system

Abstract

We provide the system. [Solution] Methods for obtaining email addresses, A data analysis means for analyzing text data obtained using the aforementioned email acquisition means, A data storage means for storing the analyzed text data in a database, A query receiving mechanism that accepts queries from users, A response generation means that retrieves data from a database based on a query received by the query receiving means, and sends it to a generative artificial intelligence to generate a response, A means for providing the generated response to the user, A system that includes this.

Description

Technical Field

[0005] ,

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In business, information sharing is carried out using mailing lists and emails. However, when the person in charge changes or when it is necessary to quickly refer to past information, there is a lack of means to efficiently obtain such information. In particular, searching for specific information from a huge amount of emails requires time and effort, and the handover of information becomes complicated every time the person in charge changes. In order to solve such problems, there is a need to provide a system that can quickly and efficiently obtain information from emails and use a generative artificial intelligence to obtain past information in natural language.

Means for Solving the Problems

[0005] To solve the above-mentioned problems, the present invention employs the following means. Specifically, it provides a system that includes an email acquisition means, a data analysis means for analyzing text data acquired using the email acquisition means, a data storage means for storing the analyzed text data in a database, a query receiving means for receiving queries from users, an answer generation means for acquiring data from the database based on queries received by the query receiving means and sending it to a generative artificial intelligence to generate an answer, and an answer providing means for providing the generated answer to the user. With this system, even if the person in charge changes, past email information can be acquired efficiently and quickly, and answers in natural language can be obtained by generative artificial intelligence. This significantly improves business continuity and information transfer.

[0006] "Method for obtaining emails" refers to a method that includes the function of automatically obtaining emails using an API of an email service provider.

[0007] "Data analysis means" refers to means that include the function of extracting text data from acquired emails, analyzing its content, and obtaining necessary information.

[0008] "Data storage means" refers to means that include the function of saving the analyzed text data to a database.

[0009] A "query receiving mechanism" is a means that includes a function to provide an interface for receiving inquiries (queries) from users about specific information.

[0010] "Answer generation means" refers to means that includes a function to retrieve data from a database based on queries received by a query receiving means and generate answers using generative artificial intelligence.

[0011] "Answer provision means" refers to means that include a function to provide users with answers generated by generative artificial intelligence.

[0012] "Generative artificial intelligence" refers to artificial intelligence technology that generates answers in natural language in response to input queries. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers, thereby efficiently acquiring past email information and providing answers in natural language using generative artificial intelligence.

[0035] System Overview

[0036] The server obtains Google® authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). The generated answer is sent to the user via an answer provision means.

[0037] Concrete Program Examples

[0038] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database.

[0039] Processing flow

[0040] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains details for each email and parses its text content. This text data is then stored in a database by the server.

[0041] When a user enters a query into the system, the query reception mechanism receives the query. Based on the received query, the server retrieves the corresponding information from the database and inputs it into the generative artificial intelligence. The generative AI generates the optimal answer based on the query, and the server provides the result to the user.

[0042] Specific example

[0043] For example, a user might input a query into the system saying, "Please tell me how the project will proceed as decided at the meeting last May." After receiving this query, the server queries a generative artificial intelligence system and retrieves a response based on relevant historical data. The response might look like this: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0044] In this way, this system allows users to easily retrieve important historical information and ensures business continuity even when personnel changes occur.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0048] Step 2:

[0049] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0050] Step 3:

[0051] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[0052] Step 4:

[0053] The server extracts the text portion of the email and analyzes the necessary information using data analysis tools. Here, text data is extracted from the email content, and unnecessary parts are removed.

[0054] Step 5:

[0055] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[0056] Step 6:

[0057] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[0058] Step 7:

[0059] The server receives a query entered by the user and sends it to the generative artificial intelligence. Based on the received query, the generative AI retrieves the necessary data from the database to generate an appropriate answer.

[0060] Step 8:

[0061] Generative artificial intelligence generates natural language responses to queries based on data retrieved from a database. The generated responses contain information appropriate to the content of the query.

[0062] Step 9:

[0063] The server receives the response from the generative artificial intelligence and provides it to the user. The user then checks the generated response through their device.

[0064] This processing flow allows users to easily and quickly obtain relevant information based on past email content, ensuring business continuity and efficiency even for new personnel.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] In recent years, email communication has increased, and a large amount of information is now exchanged via email in both business and personal activities. However, efficiently retrieving specific information from a vast amount of past emails and generating quick and appropriate responses based on that information is difficult. In particular, retrieving important information such as details of past meetings or projects when personnel changes occur requires a great deal of time and effort. There is a need to solve this problem by efficiently retrieving past email information and providing responses in natural language using generative artificial intelligence.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes authentication information acquisition means for acquiring authentication information, email acquisition means for acquiring emails from an email service provider's API, data analysis means for analyzing the acquired text data using natural language processing technology, data storage means for storing the data in a database, query reception means for receiving user queries, response generation means for sending prompt sentences to a generative artificial intelligence to generate answers, and response provision means for providing the generated answers to the user. This enables the user to efficiently acquire past email information and to receive answers in natural language using a generative AI model.

[0070] "Authentication information acquisition means" refers to a means of obtaining necessary authentication information by coordinating with the authentication server of an email service provider.

[0071] "Method for obtaining email" refers to the means of obtaining email from an email service provider's API using acquired authentication information.

[0072] "Data analysis means" refers to a method for analyzing the text data of acquired emails using natural language processing technology and extracting important information.

[0073] "Data storage means" refers to means for storing the analyzed text data in a database.

[0074] A "query receiving mechanism" is a means of receiving inquiries from users and processing their content.

[0075] The "response generation means" is a means for retrieving data from a database based on a query received by the query receiving means, and sending a prompt message to a generative artificial intelligence to generate a response.

[0076] "Answer provision means" refers to the means of providing the generated answers to the user.

[0077] "Generative artificial intelligence" is an artificial intelligence technology that generates the optimal answer based on user queries.

[0078] A "prompt" is a sentence input to a generative artificial intelligence system, and it is an instruction sentence that generates a response in response to a user's query.

[0079] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers. This allows for the efficient acquisition of past email information and the provision of answers in natural language using generative artificial intelligence.

[0080] The server plays a key role in operating this system. First, it obtains the necessary authentication information from the email service provider's authentication server using an authentication information acquisition method. At this time, it uses the OAuth2 protocol to obtain permission to access the user's email account. This allows access to the email service provider's APIs, such as the Gmail API.

[0081] Based on the acquired authentication information, the server uses an email retrieval method to retrieve emails associated with a specific label. The retrieved emails are then analyzed using natural language processing techniques with a data analysis method. Specifically, important keywords and phrases are extracted from the email subject and body.

[0082] This analyzed text data is stored in a database using a data storage system. The database has appropriate indexes, allowing for quick subsequent searches.

[0083] Users enter queries into the system via their terminal. For example, they might enter a query such as, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the server via a query reception mechanism.

[0084] The server searches and retrieves relevant information from the database based on the received query. Next, it sends a prompt message to the generative artificial intelligence (AI) using a response generation mechanism. The generative AI (e.g., generative AI model) generates the optimal response based on the provided data.

[0085] The generated responses are provided to the user through a response delivery system. Users can receive these responses via a web interface or a dedicated terminal.

[0086] For example, if a user enters the query "Please tell me how the project will proceed as decided at the meeting last May," the generative artificial intelligence will generate the following response based on relevant historical data: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0087] This system allows users to quickly retrieve important historical information and ensure business continuity.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] Obtaining authentication information

[0091] The server interacts with the email service provider's authentication server to obtain authentication information. Specifically, the server uses the OAuth2 protocol to obtain permission to access the user's email account. The input is the authentication request the server receives, and the output is an authentication code and access token. This information enables subsequent email retrieval.

[0092] Specifically, the server sends a request to Google's authentication URL and receives an authentication code from Google. Using that authentication code, the server obtains an access token.

[0093] Step 2:

[0094] Retrieve emails

[0095] The server uses the acquired authentication information to retrieve emails associated with a specific label (e.g., "mailing list") from the email service provider's API. The input is the access token and the label of the email to be retrieved, and the output is a list of email IDs.

[0096] Specifically, the server sends a request to the Gmail API's "users.messages.list" endpoint to retrieve a list of email IDs. Based on this list, the server retrieves the details of each email from the "users.messages.get" endpoint.

[0097] Step 3:

[0098] Email analysis

[0099] The server analyzes the content of the received emails, using natural language processing techniques. The input is the email body and subject, and the output is the analyzed text data.

[0100] Specifically, the server tokenizes the email body and performs grammatical analysis. It extracts important keywords and phrases and tags them.

[0101] Step 4:

[0102] Storage in database

[0103] The server stores the parsed text data in the database. The input is the parsed text data, and the output is the status of successful data storage. This step ensures that the database is properly indexed, allowing for faster subsequent searches.

[0104] Specifically, the server generates a query to insert text data into an SQL database, executes the query on the database, and then inserts the data.

[0105] Step 5:

[0106] Acceptance of user queries

[0107] The user enters queries into the system using a terminal. The input is a natural language query entered by the user, and the output is the content of that query. For example, it accepts queries such as, "Please tell me how to proceed with the project that was decided at the meeting last May."

[0108] In terms of specific operations, the user enters a query into a web interface or a form on a dedicated terminal and presses the submit button. The query is then sent to the server.

[0109] Step 6:

[0110] Retrieving information from the database

[0111] The server searches and retrieves relevant information from the database based on user queries. The input is the user query, and the output is the corresponding database information.

[0112] Specifically, the server parses the user query and generates an appropriate SQL query. It then executes the generated SQL query against the database and retrieves the results.

[0113] Step 7:

[0114] Answer generation

[0115] The server inputs information retrieved from the database into a generative artificial intelligence (AI) system to generate the optimal response. The input consists of information retrieved from the database and prompt statements, while the output is the generated response. Specific prompt statements are sent to the generative AI system.

[0116] In terms of specific operations, the server sends a prompt message to the generating AI model. For example, it might send a prompt message such as, "Please tell me how to proceed with the project that was decided at the meeting last May," and the generating AI model will generate the best possible answer based on that query.

[0117] Step 8:

[0118] Providing answers to users

[0119] The server provides the user with the generated response. The input is the generated response, and the output is the response displayed to the user.

[0120] In terms of specific operations, the server sends the generated response to the frontend, which then displays the response on the user's screen. The user receives this response via a web interface or a dedicated terminal.

[0121] (Application Example 1)

[0122] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0123] Conventional information retrieval systems made it difficult for users to efficiently search past emails and information. Furthermore, in factory settings, the lack of a way for employees to access necessary information without using their hands often led to decreased work efficiency. To address this challenge, a system is needed that allows employees to quickly retrieve information using wearable devices.

[0124] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0125] In this invention, the server includes email acquisition means, data analysis means, data storage means, query reception means, response generation means, and recognition display means. This makes it possible for a user to efficiently acquire past emails using a wearable device and display a response in natural language on the wearable device's display using generative artificial intelligence.

[0126] "Email acquisition means" refers to a system or device for acquiring emails using an email service provider's API.

[0127] "Data analysis means" refers to a system or device for analyzing text data obtained using email acquisition means and extracting necessary information.

[0128] "Data storage means" refers to a system or device for storing analyzed text data in a database.

[0129] A "query receiving means" is a system or device for receiving queries from users.

[0130] A "response generation means" is a system or device that retrieves data from a database based on queries received by a query receiving means, and sends it to a generative artificial intelligence to generate a response.

[0131] "Answer provision means" refers to a system or device for providing generated answers to users.

[0132] "Recognition display means" refers to a system or device for displaying the generated response on the display of a wearable device.

[0133] "Generative artificial intelligence" refers to artificial intelligence that uses natural language processing technology to generate the optimal answer to a user's query.

[0134] This invention can be implemented as an information retrieval system within a factory. This system allows employees to quickly access specific processes, past meeting records, project progress information, and other relevant data using wearable devices such as smart glasses.

[0135] Hardware and software to be used

[0136] Hardware: Servers, smart glasses, PCs

[0137] Software: Gmail API, SQLite3 database, transformers (GPT-2)

[0138] Program processing

[0139] The server uses the Gmail API through an email retrieval mechanism to obtain the necessary emails. This email retrieval mechanism has the function of centrally collecting emails related to specific labels (e.g., mailing lists) on the server. Next, a data analysis mechanism analyzes the content of the retrieved emails and extracts the necessary information. At this stage, the text portion of the emails is appropriately analyzed and stored in a database so that users can easily search for them.

[0140] When a query from a user is received by the smart glasses, the server's query receiving mechanism receives it and retrieves the corresponding data from the database based on that query. Next, the answer generation mechanism uses generative artificial intelligence (GPT-2) to generate an appropriate answer. This generated answer is displayed on the smart glasses' screen via the server, making it immediately available for the user to review.

[0141] Specific example

[0142] For example, a factory worker wearing smart glasses might ask, "What is the progress of Project X?" This query is processed by a server, which uses generative artificial intelligence to analyze past meeting records and progress reports to generate an answer. The answer is displayed on the smart glasses' screen as follows: "Project X is currently 50% complete, and the next step is to complete Task Y."

[0143] Example of a prompt

[0144] Prompt: Please tell me the progress of Project X.

[0145] As described above, the system of the present invention allows factory workers to obtain necessary information in real time without using their hands, thereby significantly improving work efficiency.

