.

[0631] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and based on that information, a generation AI automatically creates circles with members who share the same interests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it enables deeper and more empathetic interactions.

[0632] Acquiring Hobbies and Interests Information and Emotion Recognition

[0633] First, a user inputs information about their hobbies and interests on their device (personal computer, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. The emotion engine can use, for example, the API of Microsoft Azure Cognitive Services. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "relaxed").

[0634] Data transmission and storage

[0635] The device transmits the acquired hobbies, interests, and emotional state to a server using a secure communication protocol (e.g., HTTPS). The transmitted data also includes the user's ID.

[0636] Storage in the database

[0637] The server stores the received hobby / interest information and emotional state in a database. The stored data is saved corresponding to the user ID.

[0638] Data cleansing and normalization

[0639] The server periodically reads all user data from the database and cleanses and normalizes it. Cleansing is the process of correcting or removing incomplete or redundant data. Normalization is the process of transforming data into a consistent form.

[0640] Similarity calculation using generative artificial intelligence

[0641] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generative AI (e.g., a machine learning model such as GPT-4).

[0642] Example prompt sentence:

[0643] "User A: Reading, relaxing; User B: Writing, relaxing. Do they have the same interests?"

[0644] Automatic circle generation

[0645] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[0646] Circle Notifications

[0647] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[0648] Acceptance of participation intention

[0649] The user confirms the notification and sends their intention to join the circle to the server via their device. The server stores the intention to join in the database and updates the circle member list.

[0650] Specific example explanation

[0651] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and a similarity calculation is performed by the generation AI. Because the similarity between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle is sent to users A and B. Upon receiving the notification, users A and B decide to join the circle.

[0652] This system not only allows employees to automatically build new relationships, but also allows for more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[0653] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0654] Step 1:

[0655] The user inputs information about their hobbies and interests into their device and activates the device's emotion recognition engine. For example, the user inputs hobby information such as "reading" or "hiking," and their emotional state (e.g., "relaxed") is recorded in real time using the device's camera and microphone. The device then prepares data based on the hobby and interest information entered by the user and the emotional state detected by the emotion recognition engine.

[0656] Input: User-entered hobbies and interests, and emotional state captured by the device's camera and microphone.

[0657] Output: Prepared data containing hobbies, interests, and emotional states.

[0658] Step 2:

[0659] The device sends the prepared data to the server using a secure communication protocol (e.g., HTTPS). The data sent includes the user's ID. This communication process ensures that the data is sent safely while protecting the user's privacy.

[0660] Input: Hobbies and interests, emotional state, user ID.

[0661] Output: User information data sent to the server.

[0662] Step 3:

[0663] The server verifies the received data and stores it in the database. Specifically, it creates a new entry corresponding to the user ID and stores the hobbies, interests, and emotional state. The data is stored in the database to ensure data consistency and access efficiency.

[0664] Input: User information data sent from the device.

[0665] Output: User information stored in the database.

[0666] Step 4:

[0667] The server periodically reads all user data from the database, cleansing and normalizing it. Cleansing corrects incomplete or incorrect data, and normalization converts it into a uniform format to ensure data consistency. This is done using libraries such as Python's pandas.

[0668] Input: User data stored in the database.

[0669] Output: Cleansed and normalized user data.

[0670] Step 5:

[0671] The server generates hobby vectors and emotion vectors for each user based on the cleansed and normalized data. The generated vectors are input into a generative AI model (e.g., GPT-4) to calculate the similarity between each vector. This quantifies the commonality and degree of interest agreement between users.

[0672] Input: Cleansed and normalized user data.

[0673] Output: The calculated similarity score between users.

[0674] Step 6:

[0675] The server automatically groups users who exceed a certain threshold based on the calculated similarity score and creates new circles. The server also takes into account emotional states in the similarity score, ensuring that users who can empathize with each other gather together.

[0676] Input: Similarity score.

[0677] Output: Auto-generated circle information.

[0678] Step 7:

[0679] The server notifies the user terminal of the new circle information that has been created. This notification is sent by email or within an application, informing the user that a new circle has been created.

[0680] Input: Auto-generated circle information.

[0681] Output: Notification message to the user's terminal.

[0682] Step 8:

[0683] The user receives the notification and sends their intention to join the circle to the server via their device. The server confirms the intention and updates the database entry to update the circle's member list.

[0684] Input: User's willingness to participate.

[0685] Output: Updated circle member list.

[0686] (Application example 2)

[0687] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0688] There is a need to promote communication between workers in factories, improve the work environment, and provide efficient work support.The purpose of this invention is to provide a system that utilizes information on workers' hobbies and interests and their emotional states to strengthen connections between workers and improve the quality of their refreshment time.

[0689] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each end user terminal, means for storing the acquired hobby and interest information and the user's emotional state in a database, and means for cleansing and normalizing the hobby and interest information and emotional state stored in the database. This enables workers in a factory to find colleagues who share common hobbies and interests and similar emotional states, and to more actively enjoy their refreshment time and work time.

[0690] "End-user device" means an electronic device used by a user to input and check information on hobbies, interests, and emotional states, including smartphones, PCs, tablets, etc.

[0691] "Hobbies and interests" refers to information about activities and themes that interest a user, and is stored in a database as part of the user's profile.

[0692] "Emotional state" is information that indicates the user's current emotional state, and is analyzed and recorded using an emotion recognition engine.

[0693] "Database" refers to an information storage system for storing and managing acquired hobby and interest information and emotional states.

[0694] "Cleansing" is the process of formatting information stored in a database and converting it into an accurate and usable format.

[0695] "Normalization" is the process of converting data of different formats into a consistent standard format to facilitate calculations and analysis.

[0696] "Similarity" is an index that numerically indicates the similarity between different data, and is calculated using a method such as cosine similarity.

[0697] "Generative AI" is an AI system that uses machine learning models to calculate the similarity of data and output analysis results.

[0698] A "circle" is a group formed by users who share common hobbies and interests, with the aim of engaging in hobby activities and interacting with others.

[0699] "Notification" is a function that sends information from the server to the end user terminal to notify the user of the creation of new circles and other important information.

[0700] "Intention to participate" is an expression of a user's desire to participate in a circle, and is transmitted to the server via the end user terminal.

[0701] This invention relates to a system for improving communication and work efficiency among workers in a factory. Specifically, it is a system that recognizes information about the hobbies and interests of workers and their emotional states, and automatically generates circles based on this information.

[0702] First, a user enters their hobbies and interests using their device. At the same time, the device activates an emotion engine to recognize the user's emotional state. For example, the device uses the camera and sensors of a smartphone or tablet to analyze the user's facial expressions and tone of voice and record their current emotional state.

[0703] The acquired hobby / interest information and emotional state are sent to the server via a secure communication protocol. The server stores this information in a database. The database stores each user's ID and their corresponding hobby / interest information and emotional state.

[0704] Next, the server periodically reads all users' data from the database and performs cleansing and normalization processes. Based on the normalized data, the server uses generative artificial intelligence to generate each user's interest vector and emotion vector, and calculates the similarity between these vectors. This similarity is calculated using cosine similarity in particular.

[0705] Based on the results of the similarity calculation, the server pairs users who have a high similarity level above a certain threshold and automatically generates a circle. This circle brings together users who share common hobbies and interests and who are in a similar emotional state. For example, users who enjoy reading or hiking and who enjoy relaxation will be given priority.

[0706] When a new circle is created, the server sends a notification to the end-user device of the user. The user can then express their intention to join the circle through a dedicated interface. Once the intention to join is sent to the server, the information is also saved in the database and the circle member list is updated.

[0707] In this way, the present invention allows workers in a factory to find other workers who share common hobbies and interests and work together, thereby realizing a better working environment and communication.

[0708] As a specific example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in a database. The data is then cleansed and normalized, and similarities are calculated. Because the similarities between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[0709] An example of a prompt sentence is, "If user A enjoys reading and hiking and is in a relaxed state, please find other users with similar hobbies and create a circle."

[0710] This invention utilizes generative AI models and emotion recognition technology to promote communication between workers in a factory, improving production efficiency and providing a comfortable working environment.

[0711] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0712] Step 1:

[0713] The user uses the end-user device to input information about their hobbies and interests. The input data can be information about hobbies such as reading or hiking. At the same time, the device uses a camera and microphone to record the user's facial expressions and tone of voice, which are then analyzed by the emotion engine. For example, it can determine whether the user is relaxed.

[0714] Step 2:

[0715] The device sends the acquired hobby / interest information and emotional state to the server. The sent data includes the user ID, hobby / interest information, and emotional state. The server receives this data and stores it in a database. For example, User A's hobby information of reading and hiking and his / her emotional state of relaxation are registered in the database.

[0716] Step 3:

[0717] The server periodically reads all users' hobbies, interests, and emotional states from the database, and cleanses and normalizes the data. For example, it converts information in the same hobby category into a unified format and sorts out duplicate data. This ensures that the data is consistent.

[0718] Step 4:

[0719] The server uses the generative AI model to calculate the similarity between the cleansed and normalized hobby / interest information and emotional states. This calculation is performed using cosine similarity to quantify the similarity between each user's hobby vector and emotional vector. For example, the similarity between reading and writing, and the similarity between the relaxed emotional state are calculated.

[0720] Step 5:

[0721] Based on the similarity calculation results, the server pairs users with high similarities and automatically generates circles. For example, users who share the hobbies of reading and writing and are in a relaxed emotional state are grouped into a circle.

[0722] Step 6:

[0723] The server notifies the target end user device of the newly created circle. For example, a notification that a reading / writing circle has been created is sent to the devices of user A and user B.

[0724] Step 7:

[0725] Users receive the circle creation notification and use their end-user devices to express their intention to join the circle. The user's intention to join is sent from the device to the server, which records the intention to join in the database and updates the circle member list. For example, it is recorded that User A and User B will join a reading and writing circle.

[0726] This allows users to effectively interact with other users who share common hobbies and interests, improving the quality of communication within the factory.

[0727] 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.

[0728] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0729] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0730] [Third embodiment]

[0731] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0732] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0733] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0734] 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.

[0735] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0736] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0737] 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. 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.

[0738] 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.

[0739] 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 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.

[0740] 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.

[0741] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0742] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0743] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses this information to automatically create circles with members who share the same interests. Below are the methods for implementing this system and specific examples.