[0146] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0147] Step 1:

[0148] The server uses the Gmail API to retrieve emails associated with a specific label (mailing list). In this processing step, the server authenticates with the Gmail service and uses the label as a filter to retrieve all relevant emails. The input is Gmail credentials and a specific label, and the output is a list of emails. Specifically, it uses an API request to obtain a list of email IDs, and then retrieves detailed information for each email.

[0149] Step 2:

[0150] The server analyzes the acquired emails using data analysis tools. This includes a process of extracting the text content of the emails. The input is the text information of the emails acquired in step 1, and the output is the analyzed text data. Specifically, a text analysis algorithm is applied to extract the text portion of the emails, and the necessary information is extracted and converted into a format for storage in the database.

[0151] Step 3:

[0152] The server stores the parsed text data in a database. The input is the text data generated in step 2, and the output is the structured data stored in the database. Specifically, it performs insert operations into the database and sets up necessary indexes to support efficient query searches.

[0153] Step 4:

[0154] The user enters queries through smart glasses. The input is the query made by the user using voice or an input device, and the output is the query data sent to the server. Specifically, the smart glasses' microphone or input device is used to collect queries and send them to the server.

[0155] Step 5:

[0156] The server retrieves relevant data from the database based on queries received by the query reception mechanism. The input is query data, and the output is related text data. Specifically, it searches the database based on the query and extracts the corresponding data.

[0157] Step 6:

[0158] The server uses generative artificial intelligence as a means of generating answers, and generates responses to user queries based on acquired data. The input consists of text data and the query content, and the output is a generated natural language response. Specifically, the operation includes a process of inputting the query and data into a generative AI model such as GPT-2 and generating the optimal response.

[0159] Step 7:

[0160] The server sends the generated response to the smart glasses and displays it on the screen. The input is the generated response, and the output is the response displayed on the smart glasses' screen. Specifically, the process involves converting the text data into the smart glasses' display format and displaying it to the user at the appropriate time.

[0161] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0162] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers, and further incorporates an emotion engine that recognizes the user's emotions. This system makes it possible to efficiently acquire past email information, provide answers in natural language using generative artificial intelligence, and generate optimal answers according to the user's emotional state.

[0163] System Overview

[0164] The server obtains Google authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). At this time, an emotion engine evaluates the user's emotional state from the query and response, and the answer generation means generates an answer that is appropriate to that emotional state. The generated answer is sent to the user via an answer provision means.

[0165] Concrete Program Examples

[0166] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (e.g., mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database. The sentiment engine analyzes the user's emotional state from the user's input queries and responses from the system, and provides the analysis results to the response generation method.

[0167] Processing flow

[0168] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains detailed information about each email and parses its text content. This text data is then stored in a database by the server.

[0169] When a user enters a query into the system, a query reception mechanism receives the query. The server analyzes the received query using an emotion engine and evaluates the user's emotional state. It then sends the query to a generative artificial intelligence (AI). The generative AI retrieves corresponding information from the database based on the received query and generates the optimal answer while taking the user's emotions into consideration.

[0170] Specific example

[0171] For example, if a user enters a query into the system such as, "Please tell me how the project will proceed as decided at the meeting last May," the emotion engine will analyze the user's emotional state after receiving the query. If the system determines that the user is feeling anxious, the generative artificial intelligence will use that information to generate a response that takes the user's emotions into consideration, such as, "Please rest assured. The following progress plan was decided at the meeting last May. Task A will be handled by person B, and Task C will be handled by person D."

[0172] In this way, the system can provide information adapted to the user's emotional state, and along with retrieving past email information, it realizes interactions that enhance the user's sense of security and satisfaction.

[0173] The following describes the processing flow.

[0174] Step 1:

[0175] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0176] Step 2:

[0177] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0178] Step 3:

[0179] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[0180] Step 4:

[0181] The server extracts the text portion of the email and uses data analysis tools to analyze the necessary information. Here, text data is extracted from the email content, and unnecessary parts are removed.

[0182] Step 5:

[0183] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[0184] Step 6:

[0185] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[0186] Step 7:

[0187] The terminal sends the query entered by the user to the server.

[0188] Step 8:

[0189] The server receives the query and the emotion engine analyzes the user's emotional state. The emotion engine analyzes the query content and input method (such as keystroke speed and timing) to determine the user's emotional state.

[0190] Step 9:

[0191] The server sends the query to the generative artificial intelligence system along with the analysis results of the emotion engine.

[0192] Step 10:

[0193] The generative artificial intelligence retrieves corresponding information from the database based on the query and the results of the emotion engine's analysis, and generates a response that takes the user's emotional state into consideration. For example, if the user is feeling anxious, the response's tone will be adjusted to be gentler.

[0194] Step 11:

[0195] The server receives the response from the generative artificial intelligence and provides that response to the user. The response is displayed through the terminal.

[0196] Step 12:

[0197] The user reviews the response generated through their device and re-enters the query if necessary.

[0198] This processing flow allows users to easily and quickly obtain relevant information based on past email content, and also enables interaction tailored to the user's emotional state. This enhances business continuity and efficiency while improving user satisfaction and peace of mind.

[0199] (Example 2)

[0200] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0201] Traditional email management systems have struggled to efficiently retrieve and analyze past email information. Furthermore, few systems utilize generative artificial intelligence to provide appropriate responses to user queries, and they particularly lack mechanisms for generating responses that consider the user's emotional state. This makes it difficult to achieve interactions that enhance user satisfaction.

[0202] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0203] In this invention, the server includes an email acquisition means, a data analysis means for analyzing text data acquired using the email acquisition means, a data storage means for storing the analyzed text data in a database, a query receiving means for receiving queries from users, an answer generation means for acquiring data from the database based on queries received by the query receiving means and sending it to a generative artificial intelligence model to generate an answer, an emotion analysis means for analyzing the user's emotional state and providing the analysis results to the answer generation means, and an answer provision means for providing the generated answer to the user. This makes it possible to efficiently acquire and analyze past email information and generate and provide answers that correspond to the user's emotional state.

[0204] "Method of obtaining email" refers to a method of obtaining email using an API of an email service provider.

[0205] "Data analysis means" refers to methods for analyzing the text data of acquired emails and extracting necessary information.

[0206] "Data storage means" refers to the means of storing the analyzed text data in a database.

[0207] A "query receiving mechanism" is a means of receiving queries from users.

[0208] The "response generation means" is a means of retrieving data from a database based on a query received by the query receiving means, and sending it to a generative artificial intelligence model to generate a response.

[0209] "Emotional analysis means" refers to a method for analyzing a user's emotional state from user queries and system responses.

[0210] "Answer provision means" refers to the means of providing the generated answer to the user.

[0211] A "generative artificial intelligence model" is an artificial intelligence technology that retrieves necessary information from a database based on a received query and generates an appropriate response.

[0212] This invention is a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating responses, means for analyzing sentiment, and means for providing responses. The following hardware and software are used to implement this system.

[0213] Hardware to use

[0214] Server machine: Cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[0215] Software to use

[0216] Email acquisition methods: Google OAuth authentication and Gmail API

[0217] Data analysis method: Text analysis library (e.g., BeautifulSoup)

[0218] Data storage method: Database (e.g., PostgreSQL, MySQL®)

[0219] Generative artificial intelligence models: Natural language processing models (e.g., OpenAI®, GPT-3®)

[0220] Sentiment analysis method: Sentiment Analysis API (e.g. Sentiment Analysis API)

[0221] Program processing

[0222] First, the server obtains Google's OAuth credentials and uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The retrieved emails are passed to a data analysis tool, converted into text data, and then stored in a database. For example, the server sends an authentication request to the user's Google account and obtains an access token.

[0223] Next, the user uses a terminal to enter a query into the system. For example, they might enter, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the query reception mechanism and sent by the server to the sentiment analysis mechanism. The sentiment analysis mechanism analyzes the user's emotional state from the query and stores the results. For example, if it is determined that the user is experiencing anxiety, the results are used in the next process.

[0224] Based on the sentiment analysis results, the server sends queries and sentiment information to a generative artificial intelligence model. For example, it might send a prompt to the generative AI model saying, "The user is feeling anxious. Please tell me about the project's progress as decided at the meeting in May of last year." The generative AI model searches the database for relevant information and generates an appropriate response. The generated response is then provided to the user through a response delivery system. For example, a response that reassures the user might be provided in the form of, "Please rest assured. The following progress plan was decided at the meeting in May of last year. Task A will be handled by B, and Task C will be handled by D."

[0225] This system efficiently acquires and analyzes past email information, and generates and provides optimal responses tailored to the user's emotional state, thereby achieving interactions that enhance user satisfaction.

[0226] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0227] Step 1:

[0228] The server obtains authentication information using Google OAuth authentication. The input is the user's Google account information, and the output is a token that grants access to Google. The server sends an authentication request to the user's Google account and obtains an authentication code. Next, it uses this authentication code to obtain an access token.

[0229] Step 2:

[0230] The server uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The input is an access token and label information, and the output is a list of emails. The server temporarily stores the IDs and contents of the retrieved emails as a list, preparing for the next processing step.

[0231] Step 3:

[0232] The server converts the retrieved email content into text data and extracts the necessary information. The input is an email list, and the output is text data and metadata (sender, subject, date and time, etc.). The server uses a text analysis library (e.g., BeautifulSoup) to convert the email body into text format and saves it as dictionary data along with the metadata.

[0233] Step 4:

[0234] The server stores the parsed text data in a database (e.g., PostgreSQL, MySQL). The input is text data and metadata, and the output is the database containing this data. The server inserts this data into the corresponding tables in the database.

[0235] Step 5:

[0236] The user enters a query into the system using a terminal. The input is a query requesting specific information, and the output is query data stored in the query reception device. For example, the user might enter, "Please tell me how to proceed with the project that was decided at the meeting in May of last year."

[0237] Step 6:

[0238] The server sends a query to a sentiment analysis system, which then analyzes the user's emotional state. The input is the query data, and the output is the sentiment analysis result. The sentiment analysis system uses natural language processing techniques (e.g., Sentiment Analysis API) to evaluate the user's emotional state from the query text. For example, it might analyze that the user is in an anxious state.

[0239] Step 7:

[0240] The server sends queries and sentiment information to a generative artificial intelligence model based on the sentiment analysis results. The input is query data and sentiment analysis results, and the output is the generated response. For example, the prompt "The user is feeling anxious. Please tell me about the project progress that was decided at the meeting last May." is sent to the generative artificial intelligence model. The generative artificial intelligence model searches the database for relevant information and generates an appropriate response.

[0241] Step 8:

[0242] The server provides the user with a generated response. The input is the generated response, and the output is the response displayed on the user's terminal. For example, it might provide a response such as, "Please rest assured. At the meeting in May of last year, the following procedure was decided: Task A will be handled by B, and Task C will be handled by D."

[0243] This series of steps enables the system to efficiently retrieve and analyze past email information and generate and provide appropriate responses tailored to the user's emotional state.

[0244] (Application Example 2)

[0245] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0246] Conventional email analysis systems analyze text data from emails and provide answers to user queries. However, they cannot consider the user's emotional state, making it difficult to provide interactions optimized for the user's feelings. Furthermore, if a user is experiencing emotional stress, inappropriate responses may lead to decreased satisfaction and trust. Therefore, there is a need for a system that analyzes the user's emotional state and generates responses that reflect it.

[0247] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0248] In this invention, the server includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing emotions, means for generating answers, and means for providing answers. This makes it possible to generate and provide the optimal answer according to the user's emotional state.

[0249] "Electronic message retrieval means" refers to a means of retrieving a specific message using the application programming interface of an electronic message service provider.

[0250] "Data analysis means" refers to a means of extracting and analyzing text data from acquired electronic messages.

[0251] "Data storage means" refers to means for storing the analyzed text data in a database.

[0252] A "query receiving method" is a means of receiving inquiries (queries) from users.

[0253] An "emotional analysis tool" is a means of analyzing a user's emotional state and providing the results of that analysis.

[0254] A "response generation method" is a means of retrieving data from a database based on a received query and generating a response using generative artificial intelligence.

[0255] "Answer provision means" refers to the means of providing the generated answers to users.

[0256] "Generative artificial intelligence" is an artificial intelligence technology that generates natural language responses based on user queries.

[0257] The present invention is a system that includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing sentiment, means for generating answers, and means for providing answers, thereby providing the optimal answer to the user's query according to their emotional state.

[0258] This system is configured as follows:

[0259] ---

[0260] The server obtains Google authentication credentials and configures itself to operate the Gmail API. It uses an electronic message retrieval method to retrieve emails related to mailing lists and specific labels. This retrieved text data is then analyzed by a data analysis tool, converted into text information, and stored in a database.

[0261] The terminal provides a user interface for users to input queries to the system. These queries are sent to the server by a query receiving mechanism. The server analyzes the received queries using an emotion analysis mechanism to evaluate the user's emotional state. Specifically, it reads the emotional state from the context of the query and the user's expressions, detecting states such as "excited" or "anxious."

[0262] Based on the sentiment analysis results, the server uses a response generation mechanism to send a query to a generative AI model (e.g., GPT-3) and generates a response adapted to the emotional state. In this response generation process, the content of the response is adjusted to accurately provide the necessary information while taking the user's emotions into consideration.

[0263] On the device, the user receives the generated response. Because the response is displayed through the response delivery method, the user can receive a response that takes their emotional state into consideration.

[0264] Hardware and software to be used

[0265] Hardware: Servers (cloud or on-premises), user devices (smartphones, head-mounted displays, etc.)