[0744] Obtaining information about hobbies and interests

[0745] First, a user inputs information about their hobbies and interests on their device (PC, smartphone, tablet, etc.). For example, User A inputs "reading" and "hiking" as their hobbies. Next, the device sends this input information to the server.

[0746] Storage in the database

[0747] The server stores the received hobby and interest information in a database, which stores each user's ID and the corresponding hobby and interest information.

[0748] Data cleansing and normalization

[0749] Periodically, the server reads all user interest information from the database and performs cleansing and normalization to ensure the data is consistent and accurate, for example by correcting spelling and unifying synonyms.

[0750] Similarity calculation using generative artificial intelligence

[0751] Next, the server passes the normalized hobby and interest information to a generation AI that calculates the similarity between each user. This generation AI uses a machine learning model to evaluate the similarity of hobbies. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[0752] Automatic circle generation

[0753] The server then pairs users who meet a certain threshold based on the calculated similarity and automatically creates circles, such as reading and writing circles.

[0754] Circle Notifications

[0755] When a new circle is created, the server sends a circle creation notification to the user, who then displays the notification on the device to notify the user.

[0756] Acceptance of participation intention

[0757] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[0758] Specific examples

[0759] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[0760] The system helps employees automatically build new relationships, promotes communication in the workplace, and helps create a vibrant work environment.

[0761] The processing flow will be explained below.

[0762] Step 1:

[0763] Users input their hobbies and interests into their devices (PCs, smartphones, tablets, etc.) This information includes the user's favorite activities and areas of interest, such as "reading" or "hiking."

[0764] Step 2:

[0765] The device transmits the entered hobbies and interests to a server using a secure communication protocol.

[0766] Step 3:

[0767] The server validates the received hobbies and interests information and stores it in a database. The validation process ensures that the input data is in the correct format, for example, checking for incorrect formatting or invalid data.

[0768] Step 4:

[0769] The server periodically reads all users' hobbies and interests from the database and cleanses and normalizes them. Cleansing is the process of modifying or deleting data to keep it consistent and accurate, while normalization is the process of standardizing the data into a standard format.

[0770] Step 5:

[0771] The server generates hobby vectors for each user using the normalized hobby and interest information, and calculates the similarity between these vectors using a generative AI. The generative AI uses a machine learning model to evaluate the similarity of hobbies.

[0772] Step 6:

[0773] The server automatically pairs users who have similarities above a certain threshold based on the similarity matrix and creates circles. For example, it groups users A and B, who have similarities, into a single reading / writing circle.

[0774] Step 7:

[0775] After a new circle is created, the server notifies the affected users that a new circle has been created, either by email or via the application's in-app notification system.

[0776] Step 8:

[0777] The device displays the received notification, which includes details about the new circle, and asks the user to confirm their intention to join the new circle.

[0778] Step 9:

[0779] The user confirms the notification and sends their intention to join the circle to the server via their device, where it is recorded in the database.

[0780] Step 10:

[0781] The server saves the updated member list of the circle in its database, and prepares to start circle activities. This officially launches the new circle.

[0782] Through this processing step, the system can create new networking opportunities among employees, resulting in a more vibrant work environment.

[0783] Example 1

[0784] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0785] Previous systems for strengthening connections between employees had problems with grouping based on individual hobbies and interests, and were unable to automatically generate circles with the right members. Furthermore, manually creating circles required a great deal of effort and time, and did not guarantee appropriate matching between employees. This resulted in ineffective promotion of communication and the building of new relationships.

[0786] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0787] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; and means for accepting intentions to join the new circles from end user terminals. This enables appropriate grouping based on employees' hobbies and interests, and enables the automatic generation and notification of circles and the acceptance of intentions to join to be performed in a consistent manner, thereby promoting communication between employees and building new relationships more effectively.

[0788] "Each end user terminal" is an information technology device used by a user (e.g., a PC, a smartphone, a tablet, etc.).

[0789] "Hobbies and interests information" is data entered by the user about their own hobbies and interests.

[0790] "Database" means the information technology infrastructure for storing and managing Hobbies and Interests Information.

[0791] "Cleansing" is the process of correcting and shaping data to ensure its consistency and accuracy.

[0792] "Normalization" refers to the standardization of data through the unification of different notations and the integration of synonyms.

[0793] "Generative AI" is an AI technology that uses algorithms such as machine learning models to process and analyze data.

[0794] "Similarity" is an index that numerically evaluates the commonality or closeness between different data.

[0795] "Grouping" refers to classifying multiple users into a set based on similarity.

[0796] A "circle" is a group made up of users who share common hobbies and interests.

[0797] "Notification" is a means of communication to inform users of information about a newly created circle.

[0798] "Intention to join" is an act by a user indicating their intention to join a newly created circle.

[0799] MODE FOR CARRYING OUT THE INVENTION

[0800] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between employees, and based on that information, a generative AI automatically creates circles with members who share the same interests. The specific method for implementing this system and its details are described below.

[0801] Obtaining information about hobbies and interests

[0802] First, a user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. Then, they enter information about their hobbies and interests. For example, User A enters "reading" and "hiking" as their hobbies. Next, the device sends this entered information to the server as a POST request.

[0803] Storage in the database

[0804] The server analyzes the received POST request and extracts the hobby and interest information. The information is stored in a database (e.g., MongoDB or PostgreSQL). The database stores each user's ID and the corresponding hobby and interest information.

[0805] Data cleansing and normalization

[0806] The server periodically reads all users' hobby and interest information from the database and cleanses it using Python's Pandas library. This cleansing process involves correcting spelling and standardizing synonyms to ensure consistency and accuracy of the data. For example, "cycling" is normalized as "Cycling."

[0807] Similarity calculation using generative artificial intelligence

[0808] The server passes the cleansed hobby and interest information to a generative AI model in a machine learning framework (e.g., TensorFlow or PyTorch) to calculate the similarity between each user. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between these vectors. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[0809] Automatic circle generation

[0810] The server pairs users who exceed a certain threshold based on the calculated similarity and automatically creates circles with users who share the same hobbies and interests. For example, users who share a high similarity between reading and writing are selected as a pair to create a reading / writing circle.

[0811] Circle Notifications

[0812] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification can be sent by push notification, email, or in-app notification. The device receives this notification and displays it to the user. For example, a notification saying "A new reading and writing circle has been created" will be displayed on User A's smartphone.

[0813] Acceptance of participation intention

[0814] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join to the server. The server records the received intention to join in its database and updates the circle member list.

[0815] Specific examples

[0816] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[0817] Prompt Sentence Examples

[0818] "Please tell me the specific process flow of a system that uses a generative AI model to automatically generate circles based on employees' hobbies and interests and notify them."

[0819] The system is designed to promote communication among employees and enhance the vibrancy of the work environment.

[0820] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0821] Step 1: Enter and submit your hobbies and interests

[0822] A user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. The user enters information about their hobbies and interests. For example, User A enters their hobbies of "reading" and "hiking." The entered data is temporarily saved within the device. Next, when the user clicks the submit button, the device sends this information to the server as a POST request in JSON format. The input is the user's hobbies and interests, and the output is a POST request to the server.

[0823] Step 2: Store in the database

[0824] The server analyzes the received POST request and extracts hobby and interest information. The extracted information is stored in a database. For example, user IDs and their corresponding hobby information are stored in a table. Databases such as MongoDB and PostgreSQL are used. The input is the hobby and interest information received by the server, and the output is the information stored in the database. Specifically, the server extracts the received data and executes an INSERT query on the database.

[0825] Step 3: Cleanse and normalize the data

[0826] The server periodically reads all users' hobby and interest information from the database. The read data is cleansed using Python's Pandas library, among other tools. This process involves correcting spelling and unifying synonyms. For example, "cycling" and "cycling" are unified as the same hobby. The input is hobby and interest information retrieved from the database, and the output is cleansed and normalized data. Specifically, the server executes a data query and performs data formatting on the retrieved data.

[0827] Step 4: Similarity calculation by generative AI

[0828] The server passes the cleansed hobby and interest information to a generative AI model created using a machine learning framework such as TensorFlow or PyTorch. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between those vectors. For example, it rates the similarity between User A, who likes "reading," and User B, who likes "writing," as high. The input is the cleansed and normalized hobby and interest information, and the output is the calculated similarity score. Specifically, the server passes the data to the generative AI model and obtains the calculation results.

[0829] Step 5: Automatic circle generation

[0830] Based on the calculated similarity score, the server pairs users who exceed a certain threshold and creates new circles with users who share common hobbies and interests. For example, users who share a high similarity between reading and writing are selected to create a reading / writing circle. The input is the similarity score, and the output is the newly created circle information. Specifically, the server applies a grouping algorithm based on the similarity score to create the circle information.

[0831] Step 6: Circle Notifications

[0832] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification is sent via push notification, email, in-app notification, etc. The device receives this notification and displays it to the user. For example, "A new reading and writing circle has been created" is displayed on User A's smartphone. The input is the newly created circle information, and the output is a notification to the user. Specifically, the server generates a notification message and sends it via the notification service.

[0833] Step 7: Accepting participation

[0834] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join information to the server. The server records the received intention to join information in a database and updates the circle member list. The input is the user's intention to join information, and the output is the updated database information. Specifically, the server analyzes the received data and executes an UPDATE query on the database.

[0835] (Application example 1)

[0836] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0837] In modern society, there is little interaction between customers in physical stores, making it difficult to improve customer satisfaction and repeat customer rates. In particular, there are few opportunities for customers with common hobbies or interests to naturally interact with each other, which can lead to a decline in the quality of the store experience. For this reason, there is a need for a system that promotes connections between customers and forms communities within physical stores.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0839] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; means for accepting intentions from end users to join the circles; and means for connecting customers with similar hobbies and interests in real time and automatically forming in-store communities. This allows customers to easily meet other customers with common hobbies, enabling the formation of active communities within the physical store.

[0840] An "end user terminal" is a device used by a user to input and receive information, including a smartphone, PC, tablet, etc.

[0841] "Hobbies and Interests Information" refers to information that expresses a user's hobbies and interests, including specific activities, themes, preferences, etc.

[0842] A "database" is an information management system that systematically stores acquired data and makes it easy to search and access.

[0843] "Cleansing" is the process of eliminating errors and redundancies and standardizing data to ensure consistency and accuracy.

[0844] "Normalization" is the process of standardizing data into a uniform format, making it easier to compare and process.

[0845] "Generative AI" refers to AI that uses machine learning models to generate useful information and patterns from input data.

[0846] "Similarity" is an index that indicates how similar two or more data points are, and in this case, it particularly evaluates the commonality of users' hobbies and interests.

[0847] A "circle" is a group of users who share common hobbies or interests, and is a gathering for interacting and sharing information.

[0848] A "notification" is a message or alert that the system uses to inform the user of new information or actions.

[0849] "Intention to participate" is information indicating the user's intention to join a particular circle or group.

[0850] "Real-time" refers to a state in which information is processed immediately and results are reflected almost instantly.

[0851] An "in-store community" is a group formed within a specific physical store that promotes interaction between customers who share common hobbies and interests.

[0852] This invention provides a system that automatically connects customers in a physical store and forms an in-store community. This system is implemented using hardware and software such as a server, end-user terminals, a database, and generative artificial intelligence.

[0853] System Configuration

[0854] The system consists of the following main components:

[0855] 1. End-user Devices

[0856] A device such as a smartphone, PC, or tablet that allows users to input and receive information about their hobbies and interests.

[0857] 2. Server

[0858] It is a central computer system that acquires hobbies and interests information, stores it in a database, and processes the data using artificial intelligence to generate it.

[0859] 3. Database

[0860] An information management system for effectively storing, retrieving, and accessing acquired hobbies and interests information.

[0861] 4. Generative Artificial Intelligence

[0862] Uses machine learning models to calculate the similarity of hobbies and interests and group users. Based on cosine similarity calculation.

[0863] Detailed Description of the Invention

[0864] 1. Acquiring information about hobbies and interests

[0865] Users use their own devices to enter information about their hobbies and interests. For example, User A registers "mystery novels" and "literature" as his or her hobbies.

[0866] 2. Storage in the database

[0867] The hobby and interest information acquired by the device is sent to the server, which stores the information in a database.

[0868] 3. Data cleansing and normalization

[0869] The server periodically retrieves all users' hobbies and interests from the database and performs spelling corrections and synonym unification.

[0870] 4. Similarity calculation using generative artificial intelligence

[0871] The server passes the cleansed and normalized data to a generative AI model, which uses cosine similarity to calculate the similarity of hobbies and interests between users.

[0872] 5. Automatic circle generation

[0873] Users with similar interests are grouped together and automatically created into circles, such as a "mystery novel club" or a "literature club."

[0874] 6. Circle Notifications

[0875] The server notifies the relevant end user terminal of the newly created circle and notifies the user.

[0876] 7. Acceptance of participation intention

[0877] The end user receives the notification and sends their intention to join the circle to the server via their device. The server records this information in a database and updates the circle member list.

[0878] Specific examples

[0879] For example, if a user at a bookstore registers "mystery novels" and "literature" as their hobbies, the server will use this information to match them with other users at the same bookstore and automatically create a "mystery novel club." Users will receive a notification about this club and can join the in-store community by indicating their intention to join.

[0880] Prompt Sentence Examples

[0881] "User A has registered 'mystery novels' and 'literature' as his hobbies. Compare this with the hobbies of other users and automatically group users with the same hobbies into circles."

[0882] This system allows customers to easily meet other customers with common interests and form active communities within the physical store.

[0883] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0884] Step 1:

[0885] Enter and submit information about your hobbies and interests

[0886] Users enter their hobbies and interests using their own devices (smartphones, PCs, tablets, etc.). The devices acquire the entered information and send it to the server. For example, User A enters "mystery novels" and "literature."

[0887] Input: Hobbies and interests entered by the user into the device

[0888] Output: Sending hobby and interest information from the device to the server

[0889] Step 2:

[0890] Storage in the database

[0891] The server stores the hobby and interest information received from the device in a database. This database stores each user's ID and the corresponding hobby and interest information.

[0892] Input: Hobbies and interests sent from your device

[0893] Output: Hobbies and interests stored in a database

[0894] Step 3:

[0895] Data cleansing and normalization

[0896] The server periodically reads the hobbies and interests information from the database and cleanses and normalizes it, correcting spelling errors and standardizing synonyms to ensure the data is consistent and accurate.

[0897] Input: Hobbies and interests read from the database

[0898] Output: Cleansed and normalized hobbies and interests

[0899] Step 4:

[0900] Similarity calculation

[0901] The server passes the cleansed and normalized hobby and interest information to the generative AI model, which then calculates the similarity, using cosine similarity to evaluate the commonality of interests between users.

[0902] Input: Cleansed and normalized hobbies and interests

[0903] Output: Similarity scores between each user

[0904] Step 5:

[0905] Automatic circle generation

[0906] The server then groups users who exceed a certain threshold based on the calculated similarity and automatically generates circles, such as a "mystery novel club" or a "literature lovers club."

[0907] Input: Similarity score between each user

[0908] Output: A list of generated circles

[0909] Step 6:

[0910] Circle Notifications

[0911] The server notifies the corresponding end user terminal of the newly created circle, and the user receives a notification of the circle creation.

[0912] Input: A list of generated circles

[0913] Output: Sending a circle creation notification to the device

[0914] Step 7:

[0915] Acceptance of participation intention

[0916] When a user receives the notification of the creation of a circle, they send their intention to join the circle to the server via their device. The server records this information in its database and updates the circle member list.

[0917] Input: User's participation intention information

[0918] Output: Join intentions stored in the database and an updated list of circle members

[0919] These steps enable the system to automatically foster connections between customers within the physical store and create an active in-store community.

[0920] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0921] This invention combines a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses that information to automatically create circles with members who share the same interests using a generation AI, with an emotion engine that recognizes the user's emotions. Specific methods and examples for implementing this system are shown below.

[0922] Acquiring Hobbies and Interests Information and Emotion Recognition

[0923] First, a user inputs their hobbies and interests on their device (PC, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "excited" or "relaxed").

[0924] Data transmission and storage

[0925] The device transmits the entered hobbies and interests and the recorded emotional state to the server using a secure communication protocol.

[0926] Storage in the database

[0927] The server stores the received hobby / interest information and emotional state in a database, which stores each user's ID and their corresponding hobby / interest information and emotional state.

[0928] Data cleansing and normalization

[0929] Periodically, the server reads all users' interests and emotional states from the database, cleansing and normalizing them.

[0930] Similarity calculation using generative artificial intelligence

[0931] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generation AI. The generation AI uses a machine learning model to evaluate the similarity of hobbies and emotions. For example, it calculates that User A, who likes "reading" and finds "relaxing," and User B, who likes "writing" and finds "relaxing" have a high similarity.

[0932] Automatic circle generation

[0933] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[0934] Circle Notifications

[0935] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[0936] Acceptance of participation intention

[0937] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[0938] Specific examples

[0939] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and similarity is calculated. Because the similarity between reading and writing and the emotional state of being relaxed is high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[0940] This system not only allows employees to automatically build new relationships, but also allows for deeper, more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[0941] The processing flow will be explained below.

[0942] Step 1:

[0943] Users enter their hobbies and interests into their devices (PC, smartphone, tablet, etc.) Specifically, they register hobbies such as "reading" or "hiking" using a dedicated form or application.

[0944] Step 2:

[0945] As the device receives information about hobbies and interests, it activates an emotion engine to recognize the user's emotional state. For example, it uses cameras and sensors to analyze the user's facial expressions and voice to determine emotional states such as "relaxed" or "excited."

[0946] Step 3:

[0947] The device transmits the input information about hobbies and interests and the recognized emotional state to a server using a secure communication protocol to prevent unauthorized access and information leaks.

[0948] Step 4:

[0949] The server validates the received hobbies, interests, and emotional state information to ensure that it is in the correct format, e.g., by checking for incorrect data formatting or inappropriate information.

[0950] Step 5:

[0951] The server stores the verified data in a database, which stores each user's ID and corresponding hobbies, interests, and emotional state.

[0952] Step 6:

[0953] The server periodically reads all users' interests and emotional states from the database and performs cleansing and normalization, correcting spelling and removing unnecessary data to ensure consistency and accuracy of the data.

[0954] Step 7:

[0955] The server uses the normalized information to generate interest vectors and emotion vectors for each user, and uses a generative AI to calculate the similarity between these vectors. The machine learning model evaluates the similarity between interest and emotion.

[0956] Step 8:

[0957] The server pairs users who exceed a certain threshold based on the calculated similarity matrix and automatically generates circles with common hobbies and emotional states. For example, if there is a user whose hobbies are "reading" and "writing" and who is in a "relaxed" state, a reading / writing circle will be generated.

[0958] Step 9:

[0959] The server notifies the corresponding users of the newly created circle information via email or the notification function within the application.

[0960] Step 10:

[0961] The device displays the received notification and provides the user with details about the new circle, which the user can then review and express their intention to join.

[0962] Step 11:

[0963] Users can send their intention to join a circle to the server via their device by clicking an approval button or sending a message requesting participation.

[0964] Step 12:

[0965] The server records the intention to join in its database and updates the circle's member list, so the newly created circle is ready to officially begin its activities.

[0966] Specific examples

[0967] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as "relaxed" by the emotion engine, and similarly user B registers "writing" and "cycling" as hobbies and is recognized as "relaxed," the server stores this data in the database. After cleansing and normalization, the similarity of hobbies and emotions is calculated, and a reading / writing circle is automatically created. A notification of the new circle is sent to user A and user B, and after they confirm their intention to join, the circle member list is updated and the circle is officially launched.

[0968] This system can improve the quality of communication in the workplace by strengthening connections between employees and enabling deeper interactions that take into account their emotional states.

[0969] Example 2

[0970] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0971] Strengthening connections between employees and improving the quality of communication within a company is an important issue in many workplaces. Promoting interaction between employees with similar hobbies and interests is particularly expected to build deeper relationships of trust. However, conventional methods often involve manually ascertaining employees' hobbies and interests and grouping them based on that information, making it difficult to implement efficiently. Furthermore, creating groups without considering the user's emotional state can sometimes hinder smooth interaction. The present invention aims to solve these problems.

[0972] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each user's terminal, means for the terminal to recognize and record the user's emotional state, means for transmitting the acquired hobby and interest information and emotional state data to the server, means for storing the transmitted data in a database, means for cleansing and normalizing the data stored in the database, means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information and emotional state, means for grouping users based on the similarity and automatically generating a circle, means for notifying the corresponding user terminal of the newly generated circle, and means for accepting the user's intention to join the circle. This allows users to be appropriately grouped based on their hobby and interest information and emotional state, enabling interaction that enhances emotional empathy.