[0266] Software: Gmail API, SQLite, TENSORFLOW®, Generative AI models (e.g., OpenAI's GPT-3)

[0267] Specific example

[0268] For example, if a user enters the query "Tell me about the latest promotions," the sentiment analysis tool will determine that the user is "interested." Based on this result, a generative AI model will generate a response containing more engaging content, such as "Would you like to see our latest promotions? Certain items are currently 20% off." Finally, this response will be displayed on the device and provided to the user.

[0269] Example of a prompt

[0270] Query: "Tell me about your latest promotions."

[0271] Sentiment analysis results: "Interest"

[0272] AI response: "Here's our latest promotion. Certain products are currently available at 20% off."

[0273] Thus, the present invention can provide a better user experience by providing information that is tailored to the user's emotional state.

[0274] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0275] Step 1:

[0276] The server retrieves electronic messages through the application programming interface of the electronic message service provider. The input consists of authentication information and the message label to be retrieved, while the output is a list of retrieved messages. The server receives the retrieved messages in batches.

[0277] Step 2:

[0278] The server analyzes received electronic messages using data analysis tools. The input is a list of acquired messages, and the output is the analyzed text data. The server extracts the text portion from the messages and performs grammatical analysis and keyword extraction.

[0279] Step 3:

[0280] The server stores the parsed text data in a database. The input is the parsed text data, and the output is the parsed data stored in the database. The server inserts the corresponding data into the appropriate table in the database.

[0281] Step 4:

[0282] The user inputs a query through the terminal and sends it to the server through the query reception means. The input is the user's query, and the output is the query transmission to the server. The query processing is started by the user's input.

[0283] Step 5:

[0284] The server analyzes the received query with the sentiment analysis means. The input is the user's query, and the output is the evaluation result of the sentiment state based on the query. The server analyzes the content and expression of the query to determine the user's sentiment.

[0285] Step 6:

[0286] The server sends the query to the generation AI model based on the sentiment analysis result to generate an optimal answer. The input is the sentiment analysis result and the query, and the output is the generated answer. The generation AI model obtains appropriate information from the database and generates an answer in natural language.

[0287] Step 7:

[0288] The server sends the generated answer to the terminal through the answer providing means. The input is the generated answer, and the output is the answer transmission to the terminal. By the server sending the answer to the terminal, the user can receive an appropriate answer.

[0289] Step 8:

[0290] The user checks the answer generated on the terminal and executes the next action. The input is the transmitted answer, and the output is the user's next action. The user takes the next inquiry or action based on the answer.

[0291] <00009The 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0292] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0293] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0294] [Second Embodiment]

[0295] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0296] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0297] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0298] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0299] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0300] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0301] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0302] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0303] The specific processing program 56 is an example of the "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by operating as the specific processing unit 290 according to the specific processing program 56 executed by the processor 28 on the RAM 30.

[0304] 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 specific processing unit 290.

[0305] In the smart glasses 214, the processor 46 performs reception / output processing. The storage 50 stores a reception / output program 60. 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 processing is realized by operating as the control unit 46A according to the reception / output program 60 executed by the processor 46 on the RAM 48.

[0306] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0307] The present invention is a system including an e-mail acquisition means, a data analysis means, a data storage means, a query reception means, an answer generation means, and an answer providing means, thereby efficiently acquiring past e-mail information and providing an answer in natural language using a generative artificial intelligence.

[0308] Overview of the entire system

[0309] The server obtains Google authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). The generated answer is sent to the user via an answer provision means.

[0310] Concrete Program Examples

[0311] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database.

[0312] Processing flow

[0313] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains details for each email and parses its text content. This text data is then stored in a database by the server.

[0314] When a user enters a query into the system, the query reception mechanism receives the query. Based on the received query, the server retrieves the corresponding information from the database and inputs it into the generative artificial intelligence. The generative AI generates the optimal answer based on the query, and the server provides the result to the user.

[0315] Specific example

[0316] For example, a user might input a query into the system saying, "Please tell me how the project will proceed as decided at the meeting last May." After receiving this query, the server queries a generative artificial intelligence system and retrieves a response based on relevant historical data. The response might look like this: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0317] In this way, this system allows users to easily retrieve important historical information and ensures business continuity even when personnel changes occur.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0321] Step 2:

[0322] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0323] Step 3:

[0324] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[0325] Step 4:

[0326] The server extracts the text portion of the email and analyzes the necessary information using data analysis tools. Here, text data is extracted from the email content, and unnecessary parts are removed.

[0327] Step 5:

[0328] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[0329] Step 6:

[0330] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[0331] Step 7:

[0332] The server receives a query entered by the user and sends it to the generative artificial intelligence. Based on the received query, the generative AI retrieves the necessary data from the database to generate an appropriate answer.

[0333] Step 8:

[0334] Generative artificial intelligence generates natural language responses to queries based on data retrieved from a database. The generated responses contain information appropriate to the content of the query.

[0335] Step 9:

[0336] The server receives the response from the generative artificial intelligence and provides it to the user. The user then checks the generated response through their device.

[0337] This processing flow allows users to easily and quickly obtain relevant information based on past email content, ensuring business continuity and efficiency even for new personnel.

[0338] (Example 1)

[0339] Next, we will describe Example 1. 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".

[0340] In recent years, email communication has increased, and a large amount of information is now exchanged via email in both business and personal activities. However, efficiently retrieving specific information from a vast amount of past emails and generating quick and appropriate responses based on that information is difficult. In particular, retrieving important information such as details of past meetings or projects when personnel changes occur requires a great deal of time and effort. There is a need to solve this problem by efficiently retrieving past email information and providing responses in natural language using generative artificial intelligence.

[0341] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0342] In this invention, the server includes authentication information acquisition means for acquiring authentication information, email acquisition means for acquiring emails from an email service provider's API, data analysis means for analyzing the acquired text data using natural language processing technology, data storage means for storing the data in a database, query reception means for receiving user queries, response generation means for sending prompt sentences to a generative artificial intelligence to generate answers, and response provision means for providing the generated answers to the user. This enables the user to efficiently acquire past email information and to receive answers in natural language using a generative AI model.

[0343] "Authentication information acquisition means" refers to a means of obtaining necessary authentication information by coordinating with the authentication server of an email service provider.

[0344] "Method for obtaining email" refers to the means of obtaining email from an email service provider's API using acquired authentication information.

[0345] "Data analysis means" refers to a method for analyzing the text data of acquired emails using natural language processing technology and extracting important information.

[0346] "Data storage means" refers to means for storing the analyzed text data in a database.

[0347] A "query receiving mechanism" is a means of receiving inquiries from users and processing their content.

[0348] The "response generation means" is a means for retrieving data from a database based on a query received by the query receiving means, and sending a prompt message to a generative artificial intelligence to generate a response.

[0349] "Answer provision means" refers to the means of providing the generated answers to the user.

[0350] "Generative artificial intelligence" is an artificial intelligence technology that generates the optimal answer based on user queries.

[0351] A "prompt" is a sentence input to a generative artificial intelligence system, and it is an instruction sentence that generates a response in response to a user's query.

[0352] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers. This allows for the efficient acquisition of past email information and the provision of answers in natural language using generative artificial intelligence.

[0353] The server plays a key role in operating this system. First, it obtains the necessary authentication information from the email service provider's authentication server using an authentication information acquisition method. At this time, it uses the OAuth2 protocol to obtain permission to access the user's email account. This allows access to the email service provider's APIs, such as the Gmail API.

[0354] Based on the acquired authentication information, the server uses an email retrieval method to retrieve emails associated with a specific label. The retrieved emails are then analyzed using natural language processing techniques with a data analysis method. Specifically, important keywords and phrases are extracted from the email subject and body.

[0355] This analyzed text data is stored in a database using a data storage system. The database has appropriate indexes, allowing for quick subsequent searches.

[0356] Users enter queries into the system via their terminal. For example, they might enter a query such as, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the server via a query reception mechanism.

[0357] The server searches and retrieves relevant information from the database based on the received query. Next, it sends a prompt message to the generative artificial intelligence (AI) using a response generation mechanism. The generative AI (e.g., generative AI model) generates the optimal response based on the provided data.

[0358] The generated responses are provided to the user through a response delivery system. Users can receive these responses via a web interface or a dedicated terminal.

[0359] For example, if a user enters the query "Please tell me how the project will proceed as decided at the meeting last May," the generative artificial intelligence will generate the following response based on relevant historical data: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0360] This system allows users to quickly retrieve important historical information and ensure business continuity.

[0361] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0362] Step 1:

[0363] Obtaining authentication information

[0364] The server interacts with the email service provider's authentication server to obtain authentication information. Specifically, the server uses the OAuth2 protocol to obtain permission to access the user's email account. The input is the authentication request the server receives, and the output is an authentication code and access token. This information enables subsequent email retrieval.

[0365] Specifically, the server sends a request to Google's authentication URL and receives an authentication code from Google. Using that authentication code, the server obtains an access token.

[0366] Step 2:

[0367] Retrieve emails

[0368] The server uses the acquired authentication information to retrieve emails associated with a specific label (e.g., "mailing list") from the email service provider's API. The input is the access token and the label of the email to be retrieved, and the output is a list of email IDs.

[0369] Specifically, the server sends a request to the Gmail API's "users.messages.list" endpoint to retrieve a list of email IDs. Based on this list, the server retrieves the details of each email from the "users.messages.get" endpoint.

[0370] Step 3:

[0371] Email analysis

[0372] The server analyzes the content of the received emails, using natural language processing techniques. The input is the email body and subject, and the output is the analyzed text data.

[0373] Specifically, the server tokenizes the email body and performs grammatical analysis. It extracts important keywords and phrases and tags them.

[0374] Step 4:

[0375] Storage in database

[0376] The server stores the parsed text data in the database. The input is the parsed text data, and the output is the status of successful data storage. This step ensures that the database is properly indexed, allowing for faster subsequent searches.

[0377] Specifically, the server generates a query to insert text data into an SQL database, executes the query on the database, and then inserts the data.

[0378] Step 5:

[0379] Acceptance of user queries

[0380] The user enters queries into the system using a terminal. The input is a natural language query entered by the user, and the output is the content of that query. For example, it accepts queries such as, "Please tell me how to proceed with the project that was decided at the meeting last May."

[0381] In terms of specific operations, the user enters a query into a web interface or a form on a dedicated terminal and presses the submit button. The query is then sent to the server.

[0382] Step 6:

[0383] Retrieving information from the database

[0384] The server searches and retrieves relevant information from the database based on user queries. The input is the user query, and the output is the corresponding database information.

[0385] Specifically, the server parses the user query and generates an appropriate SQL query. It then executes the generated SQL query against the database and retrieves the results.

[0386] Step 7:

[0387] Answer generation

[0388] The server inputs information retrieved from the database into a generative artificial intelligence (AI) system to generate the optimal response. The input consists of information retrieved from the database and prompt statements, while the output is the generated response. Specific prompt statements are sent to the generative AI system.

[0389] In terms of specific operations, the server sends a prompt message to the generating AI model. For example, it might send a prompt message such as, "Please tell me how to proceed with the project that was decided at the meeting last May," and the generating AI model will generate the best possible answer based on that query.

[0390] Step 8:

[0391] Providing answers to users

[0392] The server provides the user with the generated response. The input is the generated response, and the output is the response displayed to the user.

[0393] In terms of specific operations, the server sends the generated response to the frontend, which then displays the response on the user's screen. The user receives this response via a web interface or a dedicated terminal.

[0394] (Application Example 1)

[0395] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0396] Conventional information retrieval systems made it difficult for users to efficiently search past emails and information. Furthermore, in factory settings, the lack of a way for employees to access necessary information without using their hands often led to decreased work efficiency. To address this challenge, a system is needed that allows employees to quickly retrieve information using wearable devices.

[0397] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0398] In this invention, the server includes email acquisition means, data analysis means, data storage means, query reception means, response generation means, and recognition display means. This makes it possible for a user to efficiently acquire past emails using a wearable device and display a response in natural language on the wearable device's display using generative artificial intelligence.

[0399] "Email acquisition means" refers to a system or device for acquiring emails using an email service provider's API.

[0400] "Data analysis means" refers to a system or device for analyzing text data obtained using email acquisition means and extracting necessary information.

[0401] "Data storage means" refers to a system or device for storing analyzed text data in a database.

[0402] A "query receiving means" is a system or device for receiving queries from users.

[0403] A "response generation means" is a system or device that retrieves data from a database based on queries received by a query receiving means, and sends it to a generative artificial intelligence to generate a response.

[0404] "Answer provision means" refers to a system or device for providing generated answers to users.

[0405] "Recognition display means" refers to a system or device for displaying the generated response on the display of a wearable device.

[0406] "Generative artificial intelligence" refers to artificial intelligence that uses natural language processing technology to generate the optimal answer to a user's query.

[0407] This invention can be implemented as an information retrieval system within a factory. This system allows employees to quickly access specific processes, past meeting records, project progress information, and other relevant data using wearable devices such as smart glasses.

[0408] Hardware and software to be used

[0409] Hardware: Servers, smart glasses, PCs

[0410] Software: Gmail API, SQLite3 database, transformers (GPT-2)

[0411] Program processing

[0412] The server uses the Gmail API through an email retrieval mechanism to obtain the necessary emails. This email retrieval mechanism has the function of centrally collecting emails related to specific labels (e.g., mailing lists) on the server. Next, a data analysis mechanism analyzes the content of the retrieved emails and extracts the necessary information. At this stage, the text portion of the emails is appropriately analyzed and stored in a database so that users can easily search for them.

[0413] When a query from a user is received by the smart glasses, the server's query receiving mechanism receives it and retrieves the corresponding data from the database based on that query. Next, the answer generation mechanism uses generative artificial intelligence (GPT-2) to generate an appropriate answer. This generated answer is displayed on the smart glasses' screen via the server, making it immediately available for the user to review.

[0414] Specific example

[0415] For example, a factory worker wearing smart glasses might ask, "What is the progress of Project X?" This query is processed by a server, which uses generative artificial intelligence to analyze past meeting records and progress reports to generate an answer. The answer is displayed on the smart glasses' screen as follows: "Project X is currently 50% complete, and the next step is to complete Task Y."

[0416] Example of a prompt

[0417] Prompt: Please tell me the progress of Project X.

[0418] As described above, the system of the present invention allows factory workers to obtain necessary information in real time without using their hands, thereby significantly improving work efficiency.

[0419] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0420] Step 1:

[0421] The server uses the Gmail API to retrieve emails associated with a specific label (mailing list). In this processing step, the server authenticates with the Gmail service and uses the label as a filter to retrieve all relevant emails. The input is Gmail credentials and a specific label, and the output is a list of emails. Specifically, it uses an API request to obtain a list of email IDs, and then retrieves detailed information for each email.

[0422] Step 2:

[0423] The server analyzes the acquired emails using data analysis tools. This includes a process of extracting the text content of the emails. The input is the text information of the emails acquired in step 1, and the output is the analyzed text data. Specifically, a text analysis algorithm is applied to extract the text portion of the emails, and the necessary information is extracted and converted into a format for storage in the database.

[0424] Step 3:

[0425] The server stores the parsed text data in a database. The input is the text data generated in step 2, and the output is the structured data stored in the database. Specifically, it performs insert operations into the database and sets up necessary indexes to support efficient query searches.

[0426] Step 4:

[0427] The user enters queries through smart glasses. The input is the query made by the user using voice or an input device, and the output is the query data sent to the server. Specifically, the smart glasses' microphone or input device is used to collect queries and send them to the server.

[0428] Step 5:

[0429] The server retrieves relevant data from the database based on queries received by the query reception mechanism. The input is query data, and the output is related text data. Specifically, it searches the database based on the query and extracts the corresponding data.

[0430] Step 6:

[0431] The server uses generative artificial intelligence as a means of generating answers, and generates responses to user queries based on acquired data. The input consists of text data and the query content, and the output is a generated natural language response. Specifically, the operation includes a process of inputting the query and data into a generative AI model such as GPT-2 and generating the optimal response.

[0432] Step 7:

[0433] The server sends the generated response to the smart glasses and displays it on the screen. The input is the generated response, and the output is the response displayed on the smart glasses' screen. Specifically, the process involves converting the text data into the smart glasses' display format and displaying it to the user at the appropriate time.

[0434] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0435] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers, and further incorporates an emotion engine that recognizes the user's emotions. This system makes it possible to efficiently acquire past email information, provide answers in natural language using generative artificial intelligence, and generate optimal answers according to the user's emotional state.

[0436] System Overview

[0437] The server obtains Google authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). At this time, an emotion engine evaluates the user's emotional state from the query and response, and the answer generation means generates an answer that is appropriate to that emotional state. The generated answer is sent to the user via an answer provision means.

[0438] Concrete Program Examples

[0439] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (e.g., mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database. The sentiment engine analyzes the user's emotional state from the user's input queries and responses from the system, and provides the analysis results to the response generation method.

[0440] Processing flow

[0441] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains detailed information about each email and parses its text content. This text data is then stored in a database by the server.

[0442] When a user enters a query into the system, a query reception mechanism receives the query. The server analyzes the received query using an emotion engine and evaluates the user's emotional state. It then sends the query to a generative artificial intelligence (AI). The generative AI retrieves corresponding information from the database based on the received query and generates the optimal answer while taking the user's emotions into consideration.

[0443] Specific example

[0444] For example, if a user enters a query into the system such as, "Please tell me how the project will proceed as decided at the meeting last May," the emotion engine will analyze the user's emotional state after receiving the query. If the system determines that the user is feeling anxious, the generative artificial intelligence will use that information to generate a response that takes the user's emotions into consideration, such as, "Please rest assured. The following progress plan was decided at the meeting last May. Task A will be handled by person B, and Task C will be handled by person D."

[0445] In this way, the system can provide information adapted to the user's emotional state, and along with retrieving past email information, it realizes interactions that enhance the user's sense of security and satisfaction.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0449] Step 2:

[0450] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0451] Step 3:

[0452] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[0453] Step 4:

[0454] The server extracts the text portion of the email and uses data analysis tools to analyze the necessary information. Here, text data is extracted from the email content, and unnecessary parts are removed.

[0455] Step 5:

[0456] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[0457] Step 6:

[0458] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[0459] Step 7:

[0460] The terminal sends the query entered by the user to the server.

[0461] Step 8:

[0462] The server receives the query and the emotion engine analyzes the user's emotional state. The emotion engine analyzes the query content and input method (such as keystroke speed and timing) to determine the user's emotional state.

[0463] Step 9:

[0464] The server sends the query to the generative artificial intelligence system along with the analysis results of the emotion engine.

[0465] Step 10:

[0466] The generative artificial intelligence retrieves corresponding information from the database based on the query and the results of the emotion engine's analysis, and generates a response that takes the user's emotional state into consideration. For example, if the user is feeling anxious, the response's tone will be adjusted to be gentler.

[0467] Step 11:

[0468] The server receives the response from the generative artificial intelligence and provides that response to the user. The response is displayed through the terminal.

[0469] Step 12:

[0470] The user reviews the response generated through their device and re-enters the query if necessary.

[0471] This processing flow allows users to easily and quickly obtain relevant information based on past email content, and also enables interaction tailored to the user's emotional state. This enhances business continuity and efficiency while improving user satisfaction and peace of mind.

[0472] (Example 2)

[0473] Next, we will describe Example 2. 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".

[0474] Traditional email management systems have struggled to efficiently retrieve and analyze past email information. Furthermore, few systems utilize generative artificial intelligence to provide appropriate responses to user queries, and they particularly lack mechanisms for generating responses that consider the user's emotional state. This makes it difficult to achieve interactions that enhance user satisfaction.

[0475] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0476] In this invention, the server includes an email acquisition means, a data analysis means for analyzing text data acquired using the email acquisition means, a data storage means for storing the analyzed text data in a database, a query receiving means for receiving queries from users, an answer generation means for acquiring data from the database based on queries received by the query receiving means and sending it to a generative artificial intelligence model to generate an answer, an emotion analysis means for analyzing the user's emotional state and providing the analysis results to the answer generation means, and an answer provision means for providing the generated answer to the user. This makes it possible to efficiently acquire and analyze past email information and generate and provide answers that correspond to the user's emotional state.

[0477] "Method of obtaining email" refers to a method of obtaining email using an API of an email service provider.

[0478] "Data analysis means" refers to methods for analyzing the text data of acquired emails and extracting necessary information.

[0479] "Data storage means" refers to the means of storing the analyzed text data in a database.

[0480] A "query receiving mechanism" is a means of receiving queries from users.

[0481] The "response generation means" is a means of retrieving data from a database based on a query received by the query receiving means, and sending it to a generative artificial intelligence model to generate a response.

[0482] "Emotional analysis means" refers to a method for analyzing a user's emotional state from user queries and system responses.

[0483] "Answer provision means" refers to the means of providing the generated answer to the user.

[0484] A "generative artificial intelligence model" is an artificial intelligence technology that retrieves necessary information from a database based on a received query and generates an appropriate response.

[0485] This invention is a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating responses, means for analyzing sentiment, and means for providing responses. The following hardware and software are used to implement this system.

[0486] Hardware to use

[0487] Server machine: Cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[0488] Software to use

[0489] Email acquisition methods: Google OAuth authentication and Gmail API

[0490] Data analysis method: Text analysis library (e.g., BeautifulSoup)

[0491] Data storage method: Database (e.g., PostgreSQL, MySQL)

[0492] Generative artificial intelligence models: Natural language processing models (e.g., OpenAI GPT-3)

[0493] Sentiment analysis method: Sentiment Analysis API (e.g. Sentiment Analysis API)

[0494] Program processing

[0495] First, the server obtains Google's OAuth credentials and uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The retrieved emails are passed to a data analysis tool, converted into text data, and then stored in a database. For example, the server sends an authentication request to the user's Google account and obtains an access token.

[0496] Next, the user uses a terminal to enter a query into the system. For example, they might enter, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the query reception mechanism and sent by the server to the sentiment analysis mechanism. The sentiment analysis mechanism analyzes the user's emotional state from the query and stores the results. For example, if it is determined that the user is experiencing anxiety, the results are used in the next process.

[0497] Based on the sentiment analysis results, the server sends queries and sentiment information to a generative artificial intelligence model. For example, it might send a prompt to the generative AI model saying, "The user is feeling anxious. Please tell me about the project's progress as decided at the meeting in May of last year." The generative AI model searches the database for relevant information and generates an appropriate response. The generated response is then provided to the user through a response delivery system. For example, a response that reassures the user might be provided in the form of, "Please rest assured. The following progress plan was decided at the meeting in May of last year. Task A will be handled by B, and Task C will be handled by D."

[0498] This system efficiently acquires and analyzes past email information, and generates and provides optimal responses tailored to the user's emotional state, thereby achieving interactions that enhance user satisfaction.

[0499] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0500] Step 1:

[0501] The server obtains authentication information using Google OAuth authentication. The input is the user's Google account information, and the output is a token that grants access to Google. The server sends an authentication request to the user's Google account and obtains an authentication code. Next, it uses this authentication code to obtain an access token.

[0502] Step 2:

[0503] The server uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The input is an access token and label information, and the output is a list of emails. The server temporarily stores the IDs and contents of the retrieved emails as a list, preparing for the next processing step.

[0504] Step 3:

[0505] The server converts the retrieved email content into text data and extracts the necessary information. The input is an email list, and the output is text data and metadata (sender, subject, date and time, etc.). The server uses a text analysis library (e.g., BeautifulSoup) to convert the email body into text format and saves it as dictionary data along with the metadata.

[0506] Step 4:

[0507] The server stores the parsed text data in a database (e.g., PostgreSQL, MySQL). The input is text data and metadata, and the output is the database containing this data. The server inserts this data into the corresponding tables in the database.

[0508] Step 5:

[0509] The user enters a query into the system using a terminal. The input is a query requesting specific information, and the output is query data stored in the query reception device. For example, the user might enter, "Please tell me how to proceed with the project that was decided at the meeting in May of last year."

[0510] Step 6:

[0511] The server sends a query to a sentiment analysis system, which then analyzes the user's emotional state. The input is the query data, and the output is the sentiment analysis result. The sentiment analysis system uses natural language processing techniques (e.g., Sentiment Analysis API) to evaluate the user's emotional state from the query text. For example, it might analyze that the user is in an anxious state.

[0512] Step 7:

[0513] The server sends queries and sentiment information to a generative artificial intelligence model based on the sentiment analysis results. The input is query data and sentiment analysis results, and the output is the generated response. For example, the prompt "The user is feeling anxious. Please tell me about the project progress that was decided at the meeting last May." is sent to the generative artificial intelligence model. The generative artificial intelligence model searches the database for relevant information and generates an appropriate response.

[0514] Step 8:

[0515] The server provides the user with a generated response. The input is the generated response, and the output is the response displayed on the user's terminal. For example, it might provide a response such as, "Please rest assured. At the meeting in May of last year, the following procedure was decided: Task A will be handled by B, and Task C will be handled by D."

[0516] This series of steps enables the system to efficiently retrieve and analyze past email information and generate and provide appropriate responses tailored to the user's emotional state.

[0517] (Application Example 2)

[0518] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0519] Conventional email analysis systems analyze text data from emails and provide answers to user queries. However, they cannot consider the user's emotional state, making it difficult to provide interactions optimized for the user's feelings. Furthermore, if a user is experiencing emotional stress, inappropriate responses may lead to decreased satisfaction and trust. Therefore, there is a need for a system that analyzes the user's emotional state and generates responses that reflect it.

[0520] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0521] In this invention, the server includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing emotions, means for generating answers, and means for providing answers. This makes it possible to generate and provide the optimal answer according to the user's emotional state.

[0522] "Electronic message retrieval means" refers to a means of retrieving a specific message using the application programming interface of an electronic message service provider.

[0523] "Data analysis means" refers to a means of extracting and analyzing text data from acquired electronic messages.

[0524] "Data storage means" refers to means for storing the analyzed text data in a database.

[0525] A "query receiving method" is a means of receiving inquiries (queries) from users.

[0526] An "emotional analysis tool" is a means of analyzing a user's emotional state and providing the results of that analysis.

[0527] A "response generation method" is a means of retrieving data from a database based on a received query and generating a response using generative artificial intelligence.

[0528] "Answer provision means" refers to the means of providing the generated answers to users.

[0529] "Generative artificial intelligence" is an artificial intelligence technology that generates natural language responses based on user queries.

[0530] The present invention is a system that includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing sentiment, means for generating answers, and means for providing answers, thereby providing the optimal answer to the user's query according to their emotional state.