[0973] "User's device" refers to a device used by a user to input information or perform emotion recognition, such as a personal computer, smartphone, or tablet.

[0974] An "emotion engine" refers to software or hardware that uses a camera or microphone to analyze a user's facial expressions and tone of voice to recognize and record their emotional state in real time.

[0975] "Database" refers to a collection of hobbies, interests, and emotional state data stored in a structured, searchable, and manipulable form.

[0976] "Cleansing" refers to the process of correcting or removing incomplete, redundant, or erroneous data to ensure data accuracy and consistency.

[0977] "Normalization" refers to the process of converting data into a consistent format to facilitate comparison and analysis.

[0978] "Generative AI" refers to an AI system that uses techniques such as machine learning and natural language processing to generate and analyze meaningful information from input data.

[0979] "Similarity" is a numerical representation of the relevance and commonalities between data, and in this system it is an index that evaluates the degree of commonality in hobby and interest information and emotional states in particular.

[0980] A "Circle" is a collection of users automatically grouped together based on shared hobbies, interests, and emotional states.

[0981] "Notification" refers to the means by which a user is notified that a new Circle has been created, such as an email or in-app message.

[0982] "Intention to participate" refers to a user's expression of intent to join a circle, and the circle member list is updated based on this.

[0983] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and based on that information, a generation AI automatically creates circles with members who share the same interests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it enables deeper and more empathetic interactions.

[0984] Acquiring Hobbies and Interests Information and Emotion Recognition

[0985] First, a user inputs information about their hobbies and interests on their device (personal computer, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. The emotion engine can use, for example, the API of Microsoft Azure Cognitive Services. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "relaxed").

[0986] Data transmission and storage

[0987] The device transmits the acquired hobbies, interests, and emotional state to a server using a secure communication protocol (e.g., HTTPS). The transmitted data also includes the user's ID.

[0988] Storage in the database

[0989] The server stores the received hobby / interest information and emotional state in a database. The stored data is saved corresponding to the user ID.

[0990] Data cleansing and normalization

[0991] The server periodically reads all user data from the database and cleanses and normalizes it. Cleansing is the process of correcting or removing incomplete or redundant data. Normalization is the process of transforming data into a consistent form.

[0992] Similarity calculation using generative artificial intelligence

[0993] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generative AI (e.g., a machine learning model such as GPT-4).

[0994] Example prompt sentence:

[0995] "User A: Reading, relaxing; User B: Writing, relaxing. Do they have the same interests?"

[0996] Automatic circle generation

[0997] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[0998] Circle Notifications

[0999] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[1000] Acceptance of participation intention

[1001] The user confirms the notification and sends their intention to join the circle to the server via their device. The server stores the intention to join in the database and updates the circle member list.

[1002] Specific example explanation

[1003] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and a similarity calculation is performed by the generation AI. Because the similarity between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle is sent to users A and B. Upon receiving the notification, users A and B decide to join the circle.

[1004] This system not only allows employees to automatically build new relationships, but also allows for more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[1005] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1006] Step 1:

[1007] The user inputs information about their hobbies and interests into their device and activates the device's emotion recognition engine. For example, the user inputs hobby information such as "reading" or "hiking," and their emotional state (e.g., "relaxed") is recorded in real time using the device's camera and microphone. The device then prepares data based on the hobby and interest information entered by the user and the emotional state detected by the emotion recognition engine.

[1008] Input: User-entered hobbies and interests, and emotional state captured by the device's camera and microphone.

[1009] Output: Prepared data containing hobbies, interests, and emotional states.

[1010] Step 2:

[1011] The device sends the prepared data to the server using a secure communication protocol (e.g., HTTPS). The data sent includes the user's ID. This communication process ensures that the data is sent safely while protecting the user's privacy.

[1012] Input: Hobbies and interests, emotional state, user ID.

[1013] Output: User information data sent to the server.

[1014] Step 3:

[1015] The server verifies the received data and stores it in the database. Specifically, it creates a new entry corresponding to the user ID and stores the hobbies, interests, and emotional state. The data is stored in the database to ensure data consistency and access efficiency.

[1016] Input: User information data sent from the device.

[1017] Output: User information stored in the database.

[1018] Step 4:

[1019] The server periodically reads all user data from the database, cleansing and normalizing it. Cleansing corrects incomplete or incorrect data, and normalization converts it into a uniform format to ensure data consistency. This is done using libraries such as Python's pandas.

[1020] Input: User data stored in the database.

[1021] Output: Cleansed and normalized user data.

[1022] Step 5:

[1023] The server generates hobby vectors and emotion vectors for each user based on the cleansed and normalized data. The generated vectors are input into a generative AI model (e.g., GPT-4) to calculate the similarity between each vector. This quantifies the commonality and degree of interest agreement between users.

[1024] Input: Cleansed and normalized user data.

[1025] Output: The calculated similarity score between users.

[1026] Step 6:

[1027] The server automatically groups users who exceed a certain threshold based on the calculated similarity score and creates new circles. The server also takes into account emotional states in the similarity score, ensuring that users who can empathize with each other gather together.

[1028] Input: Similarity score.

[1029] Output: Auto-generated circle information.

[1030] Step 7:

[1031] The server notifies the user terminal of the new circle information that has been created. This notification is sent by email or within an application, informing the user that a new circle has been created.

[1032] Input: Auto-generated circle information.

[1033] Output: Notification message to the user's terminal.

[1034] Step 8:

[1035] The user receives the notification and sends their intention to join the circle to the server via their device. The server confirms the intention and updates the database entry to update the circle's member list.

[1036] Input: User's willingness to participate.

[1037] Output: Updated circle member list.

[1038] (Application example 2)

[1039] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1040] There is a need to promote communication between workers in factories, improve the work environment, and provide efficient work support.The purpose of this invention is to provide a system that utilizes information on workers' hobbies and interests and their emotional states to strengthen connections between workers and improve the quality of their refreshment time.

[1041] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each end user terminal, means for storing the acquired hobby and interest information and the user's emotional state in a database, and means for cleansing and normalizing the hobby and interest information and emotional state stored in the database. This enables workers in a factory to find colleagues who share common hobbies and interests and similar emotional states, and to more actively enjoy their refreshment time and work time.

[1042] "End-user device" means an electronic device used by a user to input and check information on hobbies, interests, and emotional states, including smartphones, PCs, tablets, etc.

[1043] "Hobbies and interests" refers to information about activities and themes that interest a user, and is stored in a database as part of the user's profile.

[1044] "Emotional state" is information that indicates the user's current emotional state, and is analyzed and recorded using an emotion recognition engine.

[1045] "Database" refers to an information storage system for storing and managing acquired hobby and interest information and emotional states.

[1046] "Cleansing" is the process of formatting information stored in a database and converting it into an accurate and usable format.

[1047] "Normalization" is the process of converting data of different formats into a consistent standard format to facilitate calculations and analysis.

[1048] "Similarity" is an index that numerically indicates the similarity between different data, and is calculated using a method such as cosine similarity.

[1049] "Generative AI" is an AI system that uses machine learning models to calculate the similarity of data and output analysis results.

[1050] A "circle" is a group formed by users who share common hobbies and interests, with the aim of engaging in hobby activities and interacting with others.

[1051] "Notification" is a function that sends information from the server to the end user terminal to notify the user of the creation of new circles and other important information.

[1052] "Intention to participate" is an expression of a user's desire to participate in a circle, and is transmitted to the server via the end user terminal.

[1053] This invention relates to a system for improving communication and work efficiency among workers in a factory. Specifically, it is a system that recognizes information about the hobbies and interests of workers and their emotional states, and automatically generates circles based on this information.

[1054] First, a user enters their hobbies and interests using their device. At the same time, the device activates an emotion engine to recognize the user's emotional state. For example, the device uses the camera and sensors of a smartphone or tablet to analyze the user's facial expressions and tone of voice and record their current emotional state.

[1055] The acquired hobby / interest information and emotional state are sent to the server via a secure communication protocol. The server stores this information in a database. The database stores each user's ID and their corresponding hobby / interest information and emotional state.

[1056] Next, the server periodically reads all users' data from the database and performs cleansing and normalization processes. Based on the normalized data, the server uses generative artificial intelligence to generate each user's interest vector and emotion vector, and calculates the similarity between these vectors. This similarity is calculated using cosine similarity in particular.

[1057] Based on the results of the similarity calculation, the server pairs users who have a high similarity level above a certain threshold and automatically generates a circle. This circle brings together users who share common hobbies and interests and who are in a similar emotional state. For example, users who enjoy reading or hiking and who enjoy relaxation will be given priority.

[1058] When a new circle is created, the server sends a notification to the end-user device of the user. The user can then express their intention to join the circle through a dedicated interface. Once the intention to join is sent to the server, the information is also saved in the database and the circle member list is updated.

[1059] In this way, the present invention allows workers in a factory to find other workers who share common hobbies and interests and work together, thereby realizing a better working environment and communication.

[1060] As a specific example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in a database. The data is then cleansed and normalized, and similarities are calculated. Because the similarities between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[1061] An example of a prompt sentence is, "If user A enjoys reading and hiking and is in a relaxed state, please find other users with similar hobbies and create a circle."

[1062] This invention utilizes generative AI models and emotion recognition technology to promote communication between workers in factories, improve production efficiency, and provide a comfortable working environment.

[1063] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1064] Step 1:

[1065] The user uses the end-user device to input information about their hobbies and interests. The input data can be information about hobbies such as reading or hiking. At the same time, the device uses a camera and microphone to record the user's facial expressions and tone of voice, which are then analyzed by the emotion engine. For example, it can determine whether the user is relaxed.

[1066] Step 2:

[1067] The device sends the acquired hobby / interest information and emotional state to the server. The sent data includes the user ID, hobby / interest information, and emotional state. The server receives this data and stores it in a database. For example, User A's hobby information of reading and hiking and his / her emotional state of relaxation are registered in the database.

[1068] Step 3:

[1069] The server periodically reads all users' hobbies, interests, and emotional states from the database, and cleanses and normalizes the data. For example, it converts information in the same hobby category into a unified format and sorts out duplicate data. This ensures that the data is consistent.

[1070] Step 4:

[1071] The server uses the generative AI model to calculate the similarity between the cleansed and normalized hobby / interest information and emotional states. This calculation is performed using cosine similarity to quantify the similarity between each user's hobby vector and emotional vector. For example, the similarity between reading and writing, and the similarity between the relaxed emotional state are calculated.