[0531] This system is configured as follows:

[0532] ---

[0533] The server obtains Google authentication credentials and configures itself to operate the Gmail API. It uses an electronic message retrieval method to retrieve emails related to mailing lists and specific labels. This retrieved text data is then analyzed by a data analysis tool, converted into text information, and stored in a database.

[0534] The terminal provides a user interface for users to input queries to the system. These queries are sent to the server by a query receiving mechanism. The server analyzes the received queries using an emotion analysis mechanism to evaluate the user's emotional state. Specifically, it reads the emotional state from the context of the query and the user's expressions, detecting states such as "excited" or "anxious."

[0535] Based on the sentiment analysis results, the server uses a response generation mechanism to send a query to a generative AI model (e.g., GPT-3) and generates a response adapted to the emotional state. In this response generation process, the content of the response is adjusted to accurately provide the necessary information while taking the user's emotions into consideration.

[0536] On the device, the user receives the generated response. Because the response is displayed through the response delivery method, the user can receive a response that takes their emotional state into consideration.

[0537] Hardware and software to be used

[0538] Hardware: Servers (cloud or on-premises), user devices (smartphones, head-mounted displays, etc.)

[0539] Software: Gmail API, SQLite, TensorFlow, Generative AI models (e.g., OpenAI's GPT-3)

[0540] Specific example

[0541] For example, if a user enters the query "Tell me about the latest promotions," the sentiment analysis tool will determine that the user is "interested." Based on this result, a generative AI model will generate a response containing more engaging content, such as "Would you like to see our latest promotions? Certain items are currently 20% off." Finally, this response will be displayed on the device and provided to the user.

[0542] Example of a prompt

[0543] Query: "Tell me about your latest promotions."

[0544] Sentiment analysis results: "Interest"

[0545] AI response: "Here's our latest promotion. Certain products are currently available at 20% off."

[0546] Thus, the present invention can provide a better user experience by providing information that is tailored to the user's emotional state.

[0547] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0548] Step 1:

[0549] The server retrieves electronic messages through the application programming interface of the electronic message service provider. The input consists of authentication information and the message label to be retrieved, while the output is a list of retrieved messages. The server receives the retrieved messages in batches.

[0550] Step 2:

[0551] The server analyzes received electronic messages using data analysis tools. The input is a list of acquired messages, and the output is the analyzed text data. The server extracts the text portion from the messages and performs grammatical analysis and keyword extraction.

[0552] Step 3:

[0553] The server stores the parsed text data in a database. The input is the parsed text data, and the output is the parsed data stored in the database. The server inserts the corresponding data into the appropriate table in the database.

[0554] Step 4:

[0555] The user enters a query through a terminal and sends it to the server via a query receiving mechanism. The input is the user's query, and the output is the query sent to the server. Query processing begins when the user enters a query.

[0556] Step 5:

[0557] The server analyzes the received query using sentiment analysis tools. The input is the user's query, and the output is an evaluation of the emotional state based on the query. The server analyzes the content and wording of the query to determine the user's emotions.

[0558] Step 6:

[0559] The server sends queries to a generating AI model based on sentiment analysis results, and generates the optimal response. The input is the sentiment analysis results and the query, and the output is the generated response. The generating AI model retrieves appropriate information from the database and generates a response in natural language.

[0560] Step 7:

[0561] The server sends the generated response to the terminal via the response delivery mechanism. The input is the generated response, and the output is the transmission of the response to the terminal. By the server sending the response to the terminal, the user can receive the appropriate response.

[0562] Step 8:

[0563] The user reviews the response generated on their device and then takes the next action. The input is the submitted response, and the output is the user's next action. Based on the response, the user makes the next inquiry or takes the next action.

[0564] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0565] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0566] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0567] [Third Embodiment]

[0568] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0569] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0570] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0571] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0572] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0573] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0574] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0575] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0576] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0577] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0578] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0579] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0580] This invention is a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers, thereby efficiently acquiring past email information and providing answers in natural language using generative artificial intelligence.

[0581] System Overview

[0582] The server obtains Google authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). The generated answer is sent to the user via an answer provision means.

[0583] Concrete Program Examples

[0584] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database.

[0585] Processing flow

[0586] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains details for each email and parses its text content. This text data is then stored in a database by the server.

[0587] When a user enters a query into the system, the query reception mechanism receives the query. Based on the received query, the server retrieves the corresponding information from the database and inputs it into the generative artificial intelligence. The generative AI generates the optimal answer based on the query, and the server provides the result to the user.

[0588] Specific example

[0589] For example, a user might input a query into the system saying, "Please tell me how the project will proceed as decided at the meeting last May." After receiving this query, the server queries a generative artificial intelligence system and retrieves a response based on relevant historical data. The response might look like this: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0590] In this way, this system allows users to easily retrieve important historical information and ensures business continuity even when personnel changes occur.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0594] Step 2:

[0595] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0596] Step 3:

[0597] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[0598] Step 4:

[0599] The server extracts the text portion of the email and analyzes the necessary information using data analysis tools. Here, text data is extracted from the email content, and unnecessary parts are removed.

[0600] Step 5:

[0601] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[0602] Step 6:

[0603] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[0604] Step 7:

[0605] The server receives a query entered by the user and sends it to the generative artificial intelligence. Based on the received query, the generative AI retrieves the necessary data from the database to generate an appropriate answer.

[0606] Step 8:

[0607] Generative artificial intelligence generates natural language responses to queries based on data retrieved from a database. The generated responses contain information appropriate to the content of the query.

[0608] Step 9:

[0609] The server receives the response from the generative artificial intelligence and provides it to the user. The user then checks the generated response through their device.

[0610] This processing flow allows users to easily and quickly obtain relevant information based on past email content, ensuring business continuity and efficiency even for new personnel.

[0611] (Example 1)

[0612] Next, we will describe Example 1. 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."

[0613] In recent years, email communication has increased, and a large amount of information is now exchanged via email in both business and personal activities. However, efficiently retrieving specific information from a vast amount of past emails and generating quick and appropriate responses based on that information is difficult. In particular, retrieving important information such as details of past meetings or projects when personnel changes occur requires a great deal of time and effort. There is a need to solve this problem by efficiently retrieving past email information and providing responses in natural language using generative artificial intelligence.

[0614] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0615] In this invention, the server includes authentication information acquisition means for acquiring authentication information, email acquisition means for acquiring emails from an email service provider's API, data analysis means for analyzing the acquired text data using natural language processing technology, data storage means for storing the data in a database, query reception means for receiving user queries, response generation means for sending prompt sentences to a generative artificial intelligence to generate answers, and response provision means for providing the generated answers to the user. This enables the user to efficiently acquire past email information and to receive answers in natural language using a generative AI model.

[0616] "Authentication information acquisition means" refers to a means of obtaining necessary authentication information by coordinating with the authentication server of an email service provider.

[0617] "Method for obtaining email" refers to the means of obtaining email from an email service provider's API using acquired authentication information.

[0618] "Data analysis means" refers to a method for analyzing the text data of acquired emails using natural language processing technology and extracting important information.

[0619] "Data storage means" refers to means for storing the analyzed text data in a database.

[0620] A "query receiving mechanism" is a means of receiving inquiries from users and processing their content.

[0621] The "response generation means" is a means for retrieving data from a database based on a query received by the query receiving means, and sending a prompt message to a generative artificial intelligence to generate a response.

[0622] "Answer provision means" refers to the means of providing the generated answers to the user.

[0623] "Generative artificial intelligence" is an artificial intelligence technology that generates the optimal answer based on user queries.

[0624] A "prompt" is a sentence input to a generative artificial intelligence system, and it is an instruction sentence that generates a response in response to a user's query.

[0625] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers. This allows for the efficient acquisition of past email information and the provision of answers in natural language using generative artificial intelligence.

[0626] The server plays a key role in operating this system. First, it obtains the necessary authentication information from the email service provider's authentication server using an authentication information acquisition method. At this time, it uses the OAuth2 protocol to obtain permission to access the user's email account. This allows access to the email service provider's APIs, such as the Gmail API.

[0627] Based on the acquired authentication information, the server uses an email retrieval method to retrieve emails associated with a specific label. The retrieved emails are then analyzed using natural language processing techniques with a data analysis method. Specifically, important keywords and phrases are extracted from the email subject and body.

[0628] This analyzed text data is stored in a database using a data storage system. The database has appropriate indexes, allowing for quick subsequent searches.

[0629] Users enter queries into the system via their terminal. For example, they might enter a query such as, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the server via a query reception mechanism.

[0630] The server searches and retrieves relevant information from the database based on the received query. Next, it sends a prompt message to the generative artificial intelligence (AI) using a response generation mechanism. The generative AI (e.g., generative AI model) generates the optimal response based on the provided data.

[0631] The generated responses are provided to the user through a response delivery system. Users can receive these responses via a web interface or a dedicated terminal.

[0632] For example, if a user enters the query "Please tell me how the project will proceed as decided at the meeting last May," the generative artificial intelligence will generate the following response based on relevant historical data: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0633] This system allows users to quickly retrieve important historical information and ensure business continuity.

[0634] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0635] Step 1:

[0636] Obtaining authentication information

[0637] The server interacts with the email service provider's authentication server to obtain authentication information. Specifically, the server uses the OAuth2 protocol to obtain permission to access the user's email account. The input is the authentication request the server receives, and the output is an authentication code and access token. This information enables subsequent email retrieval.

[0638] Specifically, the server sends a request to Google's authentication URL and receives an authentication code from Google. Using that authentication code, the server obtains an access token.

[0639] Step 2:

[0640] Retrieve emails

[0641] The server uses the acquired authentication information to retrieve emails associated with a specific label (e.g., "mailing list") from the email service provider's API. The input is the access token and the label of the email to be retrieved, and the output is a list of email IDs.

[0642] Specifically, the server sends a request to the Gmail API's "users.messages.list" endpoint to retrieve a list of email IDs. Based on this list, the server retrieves the details of each email from the "users.messages.get" endpoint.

[0643] Step 3:

[0644] Email analysis

[0645] The server analyzes the content of the received emails, using natural language processing techniques. The input is the email body and subject, and the output is the analyzed text data.

[0646] Specifically, the server tokenizes the email body and performs grammatical analysis. It extracts important keywords and phrases and tags them.

[0647] Step 4:

[0648] Storage in database

[0649] The server stores the parsed text data in the database. The input is the parsed text data, and the output is the status of successful data storage. This step ensures that the database is properly indexed, allowing for faster subsequent searches.

[0650] Specifically, the server generates a query to insert text data into an SQL database, executes the query on the database, and then inserts the data.

[0651] Step 5:

[0652] Acceptance of user queries

[0653] The user enters queries into the system using a terminal. The input is a natural language query entered by the user, and the output is the content of that query. For example, it accepts queries such as, "Please tell me how to proceed with the project that was decided at the meeting last May."

[0654] In terms of specific operations, the user enters a query into a web interface or a form on a dedicated terminal and presses the submit button. The query is then sent to the server.

[0655] Step 6:

[0656] Retrieving information from the database

[0657] The server searches and retrieves relevant information from the database based on user queries. The input is the user query, and the output is the corresponding database information.

[0658] Specifically, the server parses the user query and generates an appropriate SQL query. It then executes the generated SQL query against the database and retrieves the results.

[0659] Step 7:

[0660] Answer generation

[0661] The server inputs information retrieved from the database into a generative artificial intelligence (AI) system to generate the optimal response. The input consists of information retrieved from the database and prompt statements, while the output is the generated response. Specific prompt statements are sent to the generative AI system.

[0662] In terms of specific operations, the server sends a prompt message to the generating AI model. For example, it might send a prompt message such as, "Please tell me how to proceed with the project that was decided at the meeting last May," and the generating AI model will generate the best possible answer based on that query.

[0663] Step 8:

[0664] Providing answers to users

[0665] The server provides the user with the generated response. The input is the generated response, and the output is the response displayed to the user.

[0666] In terms of specific operations, the server sends the generated response to the frontend, which then displays the response on the user's screen. The user receives this response via a web interface or a dedicated terminal.

[0667] (Application Example 1)

[0668] Next, we will explain Application Example 1. In the following explanation, 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."

[0669] Conventional information retrieval systems made it difficult for users to efficiently search past emails and information. Furthermore, in factory settings, the lack of a way for employees to access necessary information without using their hands often led to decreased work efficiency. To address this challenge, a system is needed that allows employees to quickly retrieve information using wearable devices.

[0670] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0671] In this invention, the server includes email acquisition means, data analysis means, data storage means, query reception means, response generation means, and recognition display means. This makes it possible for a user to efficiently acquire past emails using a wearable device and display a response in natural language on the wearable device's display using generative artificial intelligence.

[0672] "Email acquisition means" refers to a system or device for acquiring emails using an email service provider's API.

[0673] "Data analysis means" refers to a system or device for analyzing text data obtained using email acquisition means and extracting necessary information.

[0674] "Data storage means" refers to a system or device for storing analyzed text data in a database.

[0675] A "query receiving means" is a system or device for receiving queries from users.

[0676] A "response generation means" is a system or device that retrieves data from a database based on queries received by a query receiving means, and sends it to a generative artificial intelligence to generate a response.

[0677] "Answer provision means" refers to a system or device for providing generated answers to users.

[0678] "Recognition display means" refers to a system or device for displaying the generated response on the display of a wearable device.

[0679] "Generative artificial intelligence" refers to artificial intelligence that uses natural language processing technology to generate the optimal answer to a user's query.

[0680] This invention can be implemented as an information retrieval system within a factory. This system allows employees to quickly access specific processes, past meeting records, project progress information, and other relevant data using wearable devices such as smart glasses.

[0681] Hardware and software to be used

[0682] Hardware: Servers, smart glasses, PCs

[0683] Software: Gmail API, SQLite3 database, transformers (GPT-2)

[0684] Program processing

[0685] The server uses the Gmail API through an email retrieval mechanism to obtain the necessary emails. This email retrieval mechanism has the function of centrally collecting emails related to specific labels (e.g., mailing lists) on the server. Next, a data analysis mechanism analyzes the content of the retrieved emails and extracts the necessary information. At this stage, the text portion of the emails is appropriately analyzed and stored in a database so that users can easily search for them.

[0686] When a query from a user is received by the smart glasses, the server's query receiving mechanism receives it and retrieves the corresponding data from the database based on that query. Next, the answer generation mechanism uses generative artificial intelligence (GPT-2) to generate an appropriate answer. This generated answer is displayed on the smart glasses' screen via the server, making it immediately available for the user to review.

[0687] Specific example

[0688] For example, a factory worker wearing smart glasses might ask, "What is the progress of Project X?" This query is processed by a server, which uses generative artificial intelligence to analyze past meeting records and progress reports to generate an answer. The answer is displayed on the smart glasses' screen as follows: "Project X is currently 50% complete, and the next step is to complete Task Y."

[0689] Example of a prompt

[0690] Prompt: Please tell me the progress of Project X.

[0691] As described above, the system of the present invention allows factory workers to obtain necessary information in real time without using their hands, thereby significantly improving work efficiency.

[0692] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0693] Step 1:

[0694] The server uses the Gmail API to retrieve emails associated with a specific label (mailing list). In this processing step, the server authenticates with the Gmail service and uses the label as a filter to retrieve all relevant emails. The input is Gmail credentials and a specific label, and the output is a list of emails. Specifically, it uses an API request to obtain a list of email IDs, and then retrieves detailed information for each email.

[0695] Step 2:

[0696] The server analyzes the acquired emails using data analysis tools. This includes a process of extracting the text content of the emails. The input is the text information of the emails acquired in step 1, and the output is the analyzed text data. Specifically, a text analysis algorithm is applied to extract the text portion of the emails, and the necessary information is extracted and converted into a format for storage in the database.

[0697] Step 3:

[0698] The server stores the parsed text data in a database. The input is the text data generated in step 2, and the output is the structured data stored in the database. Specifically, it performs insert operations into the database and sets up necessary indexes to support efficient query searches.

[0699] Step 4:

[0700] The user enters queries through smart glasses. The input is the query made by the user using voice or an input device, and the output is the query data sent to the server. Specifically, the smart glasses' microphone or input device is used to collect queries and send them to the server.

[0701] Step 5:

[0702] The server retrieves relevant data from the database based on queries received by the query reception mechanism. The input is query data, and the output is related text data. Specifically, it searches the database based on the query and extracts the corresponding data.

[0703] Step 6:

[0704] The server uses generative artificial intelligence as a means of generating answers, and generates responses to user queries based on acquired data. The input consists of text data and the query content, and the output is a generated natural language response. Specifically, the operation includes a process of inputting the query and data into a generative AI model such as GPT-2 and generating the optimal response.

[0705] Step 7:

[0706] The server sends the generated response to the smart glasses and displays it on the screen. The input is the generated response, and the output is the response displayed on the smart glasses' screen. Specifically, the process involves converting the text data into the smart glasses' display format and displaying it to the user at the appropriate time.

[0707] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0708] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers, and further incorporates an emotion engine that recognizes the user's emotions. This system makes it possible to efficiently acquire past email information, provide answers in natural language using generative artificial intelligence, and generate optimal answers according to the user's emotional state.

[0709] System Overview

[0710] The server obtains Google authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). At this time, an emotion engine evaluates the user's emotional state from the query and response, and the answer generation means generates an answer that is appropriate to that emotional state. The generated answer is sent to the user via an answer provision means.

[0711] Concrete Program Examples

[0712] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (e.g., mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database. The sentiment engine analyzes the user's emotional state from the user's input queries and responses from the system, and provides the analysis results to the response generation method.

[0713] Processing flow

[0714] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains detailed information about each email and parses its text content. This text data is then stored in a database by the server.

[0715] When a user enters a query into the system, a query reception mechanism receives the query. The server analyzes the received query using an emotion engine and evaluates the user's emotional state. It then sends the query to a generative artificial intelligence (AI). The generative AI retrieves corresponding information from the database based on the received query and generates the optimal answer while taking the user's emotions into consideration.

[0716] Specific example

[0717] For example, if a user enters a query into the system such as, "Please tell me how the project will proceed as decided at the meeting last May," the emotion engine will analyze the user's emotional state after receiving the query. If the system determines that the user is feeling anxious, the generative artificial intelligence will use that information to generate a response that takes the user's emotions into consideration, such as, "Please rest assured. The following progress plan was decided at the meeting last May. Task A will be handled by person B, and Task C will be handled by person D."

[0718] In this way, the system can provide information adapted to the user's emotional state, and along with retrieving past email information, it realizes interactions that enhance the user's sense of security and satisfaction.

[0719] The following describes the processing flow.

[0720] Step 1:

[0721] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0722] Step 2:

[0723] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0724] Step 3:

[0725] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[0726] Step 4:

[0727] The server extracts the text portion of the email and uses data analysis tools to analyze the necessary information. Here, text data is extracted from the email content, and unnecessary parts are removed.

[0728] Step 5:

[0729] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[0730] Step 6:

[0731] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[0732] Step 7:

[0733] The terminal sends the query entered by the user to the server.

[0734] Step 8:

[0735] The server receives the query and the emotion engine analyzes the user's emotional state. The emotion engine analyzes the query content and input method (such as keystroke speed and timing) to determine the user's emotional state.

[0736] Step 9:

[0737] The server sends the query to the generative artificial intelligence system along with the analysis results of the emotion engine.

[0738] Step 10:

[0739] The generative artificial intelligence retrieves corresponding information from the database based on the query and the results of the emotion engine's analysis, and generates a response that takes the user's emotional state into consideration. For example, if the user is feeling anxious, the response's tone will be adjusted to be gentler.

[0740] Step 11:

[0741] The server receives the response from the generative artificial intelligence and provides that response to the user. The response is displayed through the terminal.

[0742] Step 12:

[0743] The user reviews the response generated through their device and re-enters the query if necessary.

[0744] This processing flow allows users to easily and quickly obtain relevant information based on past email content, and also enables interaction tailored to the user's emotional state. This enhances business continuity and efficiency while improving user satisfaction and peace of mind.

[0745] (Example 2)

[0746] Next, we will describe Example 2. 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."

[0747] Traditional email management systems have struggled to efficiently retrieve and analyze past email information. Furthermore, few systems utilize generative artificial intelligence to provide appropriate responses to user queries, and they particularly lack mechanisms for generating responses that consider the user's emotional state. This makes it difficult to achieve interactions that enhance user satisfaction.

[0748] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0749] In this invention, the server includes an email acquisition means, a data analysis means for analyzing text data acquired using the email acquisition means, a data storage means for storing the analyzed text data in a database, a query receiving means for receiving queries from users, an answer generation means for acquiring data from the database based on queries received by the query receiving means and sending it to a generative artificial intelligence model to generate an answer, an emotion analysis means for analyzing the user's emotional state and providing the analysis results to the answer generation means, and an answer provision means for providing the generated answer to the user. This makes it possible to efficiently acquire and analyze past email information and generate and provide answers that correspond to the user's emotional state.

[0750] "Method of obtaining email" refers to a method of obtaining email using an API of an email service provider.

[0751] "Data analysis means" refers to methods for analyzing the text data of acquired emails and extracting necessary information.

[0752] "Data storage means" refers to the means of storing the analyzed text data in a database.

[0753] A "query receiving mechanism" is a means of receiving queries from users.

[0754] The "response generation means" is a means of retrieving data from a database based on a query received by the query receiving means, and sending it to a generative artificial intelligence model to generate a response.

[0755] "Emotional analysis means" refers to a method for analyzing a user's emotional state from user queries and system responses.

[0756] "Answer provision means" refers to the means of providing the generated answer to the user.

[0757] A "generative artificial intelligence model" is an artificial intelligence technology that retrieves necessary information from a database based on a received query and generates an appropriate response.

[0758] This invention is a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating responses, means for analyzing sentiment, and means for providing responses. The following hardware and software are used to implement this system.

[0759] Hardware to use

[0760] Server machine: Cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[0761] Software to use

[0762] Email acquisition methods: Google OAuth authentication and Gmail API

[0763] Data analysis method: Text analysis library (e.g., BeautifulSoup)

[0764] Data storage method: Database (e.g., PostgreSQL, MySQL)

[0765] Generative artificial intelligence models: Natural language processing models (e.g., OpenAI GPT-3)

[0766] Sentiment analysis method: Sentiment Analysis API (e.g. Sentiment Analysis API)

[0767] Program processing

[0768] First, the server obtains Google's OAuth credentials and uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The retrieved emails are passed to a data analysis tool, converted into text data, and then stored in a database. For example, the server sends an authentication request to the user's Google account and obtains an access token.

[0769] Next, the user uses a terminal to enter a query into the system. For example, they might enter, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the query reception mechanism and sent by the server to the sentiment analysis mechanism. The sentiment analysis mechanism analyzes the user's emotional state from the query and stores the results. For example, if it is determined that the user is experiencing anxiety, the results are used in the next process.

[0770] Based on the sentiment analysis results, the server sends queries and sentiment information to a generative artificial intelligence model. For example, it might send a prompt to the generative AI model saying, "The user is feeling anxious. Please tell me about the project's progress as decided at the meeting in May of last year." The generative AI model searches the database for relevant information and generates an appropriate response. The generated response is then provided to the user through a response delivery system. For example, a response that reassures the user might be provided in the form of, "Please rest assured. The following progress plan was decided at the meeting in May of last year. Task A will be handled by B, and Task C will be handled by D."

[0771] This system efficiently acquires and analyzes past email information, and generates and provides optimal responses tailored to the user's emotional state, thereby achieving interactions that enhance user satisfaction.

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] The server obtains authentication information using Google OAuth authentication. The input is the user's Google account information, and the output is a token that grants access to Google. The server sends an authentication request to the user's Google account and obtains an authentication code. Next, it uses this authentication code to obtain an access token.

[0775] Step 2:

[0776] The server uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The input is an access token and label information, and the output is a list of emails. The server temporarily stores the IDs and contents of the retrieved emails as a list, preparing for the next processing step.

[0777] Step 3:

[0778] The server converts the retrieved email content into text data and extracts the necessary information. The input is an email list, and the output is text data and metadata (sender, subject, date and time, etc.). The server uses a text analysis library (e.g., BeautifulSoup) to convert the email body into text format and saves it as dictionary data along with the metadata.

[0779] Step 4:

[0780] The server stores the parsed text data in a database (e.g., PostgreSQL, MySQL). The input is text data and metadata, and the output is the database containing this data. The server inserts this data into the corresponding tables in the database.

[0781] Step 5:

[0782] The user enters a query into the system using a terminal. The input is a query requesting specific information, and the output is query data stored in the query reception device. For example, the user might enter, "Please tell me how to proceed with the project that was decided at the meeting in May of last year."

[0783] Step 6:

[0784] The server sends a query to a sentiment analysis system, which then analyzes the user's emotional state. The input is the query data, and the output is the sentiment analysis result. The sentiment analysis system uses natural language processing techniques (e.g., Sentiment Analysis API) to evaluate the user's emotional state from the query text. For example, it might analyze that the user is in an anxious state.

[0785] Step 7:

[0786] The server sends queries and sentiment information to a generative artificial intelligence model based on the sentiment analysis results. The input is query data and sentiment analysis results, and the output is the generated response. For example, the prompt "The user is feeling anxious. Please tell me about the project progress that was decided at the meeting last May." is sent to the generative artificial intelligence model. The generative artificial intelligence model searches the database for relevant information and generates an appropriate response.

[0787] Step 8:

[0788] The server provides the user with a generated response. The input is the generated response, and the output is the response displayed on the user's terminal. For example, it might provide a response such as, "Please rest assured. At the meeting in May of last year, the following procedure was decided: Task A will be handled by B, and Task C will be handled by D."

[0789] This series of steps enables the system to efficiently retrieve and analyze past email information and generate and provide appropriate responses tailored to the user's emotional state.

[0790] (Application Example 2)

[0791] Next, we will explain application example 2. In the following explanation, 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."

[0792] Conventional email analysis systems analyze text data from emails and provide answers to user queries. However, they cannot consider the user's emotional state, making it difficult to provide interactions optimized for the user's feelings. Furthermore, if a user is experiencing emotional stress, inappropriate responses may lead to decreased satisfaction and trust. Therefore, there is a need for a system that analyzes the user's emotional state and generates responses that reflect it.

[0793] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0794] In this invention, the server includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing emotions, means for generating answers, and means for providing answers. This makes it possible to generate and provide the optimal answer according to the user's emotional state.

[0795] "Electronic message retrieval means" refers to a means of retrieving a specific message using the application programming interface of an electronic message service provider.

[0796] "Data analysis means" refers to a means of extracting and analyzing text data from acquired electronic messages.

[0797] "Data storage means" refers to means for storing the analyzed text data in a database.