[1072] Step 5:

[1073] Based on the similarity calculation results, the server pairs users with high similarities and automatically generates circles. For example, users who share the hobbies of reading and writing and are in a relaxed emotional state are grouped into a circle.

[1074] Step 6:

[1075] The server notifies the target end user device of the newly created circle. For example, a notification that a reading / writing circle has been created is sent to the devices of user A and user B.

[1076] Step 7:

[1077] Users receive the circle creation notification and use their end-user devices to express their intention to join the circle. The user's intention to join is sent from the device to the server, which records the intention to join in the database and updates the circle member list. For example, it is recorded that User A and User B will join a reading and writing circle.

[1078] This allows users to effectively interact with other users who share common hobbies and interests, improving the quality of communication within the factory.

[1079] 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.

[1080] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1081] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1082] [Fourth embodiment]

[1083] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1084] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1085] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1086] 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.

[1087] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1088] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1089] 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. 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.

[1090] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1091] 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.

[1092] 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 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.

[1093] 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.

[1094] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1095] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1096] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses this information to automatically create circles with members who share the same interests. Below are the methods for implementing this system and specific examples.

[1097] Obtaining information about hobbies and interests

[1098] First, a user inputs information about their hobbies and interests on their device (PC, smartphone, tablet, etc.). For example, User A inputs "reading" and "hiking" as their hobbies. Next, the device sends this input information to the server.

[1099] Storage in the database

[1100] The server stores the received hobby and interest information in a database, which stores each user's ID and the corresponding hobby and interest information.

[1101] Data cleansing and normalization

[1102] Periodically, the server reads all user interest information from the database and performs cleansing and normalization to ensure the data is consistent and accurate, for example by correcting spelling and unifying synonyms.

[1103] Similarity calculation using generative artificial intelligence

[1104] Next, the server passes the normalized hobby and interest information to a generation AI that calculates the similarity between each user. This generation AI uses a machine learning model to evaluate the similarity of hobbies. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[1105] Automatic circle generation

[1106] The server then pairs users who meet a certain threshold based on the calculated similarity and automatically creates circles, such as reading and writing circles.

[1107] Circle Notifications

[1108] When a new circle is created, the server sends a circle creation notification to the user, who then displays the notification on the device to notify the user.

[1109] Acceptance of participation intention

[1110] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[1111] Specific examples

[1112] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[1113] The system helps employees automatically build new relationships, promotes communication in the workplace, and helps create a vibrant work environment.

[1114] The processing flow will be explained below.

[1115] Step 1:

[1116] Users input their hobbies and interests into their devices (PCs, smartphones, tablets, etc.) This information includes the user's favorite activities and areas of interest, such as "reading" or "hiking."

[1117] Step 2:

[1118] The device transmits the entered hobbies and interests to a server using a secure communication protocol.

[1119] Step 3:

[1120] The server validates the received hobbies and interests information and stores it in a database. The validation process ensures that the input data is in the correct format, for example, checking for incorrect formatting or invalid data.

[1121] Step 4:

[1122] The server periodically reads all users' hobbies and interests from the database and cleanses and normalizes them. Cleansing is the process of modifying or deleting data to keep it consistent and accurate, while normalization is the process of standardizing the data into a standard format.

[1123] Step 5:

[1124] The server generates hobby vectors for each user using the normalized hobby and interest information, and calculates the similarity between these vectors using a generative AI. The generative AI uses a machine learning model to evaluate the similarity of hobbies.

[1125] Step 6:

[1126] The server automatically pairs users who have similarities above a certain threshold based on the similarity matrix and creates circles. For example, it groups users A and B, who have similarities, into a single reading / writing circle.

[1127] Step 7:

[1128] After a new circle is created, the server notifies the affected users that a new circle has been created, either by email or via the application's in-app notification system.

[1129] Step 8:

[1130] The device displays the received notification, which includes details about the new circle, and asks the user to confirm their intention to join the new circle.

[1131] Step 9:

[1132] The user confirms the notification and sends their intention to join the circle to the server via their device, where it is recorded in the database.

[1133] Step 10:

[1134] The server saves the updated member list of the circle in its database, and prepares to start circle activities. This officially launches the new circle.

[1135] Through this processing step, the system can create new networking opportunities among employees, resulting in a more vibrant work environment.

[1136] Example 1

[1137] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1138] Previous systems for strengthening connections between employees had problems with grouping based on individual hobbies and interests, and were unable to automatically generate circles with the right members. Furthermore, manually creating circles required a great deal of effort and time, and did not guarantee appropriate matching between employees. This resulted in ineffective promotion of communication and the building of new relationships.

[1139] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1140] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; and means for accepting intentions to join the new circles from end user terminals. This enables appropriate grouping based on employees' hobbies and interests, and enables the automatic generation and notification of circles and the acceptance of intentions to join to be performed in a consistent manner, thereby promoting communication between employees and building new relationships more effectively.

[1141] "Each end user terminal" is an information technology device used by a user (e.g., a PC, a smartphone, a tablet, etc.).

[1142] "Hobbies and interests information" is data entered by the user about their own hobbies and interests.

[1143] "Database" means the information technology infrastructure for storing and managing Hobbies and Interests Information.

[1144] "Cleansing" is the process of correcting and shaping data to ensure its consistency and accuracy.

[1145] "Normalization" refers to the standardization of data through the unification of different notations and the integration of synonyms.

[1146] "Generative AI" is an AI technology that uses algorithms such as machine learning models to process and analyze data.

[1147] "Similarity" is an index that numerically evaluates the commonality or closeness between different data.

[1148] "Grouping" refers to classifying multiple users into a set based on similarity.

[1149] A "circle" is a group made up of users who share common hobbies and interests.

[1150] "Notification" is a means of communication to inform users of information about a newly created circle.

[1151] "Intention to join" is an act by a user indicating their intention to join a newly created circle.

[1152] MODE FOR CARRYING OUT THE INVENTION

[1153] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between employees, and based on that information, a generative AI automatically creates circles with members who share the same interests. The specific method for implementing this system and its details are described below.

[1154] Obtaining information about hobbies and interests

[1155] First, a user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. Then, they enter information about their hobbies and interests. For example, User A enters "reading" and "hiking" as their hobbies. Next, the device sends this entered information to the server as a POST request.

[1156] Storage in the database

[1157] The server analyzes the received POST request and extracts the hobby and interest information. The information is stored in a database (e.g., MongoDB or PostgreSQL). The database stores each user's ID and the corresponding hobby and interest information.

[1158] Data cleansing and normalization

[1159] The server periodically reads all users' hobby and interest information from the database and cleanses it using Python's Pandas library. This cleansing process involves correcting spelling and standardizing synonyms to ensure consistency and accuracy of the data. For example, "cycling" is normalized as "Cycling."

[1160] Similarity calculation using generative artificial intelligence

[1161] The server passes the cleansed hobby and interest information to a generative AI model in a machine learning framework (e.g., TensorFlow or PyTorch) to calculate the similarity between each user. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between these vectors. For example, it calculates that User A, who likes "reading," and User B, who likes "writing," have a high similarity.

[1162] Automatic circle generation

[1163] The server pairs users who exceed a certain threshold based on the calculated similarity and automatically creates circles with users who share the same hobbies and interests. For example, users who share a high similarity between reading and writing are selected as a pair to create a reading / writing circle.

[1164] Circle Notifications

[1165] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification can be sent by push notification, email, or in-app notification. The device receives this notification and displays it to the user. For example, a notification saying "A new reading and writing circle has been created" will be displayed on User A's smartphone.

[1166] Acceptance of participation intention

[1167] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join to the server. The server records the received intention to join in its database and updates the circle member list.

[1168] Specific examples

[1169] For example, if user A registers "reading" and "hiking" as hobbies, and user B registers "writing" and "cycling" as hobbies, the server stores this information in a database. The data is then cleansed and normalized, and similarity is calculated. Since the similarity between reading and writing is high, a new reading / writing circle is created. The server notifies user A and user B of the creation of the new circle, and the users decide whether to join the circle.

[1170] Prompt Sentence Examples

[1171] "Please tell me the specific process flow of a system that uses a generative AI model to automatically generate circles based on employees' hobbies and interests and notify them."

[1172] The system is designed to promote communication among employees and enhance the vibrancy of the work environment.

[1173] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1174] Step 1: Enter and submit your hobbies and interests

[1175] A user uses their device (PC, smartphone, tablet, etc.) to access a dedicated application or web form. The user enters information about their hobbies and interests. For example, User A enters their hobbies of "reading" and "hiking." The entered data is temporarily saved within the device. Next, when the user clicks the submit button, the device sends this information to the server as a POST request in JSON format. The input is the user's hobbies and interests, and the output is a POST request to the server.

[1176] Step 2: Store in the database

[1177] The server analyzes the received POST request and extracts hobby and interest information. The extracted information is stored in a database. For example, user IDs and their corresponding hobby information are stored in a table. Databases such as MongoDB and PostgreSQL are used. The input is the hobby and interest information received by the server, and the output is the information stored in the database. Specifically, the server extracts the received data and executes an INSERT query on the database.

[1178] Step 3: Cleanse and normalize the data

[1179] The server periodically reads all users' hobby and interest information from the database. The read data is cleansed using Python's Pandas library, among other tools. This process involves correcting spelling and unifying synonyms. For example, "cycling" and "cycling" are unified as the same hobby. The input is hobby and interest information retrieved from the database, and the output is cleansed and normalized data. Specifically, the server executes a data query and performs data formatting on the retrieved data.

[1180] Step 4: Similarity calculation by generative AI

[1181] The server passes the cleansed hobby and interest information to a generative AI model created using a machine learning framework such as TensorFlow or PyTorch. This generative AI model creates a vector representation of each user's hobby and interest information and calculates the cosine similarity between those vectors. For example, it rates the similarity between User A, who likes "reading," and User B, who likes "writing," as high. The input is the cleansed and normalized hobby and interest information, and the output is the calculated similarity score. Specifically, the server passes the data to the generative AI model and obtains the calculation results.

[1182] Step 5: Automatic circle generation

[1183] Based on the calculated similarity score, the server pairs users who exceed a certain threshold and creates new circles with users who share common hobbies and interests. For example, users who share a high similarity between reading and writing are selected to create a reading / writing circle. The input is the similarity score, and the output is the newly created circle information. Specifically, the server applies a grouping algorithm based on the similarity score to create the circle information.