[0798] A "query receiving method" is a means of receiving inquiries (queries) from users.

[0799] An "emotional analysis tool" is a means of analyzing a user's emotional state and providing the results of that analysis.

[0800] A "response generation method" is a means of retrieving data from a database based on a received query and generating a response using generative artificial intelligence.

[0801] "Answer provision means" refers to the means of providing the generated answers to users.

[0802] "Generative artificial intelligence" is an artificial intelligence technology that generates natural language responses based on user queries.

[0803] The present invention is a system that includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing sentiment, means for generating answers, and means for providing answers, thereby providing the optimal answer to the user's query according to their emotional state.

[0804] This system is configured as follows:

[0805] ---

[0806] The server obtains Google authentication credentials and configures itself to operate the Gmail API. It uses an electronic message retrieval method to retrieve emails related to mailing lists and specific labels. This retrieved text data is then analyzed by a data analysis tool, converted into text information, and stored in a database.

[0807] The terminal provides a user interface for users to input queries to the system. These queries are sent to the server by a query receiving mechanism. The server analyzes the received queries using an emotion analysis mechanism to evaluate the user's emotional state. Specifically, it reads the emotional state from the context of the query and the user's expressions, detecting states such as "excited" or "anxious."

[0808] Based on the sentiment analysis results, the server uses a response generation mechanism to send a query to a generative AI model (e.g., GPT-3) and generates a response adapted to the emotional state. In this response generation process, the content of the response is adjusted to accurately provide the necessary information while taking the user's emotions into consideration.

[0809] On the device, the user receives the generated response. Because the response is displayed through the response delivery method, the user can receive a response that takes their emotional state into consideration.

[0810] Hardware and software to be used

[0811] Hardware: Servers (cloud or on-premises), user devices (smartphones, head-mounted displays, etc.)

[0812] Software: Gmail API, SQLite, TensorFlow, Generative AI models (e.g., OpenAI's GPT-3)

[0813] Specific example

[0814] For example, if a user enters the query "Tell me about the latest promotions," the sentiment analysis tool will determine that the user is "interested." Based on this result, a generative AI model will generate a response containing more engaging content, such as "Would you like to see our latest promotions? Certain items are currently 20% off." Finally, this response will be displayed on the device and provided to the user.

[0815] Example of a prompt

[0816] Query: "Tell me about your latest promotions."

[0817] Sentiment analysis results: "Interest"

[0818] AI response: "Here's our latest promotion. Certain products are currently available at 20% off."

[0819] Thus, the present invention can provide a better user experience by providing information that is tailored to the user's emotional state.

[0820] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0821] Step 1:

[0822] The server retrieves electronic messages through the application programming interface of the electronic message service provider. The input consists of authentication information and the message label to be retrieved, while the output is a list of retrieved messages. The server receives the retrieved messages in batches.

[0823] Step 2:

[0824] The server analyzes received electronic messages using data analysis tools. The input is a list of acquired messages, and the output is the analyzed text data. The server extracts the text portion from the messages and performs grammatical analysis and keyword extraction.

[0825] Step 3:

[0826] The server stores the parsed text data in a database. The input is the parsed text data, and the output is the parsed data stored in the database. The server inserts the corresponding data into the appropriate table in the database.

[0827] Step 4:

[0828] The user enters a query through a terminal and sends it to the server via a query receiving mechanism. The input is the user's query, and the output is the query sent to the server. Query processing begins when the user enters a query.

[0829] Step 5:

[0830] The server analyzes the received query using sentiment analysis tools. The input is the user's query, and the output is an evaluation of the emotional state based on the query. The server analyzes the content and wording of the query to determine the user's emotions.

[0831] Step 6:

[0832] The server sends queries to a generating AI model based on sentiment analysis results, and generates the optimal response. The input is the sentiment analysis results and the query, and the output is the generated response. The generating AI model retrieves appropriate information from the database and generates a response in natural language.

[0833] Step 7:

[0834] The server sends the generated response to the terminal via the response delivery mechanism. The input is the generated response, and the output is the transmission of the response to the terminal. By the server sending the response to the terminal, the user can receive the appropriate response.

[0835] Step 8:

[0836] The user reviews the response generated on their device and then takes the next action. The input is the submitted response, and the output is the user's next action. Based on the response, the user makes the next inquiry or takes the next action.

[0837] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0838] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0839] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0840] [Fourth Embodiment]

[0841] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0842] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0843] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0844] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0845] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0846] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0847] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0848] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0849] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0850] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0851] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0852] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0853] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0854] This invention is a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers, thereby efficiently acquiring past email information and providing answers in natural language using generative artificial intelligence.

[0855] System Overview

[0856] The server obtains Google authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). The generated answer is sent to the user via an answer provision means.

[0857] Concrete Program Examples

[0858] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database.

[0859] Processing flow

[0860] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains details for each email and parses its text content. This text data is then stored in a database by the server.

[0861] When a user enters a query into the system, the query reception mechanism receives the query. Based on the received query, the server retrieves the corresponding information from the database and inputs it into the generative artificial intelligence. The generative AI generates the optimal answer based on the query, and the server provides the result to the user.

[0862] Specific example

[0863] For example, a user might input a query into the system saying, "Please tell me how the project will proceed as decided at the meeting last May." After receiving this query, the server queries a generative artificial intelligence system and retrieves a response based on relevant historical data. The response might look like this: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0864] In this way, this system allows users to easily retrieve important historical information and ensures business continuity even when personnel changes occur.

[0865] The following describes the processing flow.

[0866] Step 1:

[0867] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0868] Step 2:

[0869] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0870] Step 3:

[0871] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[0872] Step 4:

[0873] The server extracts the text portion of the email and analyzes the necessary information using data analysis tools. Here, text data is extracted from the email content, and unnecessary parts are removed.

[0874] Step 5:

[0875] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[0876] Step 6:

[0877] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[0878] Step 7:

[0879] The server receives a query entered by the user and sends it to the generative artificial intelligence. Based on the received query, the generative AI retrieves the necessary data from the database to generate an appropriate answer.

[0880] Step 8:

[0881] Generative artificial intelligence generates natural language responses to queries based on data retrieved from a database. The generated responses contain information appropriate to the content of the query.

[0882] Step 9:

[0883] The server receives the response from the generative artificial intelligence and provides it to the user. The user then checks the generated response through their device.

[0884] This processing flow allows users to easily and quickly obtain relevant information based on past email content, ensuring business continuity and efficiency even for new personnel.

[0885] (Example 1)

[0886] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0887] In recent years, email communication has increased, and a large amount of information is now exchanged via email in both business and personal activities. However, efficiently retrieving specific information from a vast amount of past emails and generating quick and appropriate responses based on that information is difficult. In particular, retrieving important information such as details of past meetings or projects when personnel changes occur requires a great deal of time and effort. There is a need to solve this problem by efficiently retrieving past email information and providing responses in natural language using generative artificial intelligence.

[0888] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0889] In this invention, the server includes authentication information acquisition means for acquiring authentication information, email acquisition means for acquiring emails from an email service provider's API, data analysis means for analyzing the acquired text data using natural language processing technology, data storage means for storing the data in a database, query reception means for receiving user queries, response generation means for sending prompt sentences to a generative artificial intelligence to generate answers, and response provision means for providing the generated answers to the user. This enables the user to efficiently acquire past email information and to receive answers in natural language using a generative AI model.

[0890] "Authentication information acquisition means" refers to a means of obtaining necessary authentication information by coordinating with the authentication server of an email service provider.

[0891] "Method for obtaining email" refers to the means of obtaining email from an email service provider's API using acquired authentication information.

[0892] "Data analysis means" refers to a method for analyzing the text data of acquired emails using natural language processing technology and extracting important information.

[0893] "Data storage means" refers to means for storing the analyzed text data in a database.

[0894] A "query receiving mechanism" is a means of receiving inquiries from users and processing their content.

[0895] The "response generation means" is a means for retrieving data from a database based on a query received by the query receiving means, and sending a prompt message to a generative artificial intelligence to generate a response.

[0896] "Answer provision means" refers to the means of providing the generated answers to the user.

[0897] "Generative artificial intelligence" is an artificial intelligence technology that generates the optimal answer based on user queries.

[0898] A "prompt" is a sentence input to a generative artificial intelligence system, and it is an instruction sentence that generates a response in response to a user's query.

[0899] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers. This allows for the efficient acquisition of past email information and the provision of answers in natural language using generative artificial intelligence.

[0900] The server plays a key role in operating this system. First, it obtains the necessary authentication information from the email service provider's authentication server using an authentication information acquisition method. At this time, it uses the OAuth2 protocol to obtain permission to access the user's email account. This allows access to the email service provider's APIs, such as the Gmail API.

[0901] Based on the acquired authentication information, the server uses an email retrieval method to retrieve emails associated with a specific label. The retrieved emails are then analyzed using natural language processing techniques with a data analysis method. Specifically, important keywords and phrases are extracted from the email subject and body.

[0902] This analyzed text data is stored in a database using a data storage system. The database has appropriate indexes, allowing for quick subsequent searches.

[0903] Users enter queries into the system via their terminal. For example, they might enter a query such as, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the server via a query reception mechanism.

[0904] The server searches and retrieves relevant information from the database based on the received query. Next, it sends a prompt message to the generative artificial intelligence (AI) using a response generation mechanism. The generative AI (e.g., generative AI model) generates the optimal response based on the provided data.

[0905] The generated responses are provided to the user through a response delivery system. Users can receive these responses via a web interface or a dedicated terminal.

[0906] For example, if a user enters the query "Please tell me how the project will proceed as decided at the meeting last May," the generative artificial intelligence will generate the following response based on relevant historical data: "The following progress plan was decided last May. Task A will be handled by person B, and Task C will be handled by person D."

[0907] This system allows users to quickly retrieve important historical information and ensure business continuity.

[0908] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0909] Step 1:

[0910] Obtaining authentication information

[0911] The server interacts with the email service provider's authentication server to obtain authentication information. Specifically, the server uses the OAuth2 protocol to obtain permission to access the user's email account. The input is the authentication request the server receives, and the output is an authentication code and access token. This information enables subsequent email retrieval.

[0912] Specifically, the server sends a request to Google's authentication URL and receives an authentication code from Google. Using that authentication code, the server obtains an access token.

[0913] Step 2:

[0914] Retrieve emails

[0915] The server uses the acquired authentication information to retrieve emails associated with a specific label (e.g., "mailing list") from the email service provider's API. The input is the access token and the label of the email to be retrieved, and the output is a list of email IDs.

[0916] Specifically, the server sends a request to the Gmail API's "users.messages.list" endpoint to retrieve a list of email IDs. Based on this list, the server retrieves the details of each email from the "users.messages.get" endpoint.

[0917] Step 3:

[0918] Email analysis

[0919] The server analyzes the content of the received emails, using natural language processing techniques. The input is the email body and subject, and the output is the analyzed text data.

[0920] Specifically, the server tokenizes the email body and performs grammatical analysis. It extracts important keywords and phrases and tags them.

[0921] Step 4:

[0922] Storage in database

[0923] The server stores the parsed text data in the database. The input is the parsed text data, and the output is the status of successful data storage. This step ensures that the database is properly indexed, allowing for faster subsequent searches.

[0924] Specifically, the server generates a query to insert text data into an SQL database, executes the query on the database, and then inserts the data.

[0925] Step 5:

[0926] Acceptance of user queries

[0927] The user enters queries into the system using a terminal. The input is a natural language query entered by the user, and the output is the content of that query. For example, it accepts queries such as, "Please tell me how to proceed with the project that was decided at the meeting last May."

[0928] In terms of specific operations, the user enters a query into a web interface or a form on a dedicated terminal and presses the submit button. The query is then sent to the server.

[0929] Step 6:

[0930] Retrieving information from the database

[0931] The server searches and retrieves relevant information from the database based on user queries. The input is the user query, and the output is the corresponding database information.

[0932] Specifically, the server parses the user query and generates an appropriate SQL query. It then executes the generated SQL query against the database and retrieves the results.

[0933] Step 7:

[0934] Answer generation

[0935] The server inputs information retrieved from the database into a generative artificial intelligence (AI) system to generate the optimal response. The input consists of information retrieved from the database and prompt statements, while the output is the generated response. Specific prompt statements are sent to the generative AI system.

[0936] In terms of specific operations, the server sends a prompt message to the generating AI model. For example, it might send a prompt message such as, "Please tell me how to proceed with the project that was decided at the meeting last May," and the generating AI model will generate the best possible answer based on that query.

[0937] Step 8:

[0938] Providing answers to users

[0939] The server provides the user with the generated response. The input is the generated response, and the output is the response displayed to the user.

[0940] In terms of specific operations, the server sends the generated response to the frontend, which then displays the response on the user's screen. The user receives this response via a web interface or a dedicated terminal.

[0941] (Application Example 1)

[0942] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0943] Conventional information retrieval systems made it difficult for users to efficiently search past emails and information. Furthermore, in factory settings, the lack of a way for employees to access necessary information without using their hands often led to decreased work efficiency. To address this challenge, a system is needed that allows employees to quickly retrieve information using wearable devices.

[0944] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0945] In this invention, the server includes email acquisition means, data analysis means, data storage means, query reception means, response generation means, and recognition display means. This makes it possible for a user to efficiently acquire past emails using a wearable device and display a response in natural language on the wearable device's display using generative artificial intelligence.

[0946] "Email acquisition means" refers to a system or device for acquiring emails using an email service provider's API.