[1184] Step 6: Circle Notifications

[1185] When a new circle is created, the server sends a notification of the circle creation to the relevant user. This notification is sent via push notification, email, in-app notification, etc. The device receives this notification and displays it to the user. For example, "A new reading and writing circle has been created" is displayed on User A's smartphone. The input is the newly created circle information, and the output is a notification to the user. Specifically, the server generates a notification message and sends it via the notification service.

[1186] Step 7: Accepting participation

[1187] The user checks the notification and enters their intention to join the circle on their device. For example, they click the "Join" button. The device then sends the intention to join information to the server. The server records the received intention to join information in a database and updates the circle member list. The input is the user's intention to join information, and the output is the updated database information. Specifically, the server analyzes the received data and executes an UPDATE query on the database.

[1188] (Application example 1)

[1189] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1190] In modern society, there is little interaction between customers in physical stores, making it difficult to improve customer satisfaction and repeat customer rates. In particular, there are few opportunities for customers with common hobbies or interests to naturally interact with each other, which can lead to a decline in the quality of the store experience. For this reason, there is a need for a system that promotes connections between customers and forms communities within physical stores.

[1191] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1192] In this invention, the server includes: means for acquiring hobby and interest information from each end user terminal; means for storing the acquired hobby and interest information in a database; means for cleansing and normalizing the hobby and interest information stored in the database; means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information; means for grouping end users based on the similarity and automatically generating circles; means for notifying corresponding end user terminals of the newly generated circles; means for accepting intentions from end users to join the circles; and means for connecting customers with similar hobbies and interests in real time and automatically forming in-store communities. This allows customers to easily meet other customers with common hobbies, enabling the formation of active communities within the physical store.

[1193] An "end user terminal" is a device used by a user to input and receive information, including a smartphone, PC, tablet, etc.

[1194] "Hobbies and Interests Information" refers to information that expresses a user's hobbies and interests, including specific activities, themes, preferences, etc.

[1195] A "database" is an information management system that systematically stores acquired data and makes it easy to search and access.

[1196] "Cleansing" is the process of eliminating errors and redundancies and standardizing data to ensure consistency and accuracy.

[1197] "Normalization" is the process of standardizing data into a uniform format, making it easier to compare and process.

[1198] "Generative AI" refers to AI that uses machine learning models to generate useful information and patterns from input data.

[1199] "Similarity" is an index that indicates how similar two or more data points are, and in this case, it particularly evaluates the commonality of users' hobbies and interests.

[1200] A "circle" is a group of users who share common hobbies or interests, and is a gathering for interacting and sharing information.

[1201] A "notification" is a message or alert that the system uses to inform the user of new information or actions.

[1202] "Intention to participate" is information indicating the user's intention to join a particular circle or group.

[1203] "Real-time" refers to a state in which information is processed immediately and results are reflected almost instantly.

[1204] An "in-store community" is a group formed within a specific physical store that promotes interaction between customers who share common hobbies and interests.

[1205] This invention provides a system that automatically connects customers in a physical store and forms an in-store community. This system is implemented using hardware and software such as a server, end-user terminals, a database, and generative artificial intelligence.

[1206] System Configuration

[1207] The system consists of the following main components:

[1208] 1. End-user Devices

[1209] A device such as a smartphone, PC, or tablet that allows users to input and receive information about their hobbies and interests.

[1210] 2. Server

[1211] It is a central computer system that takes hobbies and interests information, stores it in a database, and processes the data using artificial intelligence to generate it.

[1212] 3. Database

[1213] An information management system for effectively storing, retrieving, and accessing acquired hobbies and interests information.

[1214] 4. Generative Artificial Intelligence

[1215] Uses machine learning models to calculate the similarity of hobbies and interests and group users. Based on cosine similarity calculation.

[1216] Detailed Description of the Invention

[1217] 1. Acquiring information about hobbies and interests

[1218] Users use their own devices to enter information about their hobbies and interests. For example, User A registers "mystery novels" and "literature" as his or her hobbies.

[1219] 2. Storage in the database

[1220] The hobby and interest information acquired by the device is sent to the server, which stores the information in a database.

[1221] 3. Data cleansing and normalization

[1222] The server periodically retrieves all users' hobbies and interests from the database and performs spelling corrections and synonym unification.

[1223] 4. Similarity calculation using generative artificial intelligence

[1224] The server passes the cleansed and normalized data to a generative AI model, which uses cosine similarity to calculate the similarity of hobbies and interests between users.

[1225] 5. Automatic circle generation

[1226] Users with similar interests are grouped together and automatically created into circles, such as a "mystery novel club" or a "literature club."

[1227] 6. Circle Notifications

[1228] The server notifies the relevant end user terminal of the newly created circle and notifies the user.

[1229] 7. Acceptance of participation intention

[1230] The end user receives the notification and sends their intention to join the circle to the server via their device. The server records this information in a database and updates the circle member list.

[1231] Specific examples

[1232] For example, if a user at a bookstore registers "mystery novels" and "literature" as their hobbies, the server will use this information to match them with other users at the same bookstore and automatically create a "mystery novel club." Users will receive a notification about this club and can join the in-store community by indicating their intention to join.

[1233] Prompt Sentence Examples

[1234] "User A has registered 'mystery novels' and 'literature' as his hobbies. Compare this with the hobbies of other users and automatically group users with the same hobbies into circles."

[1235] This system allows customers to easily meet other customers with common interests and form active communities within the physical store.

[1236] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1237] Step 1:

[1238] Enter and submit information about your hobbies and interests

[1239] Users enter their hobbies and interests using their own devices (smartphones, PCs, tablets, etc.). The devices acquire the entered information and send it to the server. For example, User A enters "mystery novels" and "literature."

[1240] Input: Hobbies and interests entered by the user into the device

[1241] Output: Sending hobby and interest information from the device to the server

[1242] Step 2:

[1243] Storage in the database

[1244] The server stores the hobby and interest information received from the device in a database. This database stores each user's ID and the corresponding hobby and interest information.

[1245] Input: Hobbies and interests sent from your device

[1246] Output: Hobbies and interests stored in a database

[1247] Step 3:

[1248] Data cleansing and normalization

[1249] The server periodically reads the hobbies and interests information from the database and cleanses and normalizes it, correcting spelling errors and standardizing synonyms to ensure the data is consistent and accurate.

[1250] Input: Hobbies and interests read from the database

[1251] Output: Cleansed and normalized hobbies and interests

[1252] Step 4:

[1253] Similarity calculation

[1254] The server passes the cleansed and normalized hobby and interest information to the generative AI model, which then calculates the similarity, using cosine similarity to evaluate the commonality of interests between users.

[1255] Input: Cleansed and normalized hobbies and interests

[1256] Output: Similarity scores between each user

[1257] Step 5:

[1258] Automatic circle generation

[1259] The server then groups users who exceed a certain threshold based on the calculated similarity and automatically generates circles, such as a "mystery novel club" or a "literature lovers club."

[1260] Input: Similarity score between each user

[1261] Output: A list of generated circles

[1262] Step 6:

[1263] Circle Notifications

[1264] The server notifies the corresponding end user terminal of the newly created circle, and the user receives a notification of the circle creation.

[1265] Input: A list of generated circles

[1266] Output: Sending a circle creation notification to the device

[1267] Step 7:

[1268] Acceptance of participation intention

[1269] When a user receives the notification of the creation of a circle, they send their intention to join the circle to the server via their device. The server records this information in its database and updates the circle member list.

[1270] Input: User's participation intention information

[1271] Output: Join intentions stored in the database and an updated list of circle members

[1272] These steps enable the system to automatically foster connections between customers within the physical store and create an active in-store community.

[1273] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1274] This invention combines a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and then uses that information to automatically create circles with members who share the same interests using a generation AI, with an emotion engine that recognizes the user's emotions. Specific methods and examples for implementing this system are shown below.

[1275] Acquiring Hobbies and Interests Information and Emotion Recognition

[1276] First, a user inputs their hobbies and interests on their device (PC, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "excited" or "relaxed").

[1277] Data transmission and storage

[1278] The device transmits the entered hobbies and interests and the recorded emotional state to the server using a secure communication protocol.

[1279] Storage in the database

[1280] The server stores the received hobby / interest information and emotional state in a database, which stores each user's ID and their corresponding hobby / interest information and emotional state.

[1281] Data cleansing and normalization

[1282] Periodically, the server reads all users' interests and emotional states from the database, cleansing and normalizing them.

[1283] Similarity calculation using generative artificial intelligence

[1284] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generation AI. The generation AI uses a machine learning model to evaluate the similarity of hobbies and emotions. For example, it calculates that User A, who likes "reading" and finds "relaxing," and User B, who likes "writing" and finds "relaxing" have a high similarity.

[1285] Automatic circle generation

[1286] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[1287] Circle Notifications

[1288] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[1289] Acceptance of participation intention

[1290] The user confirms the notification and sends their intention to join the circle to the server via their device. The server records the intention to join in the database and updates the circle member list.

[1291] Specific examples

[1292] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and similarity is calculated. Because the similarity between reading and writing and the emotional state of being relaxed is high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[1293] This system not only allows employees to automatically build new relationships, but also allows for deeper, more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[1294] The processing flow will be explained below.

[1295] Step 1:

[1296] Users enter their hobbies and interests into their devices (PC, smartphone, tablet, etc.) Specifically, they register hobbies such as "reading" or "hiking" using a dedicated form or application.

[1297] Step 2:

[1298] As the device receives information about hobbies and interests, it activates an emotion engine to recognize the user's emotional state. For example, it uses cameras and sensors to analyze the user's facial expressions and voice to determine emotional states such as "relaxed" or "excited."

[1299] Step 3:

[1300] The device transmits the input information about hobbies and interests and the recognized emotional state to a server using a secure communication protocol to prevent unauthorized access and information leaks.

[1301] Step 4:

[1302] The server validates the received hobbies, interests, and emotional state information to ensure that it is in the correct format, e.g., by checking for incorrect data formatting or inappropriate information.

[1303] Step 5:

[1304] The server stores the verified data in a database, which stores each user's ID and corresponding hobbies, interests, and emotional state.

[1305] Step 6:

[1306] The server periodically reads all users' interests and emotional states from the database and performs cleansing and normalization, correcting spelling and removing unnecessary data to ensure consistency and accuracy of the data.

[1307] Step 7:

[1308] The server uses the normalized information to generate interest vectors and emotion vectors for each user, and uses a generative AI to calculate the similarity between these vectors. The machine learning model evaluates the similarity between interest and emotion.

[1309] Step 8:

[1310] The server pairs users who exceed a certain threshold based on the calculated similarity matrix and automatically generates circles with common hobbies and emotional states. For example, if there is a user whose hobbies are "reading" and "writing" and who is in a "relaxed" state, a reading / writing circle will be generated.

[1311] Step 9:

[1312] The server notifies the corresponding users of the newly created circle information via email or the notification function within the application.

[1313] Step 10:

[1314] The device displays the received notification and provides the user with details about the new circle, which the user can then review and express their intention to join.

[1315] Step 11:

[1316] Users can send their intention to join a circle to the server via their device by clicking an approval button or sending a message requesting participation.

[1317] Step 12:

[1318] The server records the intention to join in its database and updates the circle's member list, so the newly created circle is ready to officially begin its activities.

[1319] Specific examples

[1320] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as "relaxed" by the emotion engine, and similarly user B registers "writing" and "cycling" as hobbies and is recognized as "relaxed," the server stores this data in the database. After cleansing and normalization, the similarity of hobbies and emotions is calculated, and a reading / writing circle is automatically created. A notification of the new circle is sent to user A and user B, and after they confirm their intention to join, the circle member list is updated and the circle is officially launched.

[1321] This system can improve the quality of communication in the workplace by strengthening connections between employees and enabling deeper interactions that take into account their emotional states.

[1322] Example 2

[1323] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1324] Strengthening connections between employees and improving the quality of communication within a company is an important issue in many workplaces. Promoting interaction between employees with similar hobbies and interests is particularly expected to build deeper relationships of trust. However, conventional methods often involve manually ascertaining employees' hobbies and interests and grouping them based on that information, making it difficult to implement efficiently. Furthermore, creating groups without considering the user's emotional state can sometimes hinder smooth interaction. The present invention aims to solve these problems.

[1325] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each user's terminal, means for the terminal to recognize and record the user's emotional state, means for transmitting the acquired hobby and interest information and emotional state data to the server, means for storing the transmitted data in a database, means for cleansing and normalizing the data stored in the database, means including a generating artificial intelligence for calculating the similarity of the cleansed and normalized hobby and interest information and emotional state, means for grouping users based on the similarity and automatically generating a circle, means for notifying the corresponding user terminal of the newly generated circle, and means for accepting the user's intention to join the circle. This allows users to be appropriately grouped based on their hobby and interest information and emotional state, enabling interaction that enhances emotional empathy.

[1326] "User's device" refers to a device used by a user to input information or perform emotion recognition, such as a personal computer, smartphone, or tablet.

[1327] An "emotion engine" refers to software or hardware that uses a camera or microphone to analyze a user's facial expressions and tone of voice to recognize and record their emotional state in real time.

[1328] "Database" refers to a collection of hobbies, interests, and emotional state data stored in a structured, searchable, and manipulable form.

[1329] "Cleansing" refers to the process of correcting or removing incomplete, redundant, or erroneous data to ensure data accuracy and consistency.

[1330] "Normalization" refers to the process of converting data into a consistent format to facilitate comparison and analysis.

[1331] "Generative AI" refers to an AI system that uses techniques such as machine learning and natural language processing to generate and analyze meaningful information from input data.

[1332] "Similarity" is a numerical representation of the relevance and commonalities between data, and in this system it is an index that evaluates the degree of commonality in hobby and interest information and emotional states in particular.

[1333] A "Circle" is a collection of users automatically grouped together based on shared hobbies, interests, and emotional states.

[1334] "Notification" refers to the means by which a user is notified that a new Circle has been created, such as an email or in-app message.

[1335] "Intention to participate" refers to a user's expression of intent to join a circle, and the circle member list is updated based on this.

[1336] This invention is a system that aggregates information on the hobbies and interests of each employee to strengthen connections between them, and based on that information, a generation AI automatically creates circles with members who share the same interests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it enables deeper and more empathetic interactions.

[1337] Acquiring Hobbies and Interests Information and Emotion Recognition

[1338] First, a user inputs information about their hobbies and interests on their device (personal computer, smartphone, tablet, etc.). At the same time, the device activates an emotion engine to recognize and record the user's emotional state. The emotion engine can use, for example, the API of Microsoft Azure Cognitive Services. For example, when User A inputs "reading" and "hiking" as their hobbies, the device's camera and sensors analyze the user's facial expressions and voice tone and record their current emotional state (e.g., "relaxed").

[1339] Data transmission and storage

[1340] The device transmits the acquired hobbies, interests, and emotional state to a server using a secure communication protocol (e.g., HTTPS). The transmitted data also includes the user's ID.

[1341] Storage in the database

[1342] The server stores the received hobby / interest information and emotional state in a database. The stored data is saved corresponding to the user ID.

[1343] Data cleansing and normalization

[1344] The server periodically reads all user data from the database and cleanses and normalizes it. Cleansing is the process of correcting or removing incomplete or redundant data. Normalization is the process of transforming data into a consistent form.

[1345] Similarity calculation using generative artificial intelligence

[1346] Next, the server uses the normalized hobby / interest information and emotional state to generate hobby vectors and emotion vectors for each user. The similarity between these vectors is calculated using a generative AI (e.g., a machine learning model such as GPT-4).

[1347] Example prompt sentence:

[1348] "User A: Reading, relaxing; User B: Writing, relaxing. Do they have the same interests?"

[1349] Automatic circle generation

[1350] The server automatically pairs users who exceed a certain threshold based on the calculated similarity and creates circles. By taking emotional states into account, users with the same hobbies and similar emotional states can interact with greater empathy. Specifically, it is conceivable that all members of a reading or writing circle would gather together in a relaxed emotional state.

[1351] Circle Notifications

[1352] When a new circle is created, the server notifies the appropriate users that a new circle has been created, either by email or via the application's in-app notification system.

[1353] Acceptance of participation intention

[1354] The user confirms the notification and sends their intention to join the circle to the server via their device. The server stores the intention to join in the database and updates the circle's member list.

[1355] Specific example explanation

[1356] For example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in the database. The data is then cleansed and normalized, and a similarity calculation is performed by the generation AI. Because the similarity between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle is sent to users A and B. Upon receiving the notification, users A and B decide to join the circle.

[1357] This system not only allows employees to automatically build new relationships, but also allows for more empathetic interactions based on their emotional state, improving the quality of communication in the workplace.

[1358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1359] Step 1:

[1360] The user inputs information about their hobbies and interests into their device and activates the device's emotion recognition engine. For example, the user inputs hobby information such as "reading" or "hiking," and their emotional state (e.g., "relaxed") is recorded in real time using the device's camera and microphone. The device then prepares data based on the hobby and interest information entered by the user and the emotional state detected by the emotion recognition engine.

[1361] Input: User-entered hobbies and interests, and emotional state captured by the device's camera and microphone.

[1362] Output: Prepared data containing hobbies, interests, and emotional states.

[1363] Step 2:

[1364] The device sends the prepared data to the server using a secure communication protocol (e.g., HTTPS). The data sent includes the user's ID. This communication process ensures that the data is sent safely while protecting the user's privacy.

[1365] Input: Hobbies and interests, emotional state, user ID.

[1366] Output: User information data sent to the server.

[1367] Step 3:

[1368] The server verifies the received data and stores it in the database. Specifically, it creates a new entry corresponding to the user ID and stores the hobbies, interests, and emotional state. The data is stored in the database to ensure data consistency and access efficiency.

[1369] Input: User information data sent from the device.

[1370] Output: User information stored in the database.

[1371] Step 4:

[1372] The server periodically reads all user data from the database, cleansing and normalizing it. Cleansing corrects incomplete or incorrect data, and normalization converts it into a uniform format to ensure data consistency. This is done using libraries such as Python's pandas.

[1373] Input: User data stored in the database.

[1374] Output: Cleansed and normalized user data.

[1375] Step 5:

[1376] The server generates hobby vectors and emotion vectors for each user based on the cleansed and normalized data. The generated vectors are input into a generative AI model (e.g., GPT-4) to calculate the similarity between each vector. This quantifies the commonality and degree of interest agreement between users.

[1377] Input: Cleansed and normalized user data.

[1378] Output: The calculated similarity score between users.

[1379] Step 6:

[1380] The server automatically groups users who exceed a certain threshold based on the calculated similarity score and creates new circles. The server also takes into account emotional states in the similarity score, ensuring that users who can empathize with each other gather together.

[1381] Input: Similarity score.

[1382] Output: Auto-generated circle information.

[1383] Step 7:

[1384] The server notifies the user terminal of the new circle information that has been created. This notification is sent by email or within an application, informing the user that a new circle has been created.

[1385] Input: Auto-generated circle information.

[1386] Output: Notification message to the user's terminal.

[1387] Step 8:

[1388] The user receives the notification and sends their intention to join the circle to the server via their device. The server confirms the intention and updates the database entry to update the circle's member list.

[1389] Input: User's willingness to participate.

[1390] Output: Updated circle member list.

[1391] (Application example 2)

[1392] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1393] There is a need to promote communication between workers in factories, improve the work environment, and provide efficient work support.The purpose of this invention is to provide a system that utilizes information on workers' hobbies and interests and their emotional states to strengthen connections between workers and improve the quality of their refreshment time.

[1394] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring hobby and interest information from each end user terminal, means for storing the acquired hobby and interest information and the user's emotional state in a database, and means for cleansing and normalizing the hobby and interest information and emotional state stored in the database. This enables workers in a factory to find colleagues who share common hobbies and interests and similar emotional states, and to more actively enjoy their refreshment time and work time.

[1395] "End-user device" means an electronic device used by a user to input and check information on hobbies, interests, and emotional states, including smartphones, PCs, tablets, etc.

[1396] "Hobbies and interests" refers to information about activities and themes that interest a user, and is stored in a database as part of the user's profile.

[1397] "Emotional state" is information that indicates the user's current emotional state, and is analyzed and recorded using an emotion recognition engine.

[1398] "Database" refers to an information storage system for storing and managing acquired hobby and interest information and emotional states.

[1399] "Cleansing" is the process of formatting information stored in a database and converting it into an accurate and usable format.

[1400] "Normalization" is the process of converting data of different formats into a consistent standard format to facilitate calculations and analysis.

[1401] "Similarity" is an index that numerically indicates the similarity between different data, and is calculated using a method such as cosine similarity.

[1402] "Generative AI" is an AI system that uses machine learning models to calculate the similarity of data and output analysis results.

[1403] A "circle" is a group formed by users who share common hobbies and interests, with the aim of engaging in hobby activities and interacting with others.

[1404] "Notification" is a function that sends information from the server to the end user terminal to notify the user of the creation of new circles and other important information.

[1405] "Intention to participate" is an expression of a user's desire to participate in a circle, and is transmitted to the server via the end user terminal.

[1406] This invention relates to a system for improving communication and work efficiency among workers in a factory. Specifically, it is a system that recognizes information about the hobbies and interests of workers and their emotional states, and automatically generates circles based on this information.

[1407] First, a user enters their hobbies and interests using their device. At the same time, the device activates an emotion engine to recognize the user's emotional state. For example, the device uses the camera and sensors of a smartphone or tablet to analyze the user's facial expressions and tone of voice and record their current emotional state.

[1408] The acquired hobby / interest information and emotional state are sent to the server via a secure communication protocol. The server stores this information in a database. The database stores each user's ID and their corresponding hobby / interest information and emotional state.

[1409] Next, the server periodically reads all users' data from the database and performs cleansing and normalization processes. Based on the normalized data, the server uses generative artificial intelligence to generate each user's interest vector and emotion vector, and calculates the similarity between these vectors. This similarity is calculated using cosine similarity in particular.

[1410] Based on the results of the similarity calculation, the server pairs users who have a high similarity level above a certain threshold and automatically generates a circle. This circle brings together users who share common hobbies and interests and who are in a similar emotional state. For example, users who enjoy reading or hiking and who enjoy relaxation will be given priority.

[1411] When a new circle is created, the server sends a notification to the end-user device of the user. The user can then express their intention to join the circle through a dedicated interface. Once the intention to join is sent to the server, the information is also saved in the database and the circle member list is updated.

[1412] In this way, the present invention allows workers in a factory to find other workers who share common hobbies and interests and work together, thereby realizing a better working environment and communication.

[1413] As a specific example, if user A registers "reading" and "hiking" as hobbies and is recognized as being in a "relaxed" state, and user B registers "writing" and "cycling" as hobbies and is also recognized as being in a "relaxed" state, the server stores this information in a database. The data is then cleansed and normalized, and similarities are calculated. Because the similarities between reading and writing and the emotional state of being relaxed are high, a new reading / writing circle is created, and a notification of the new circle creation is sent to users A and B. Upon receiving this notification, users A and B decide to join the circle.

[1414] An example of a prompt sentence is, "If user A enjoys reading and hiking and is in a relaxed state, please find other users with similar hobbies and create a circle."

[1415] This invention utilizes generative AI models and emotion recognition technology to promote communication between workers in a factory, improving production efficiency and providing a comfortable working environment.

[1416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1417] Step 1:

[1418] The user uses the end-user device to input information about their hobbies and interests. The input data can be information about hobbies such as reading or hiking. At the same time, the device uses a camera and microphone to record the user's facial expressions and tone of voice, which are then analyzed by the emotion engine. For example, it can determine whether the user is relaxed.

[1419] Step 2:

[1420] The device sends the acquired hobby / interest information and emotional state to the server. The sent data includes the user ID, hobby / interest information, and emotional state. The server receives this data and stores it in a database. For example, User A's hobby information of reading and hiking and his / her emotional state of relaxation are registered in the database.

[1421] Step 3:

[1422] The server periodically reads all users' hobbies, interests, and emotional states from the database, and cleanses and normalizes the data. For example, it converts information in the same hobby category into a unified format and sorts out duplicate data. This ensures that the data is consistent.

[1423] Step 4:

[1424] The server uses the generative AI model to calculate the similarity between the cleansed and normalized hobby / interest information and emotional states. This calculation is performed using cosine similarity to quantify the similarity between each user's hobby vector and emotional vector. For example, the similarity between reading and writing, and the similarity between the relaxed emotional state are calculated.

[1425] Step 5:

[1426] Based on the similarity calculation results, the server pairs users with high similarities and automatically generates circles. For example, users who share the hobbies of reading and writing and are in a relaxed emotional state are grouped into a circle.

[1427] Step 6:

[1428] The server notifies the target end user device of the newly created circle. For example, a notification that a reading / writing circle has been created is sent to the devices of user A and user B.

[1429] Step 7:

[1430] Users receive the circle creation notification and use their end-user devices to express their intention to join the circle. The user's intention to join is sent from the device to the server, which records the intention to join in the database and updates the circle member list. For example, it is recorded that User A and User B will join a reading and writing circle.

[1431] This allows users to effectively interact with other users who share common hobbies and interests, improving the quality of communication within the factory.

[1432] 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.

[1433] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1434] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1435] 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.

[1436] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1437] 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.

[1438] 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).

[1439] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1440] 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."

[1441] 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.

[1442] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1443] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1448] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1449] 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.

[1450] 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.

[1451] 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, in order to avoid confusion and to 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.

[1452] 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.

[1453] The following is further disclosed regarding the above embodiment.

[1454] (Claim 1)

[1455] A means for acquiring hobby and interest information from each end user device;

[1456] A means for storing the acquired hobby and interest information in a database;

[1457] A means for cleansing and normalizing the hobbies and interests information stored in the database;

[1458] A means including a generative artificial intelligence for calculating a similarity of the cleansed and normalized hobby and interest information;

[1459] a means for automatically generating circles by grouping end users based on similarity;

[1460] means for notifying a corresponding end user terminal of the newly created circle;

[1461] A means for accepting an intention to join a circle from an end user;

[1462] A system including:

[1463] (Claim 2)

[1464] 2. The system of claim 1, wherein the similarity calculation means calculates the similarity using cosine similarity.

[1465] (Claim 3)

[1466] The system of claim 1, wherein the generative artificial intelligence calculates the similarity of the hobby and interest information using a machine learning model.

[1467] "Example 1"

[1468] (Claim 1)

[1469] A means for acquiring hobby and interest information from each end user device;

[1470] A means for storing the acquired hobby and interest information in a database;

[1471] A means for cleansing and normalizing the hobbies and interests information stored in the database;

[1472] A means including a generative artificial intelligence for calculating a similarity of the cleansed and normalized hobby and interest information;

[1473] a means for automatically generating circles by grouping end users based on similarity;

[1474] means for notifying a corresponding end user terminal of the newly created circle;

[1475] means for accepting an intention to join a new circle from an end user terminal;

[1476] A system including:

[1477] (Claim 2)

[1478] 2. The system of claim 1, wherein the similarity calculation means calculates the similarity using cosine similarity.

[1479] (Claim 3)

[1480] The system of claim 1, wherein the generative artificial intelligence calculates the similarity of the hobby and interest information using a machine learning model.

[1481] "Application Example 1"

[1482] (Claim 1)

[1483] A means for acquiring hobby and interest information from each end user device;

[1484] A means for storing the acquired hobby and interest information in a database;

[1485] A means for cleansing and normalizing the hobbies and interests information stored in the database;

[1486] A means including a generative artificial intelligence for calculating a similarity of the cleansed and normalized hobby and interest information;

[1487] a means for automatically generating circles by grouping end users based on similarity;

[1488] means for notifying a corresponding end user terminal of the newly created circle;

[1489] A means for accepting an intention to join a circle from an end user;

[1490] A way to automatically form an in-store community by connecting customers with similar hobbies and interests in real time,

[1491] A system including:

[1492] (Claim 2)

[1493] 2. The system of claim 1, wherein the similarity calculation means calculates the similarity using cosine similarity.

[1494] (Claim 3)

[1495] The system of claim 1, wherein the generative artificial intelligence calculates the similarity of the hobby and interest information using a machine learning model.

[1496] "Example 2: Combining Emotion Engines"

[1497] (Claim 1)

[1498] A means for acquiring hobby and interest information from each user's device;

[1499] means for recognizing and recording the user's emotional state,

[1500] means for transmitting the acquired hobby / interest information and emotional state data to a server;

[1501] means for storing the transmitted data in a database;

[1502] A means of cleansing and normalizing the data stored in the database;

[1503] A means including a generative artificial intelligence for calculating a similarity between the cleansed and normalized hobby / interest information and the emotional state;

[1504] A means for grouping users based on similarity and automatically generating circles;

[1505] a means for notifying a corresponding user terminal of a newly created circle;

[1506] A means for accepting an intention to join a circle from a user;

[1507] A system including:

[1508] (Claim 2)

[1509] 10. The system of claim 1, wherein the emotional engine is used to recognize and record the emotional state of the user.

[1510] (Claim 3)

[1511] The system of claim 1, wherein the generative artificial intelligence calculates similarity between hobby and interest information and emotional states using a machine learning model.

[1512] "Application example 2 when combining emotion engines"

[1513] (Claim 1)

[1514] A means for acquiring hobby and interest information from each end user device;

[1515] A means for storing the acquired hobby and interest information and the user's emotional state in a database;

[1516] means for cleansing and normalizing the hobbies and interests information and emotional states stored in the database;

[1517] A means including a generative artificial intelligence for calculating a similarity between the cleansed and normalized hobby / interest information and the emotional state;

[1518] a means for automatically generating circles by grouping end users based on similarity;

[1519] means for notifying a corresponding end user terminal of the newly created circle;

[1520] A means for accepting an intention to join a circle from an end user;

[1521] A system including:

[1522] (Claim 2)

[1523] 2. The system according to claim 1, wherein the similarity calculation means calculates the similarity of the hobby / interest information and the emotional state using cosine similarity.

[1524] (Claim 3)

[1525] The system of claim 1, wherein the generative artificial intelligence calculates similarity between hobby and interest information and emotional states using a machine learning model. [Explanation of symbols]

[1526] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring hobby and interest information from each end user device; A means for storing the acquired hobby and interest information in a database; a means for cleansing and normalizing the hobbies and interests information stored in the database; A means including a generative artificial intelligence for calculating a similarity of the cleansed and normalized hobby and interest information; a means for automatically generating circles by grouping end users based on similarity; means for notifying a corresponding end user terminal of the newly created circle; A means for accepting an intention to join a circle from an end user; A system including:

2. 2. The system of claim 1, wherein the similarity calculation means calculates the similarity using cosine similarity.

3. The system according to claim 1 , wherein the generating artificial intelligence calculates the similarity of the hobby / interest information using a machine learning model.

Images