[0947] "Data analysis means" refers to a system or device for analyzing text data obtained using email acquisition means and extracting necessary information.

[0948] "Data storage means" refers to a system or device for storing analyzed text data in a database.

[0949] A "query receiving means" is a system or device for receiving queries from users.

[0950] A "response generation means" is a system or device that retrieves data from a database based on queries received by a query receiving means, and sends it to a generative artificial intelligence to generate a response.

[0951] "Answer provision means" refers to a system or device for providing generated answers to users.

[0952] "Recognition display means" refers to a system or device for displaying the generated response on the display of a wearable device.

[0953] "Generative artificial intelligence" refers to artificial intelligence that uses natural language processing technology to generate the optimal answer to a user's query.

[0954] This invention can be implemented as an information retrieval system within a factory. This system allows employees to quickly access specific processes, past meeting records, project progress information, and other relevant data using wearable devices such as smart glasses.

[0955] Hardware and software to be used

[0956] Hardware: Servers, smart glasses, PCs

[0957] Software: Gmail API, SQLite3 database, transformers (GPT-2)

[0958] Program processing

[0959] The server uses the Gmail API through an email retrieval mechanism to obtain the necessary emails. This email retrieval mechanism has the function of centrally collecting emails related to specific labels (e.g., mailing lists) on the server. Next, a data analysis mechanism analyzes the content of the retrieved emails and extracts the necessary information. At this stage, the text portion of the emails is appropriately analyzed and stored in a database so that users can easily search for them.

[0960] When a query from a user is received by the smart glasses, the server's query receiving mechanism receives it and retrieves the corresponding data from the database based on that query. Next, the answer generation mechanism uses generative artificial intelligence (GPT-2) to generate an appropriate answer. This generated answer is displayed on the smart glasses' screen via the server, making it immediately available for the user to review.

[0961] Specific example

[0962] For example, a factory worker wearing smart glasses might ask, "What is the progress of Project X?" This query is processed by a server, which uses generative artificial intelligence to analyze past meeting records and progress reports to generate an answer. The answer is displayed on the smart glasses' screen as follows: "Project X is currently 50% complete, and the next step is to complete Task Y."

[0963] Example of a prompt

[0964] Prompt: Please tell me the progress of Project X.

[0965] As described above, the system of the present invention allows factory workers to obtain necessary information in real time without using their hands, thereby significantly improving work efficiency.

[0966] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0967] Step 1:

[0968] The server uses the Gmail API to retrieve emails associated with a specific label (mailing list). In this processing step, the server authenticates with the Gmail service and uses the label as a filter to retrieve all relevant emails. The input is Gmail credentials and a specific label, and the output is a list of emails. Specifically, it uses an API request to obtain a list of email IDs, and then retrieves detailed information for each email.

[0969] Step 2:

[0970] The server analyzes the acquired emails using data analysis tools. This includes a process of extracting the text content of the emails. The input is the text information of the emails acquired in step 1, and the output is the analyzed text data. Specifically, a text analysis algorithm is applied to extract the text portion of the emails, and the necessary information is extracted and converted into a format for storage in the database.

[0971] Step 3:

[0972] The server stores the parsed text data in a database. The input is the text data generated in step 2, and the output is the structured data stored in the database. Specifically, it performs insert operations into the database and sets up necessary indexes to support efficient query searches.

[0973] Step 4:

[0974] The user enters queries through smart glasses. The input is the query made by the user using voice or an input device, and the output is the query data sent to the server. Specifically, the smart glasses' microphone or input device is used to collect queries and send them to the server.

[0975] Step 5:

[0976] The server retrieves relevant data from the database based on queries received by the query reception mechanism. The input is query data, and the output is related text data. Specifically, it searches the database based on the query and extracts the corresponding data.

[0977] Step 6:

[0978] The server uses generative artificial intelligence as a means of generating answers, and generates responses to user queries based on acquired data. The input consists of text data and the query content, and the output is a generated natural language response. Specifically, the operation includes a process of inputting the query and data into a generative AI model such as GPT-2 and generating the optimal response.

[0979] Step 7:

[0980] The server sends the generated response to the smart glasses and displays it on the screen. The input is the generated response, and the output is the response displayed on the smart glasses' screen. Specifically, the process involves converting the text data into the smart glasses' display format and displaying it to the user at the appropriate time.

[0981] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0982] This invention relates to a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating answers, and means for providing answers, and further incorporates an emotion engine that recognizes the user's emotions. This system makes it possible to efficiently acquire past email information, provide answers in natural language using generative artificial intelligence, and generate optimal answers according to the user's emotional state.

[0983] System Overview

[0984] The server obtains Google authentication credentials and generates a service that operates the Gmail API. An email retrieval means retrieves emails from a mailing list, analyzes the information into text data using a data analysis means, and stores it in a database. When a user queries for specific information through a query reception means, an answer generation means retrieves the relevant data from the database and generates an answer using generative artificial intelligence (e.g., generative AI). At this time, an emotion engine evaluates the user's emotional state from the query and response, and the answer generation means generates an answer that is appropriate to that emotional state. The generated answer is sent to the user via an answer provision means.

[0985] Concrete Program Examples

[0986] As an implementation of the email retrieval method, the Gmail API is used to retrieve emails associated with a specific label (e.g., mailing list). The server retrieves these emails in bulk and analyzes the content of each email. The text data extracted by the data analysis method is stored in a database. The sentiment engine analyzes the user's emotional state from the user's input queries and responses from the system, and provides the analysis results to the response generation method.

[0987] Processing flow

[0988] First, the server retrieves emails from the mailing list using the Gmail API. Based on the retrieved email ID, the server obtains detailed information about each email and parses its text content. This text data is then stored in a database by the server.

[0989] When a user enters a query into the system, a query reception mechanism receives the query. The server analyzes the received query using an emotion engine and evaluates the user's emotional state. It then sends the query to a generative artificial intelligence (AI). The generative AI retrieves corresponding information from the database based on the received query and generates the optimal answer while taking the user's emotions into consideration.

[0990] Specific example

[0991] For example, if a user enters a query into the system such as, "Please tell me how the project will proceed as decided at the meeting last May," the emotion engine will analyze the user's emotional state after receiving the query. If the system determines that the user is feeling anxious, the generative artificial intelligence will use that information to generate a response that takes the user's emotions into consideration, such as, "Please rest assured. The following progress plan was decided at the meeting last May. Task A will be handled by person B, and Task C will be handled by person D."

[0992] In this way, the system can provide information adapted to the user's emotional state, and along with retrieving past email information, it realizes interactions that enhance the user's sense of security and satisfaction.

[0993] The following describes the processing flow.

[0994] Step 1:

[0995] The server obtains Google's authentication credentials and creates a service object for the Gmail API. This allows the server to access the Gmail API.

[0996] Step 2:

[0997] The server uses the Gmail API to retrieve a list of emails associated with a specific label (e.g., a mailing list). This retrieves a list of email IDs.

[0998] Step 3:

[0999] Based on the list of email IDs obtained by the server, detailed information for each email is retrieved. This detailed information includes the email body and its structure (text portion, attachments, etc.).

[1000] Step 4:

[1001] The server extracts the text portion of the email and uses data analysis tools to analyze the necessary information. Here, text data is extracted from the email content, and unnecessary parts are removed.

[1002] Step 5:

[1003] The server stores the parsed text data in a database. The data is properly indexed so that it can be searched later.

[1004] Step 6:

[1005] The user enters a query about specific information into the terminal via a query reception mechanism. The query is expressed in natural language.

[1006] Step 7:

[1007] The terminal sends the query entered by the user to the server.

[1008] Step 8:

[1009] The server receives the query and the emotion engine analyzes the user's emotional state. The emotion engine analyzes the query content and input method (such as keystroke speed and timing) to determine the user's emotional state.

[1010] Step 9:

[1011] The server sends the query to the generative artificial intelligence system along with the analysis results of the emotion engine.

[1012] Step 10:

[1013] The generative artificial intelligence retrieves corresponding information from the database based on the query and the results of the emotion engine's analysis, and generates a response that takes the user's emotional state into consideration. For example, if the user is feeling anxious, the response's tone will be adjusted to be gentler.

[1014] Step 11:

[1015] The server receives the response from the generative artificial intelligence and provides that response to the user. The response is displayed through the terminal.

[1016] Step 12:

[1017] The user reviews the response generated through their device and re-enters the query if necessary.

[1018] This processing flow allows users to easily and quickly obtain relevant information based on past email content, and also enables interaction tailored to the user's emotional state. This enhances business continuity and efficiency while improving user satisfaction and peace of mind.

[1019] (Example 2)

[1020] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1021] Traditional email management systems have struggled to efficiently retrieve and analyze past email information. Furthermore, few systems utilize generative artificial intelligence to provide appropriate responses to user queries, and they particularly lack mechanisms for generating responses that consider the user's emotional state. This makes it difficult to achieve interactions that enhance user satisfaction.

[1022] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1023] In this invention, the server includes an email acquisition means, a data analysis means for analyzing text data acquired using the email acquisition means, a data storage means for storing the analyzed text data in a database, a query receiving means for receiving queries from users, an answer generation means for acquiring data from the database based on queries received by the query receiving means and sending it to a generative artificial intelligence model to generate an answer, an emotion analysis means for analyzing the user's emotional state and providing the analysis results to the answer generation means, and an answer provision means for providing the generated answer to the user. This makes it possible to efficiently acquire and analyze past email information and generate and provide answers that correspond to the user's emotional state.

[1024] "Method of obtaining email" refers to a method of obtaining email using an API of an email service provider.

[1025] "Data analysis means" refers to methods for analyzing the text data of acquired emails and extracting necessary information.

[1026] "Data storage means" refers to the means of storing the analyzed text data in a database.

[1027] A "query receiving mechanism" is a means of receiving queries from users.

[1028] The "response generation means" is a means of retrieving data from a database based on a query received by the query receiving means, and sending it to a generative artificial intelligence model to generate a response.

[1029] "Emotional analysis means" refers to a method for analyzing a user's emotional state from user queries and system responses.

[1030] "Answer provision means" refers to the means of providing the generated answer to the user.

[1031] A "generative artificial intelligence model" is an artificial intelligence technology that retrieves necessary information from a database based on a received query and generates an appropriate response.

[1032] This invention is a system that includes means for acquiring emails, means for analyzing data, means for storing data, means for receiving queries, means for generating responses, means for analyzing sentiment, and means for providing responses. The following hardware and software are used to implement this system.

[1033] Hardware to use

[1034] Server machine: Cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[1035] Software to use

[1036] Email acquisition methods: Google OAuth authentication and Gmail API

[1037] Data analysis method: Text analysis library (e.g., BeautifulSoup)

[1038] Data storage method: Database (e.g., PostgreSQL, MySQL)

[1039] Generative artificial intelligence models: Natural language processing models (e.g., OpenAI GPT-3)

[1040] Sentiment analysis method: Sentiment Analysis API (e.g. Sentiment Analysis API)

[1041] Program processing

[1042] First, the server obtains Google's OAuth credentials and uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The retrieved emails are passed to a data analysis tool, converted into text data, and then stored in a database. For example, the server sends an authentication request to the user's Google account and obtains an access token.

[1043] Next, the user uses a terminal to enter a query into the system. For example, they might enter, "Please tell me how to proceed with the project decided at the meeting last May." This query is received by the query reception mechanism and sent by the server to the sentiment analysis mechanism. The sentiment analysis mechanism analyzes the user's emotional state from the query and stores the results. For example, if it is determined that the user is experiencing anxiety, the results are used in the next process.

[1044] Based on the sentiment analysis results, the server sends queries and sentiment information to a generative artificial intelligence model. For example, it might send a prompt to the generative AI model saying, "The user is feeling anxious. Please tell me about the project's progress as decided at the meeting in May of last year." The generative AI model searches the database for relevant information and generates an appropriate response. The generated response is then provided to the user through a response delivery system. For example, a response that reassures the user might be provided in the form of, "Please rest assured. The following progress plan was decided at the meeting in May of last year. Task A will be handled by B, and Task C will be handled by D."

[1045] This system efficiently acquires and analyzes past email information, and generates and provides optimal responses tailored to the user's emotional state, thereby achieving interactions that enhance user satisfaction.

[1046] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1047] Step 1:

[1048] The server obtains authentication information using Google OAuth authentication. The input is the user's Google account information, and the output is a token that grants access to Google. The server sends an authentication request to the user's Google account and obtains an authentication code. Next, it uses this authentication code to obtain an access token.

[1049] Step 2:

[1050] The server uses the Gmail API to retrieve emails associated with a specific label (e.g., "project-updates"). The input is an access token and label information, and the output is a list of emails. The server temporarily stores the IDs and contents of the retrieved emails as a list, preparing for the next processing step.

[1051] Step 3:

[1052] The server converts the retrieved email content into text data and extracts the necessary information. The input is an email list, and the output is text data and metadata (sender, subject, date and time, etc.). The server uses a text analysis library (e.g., BeautifulSoup) to convert the email body into text format and saves it as dictionary data along with the metadata.

[1053] Step 4:

[1054] The server stores the parsed text data in a database (e.g., PostgreSQL, MySQL). The input is text data and metadata, and the output is the database containing this data. The server inserts this data into the corresponding tables in the database.

[1055] Step 5:

[1056] The user enters a query into the system using a terminal. The input is a query requesting specific information, and the output is query data stored in the query reception device. For example, the user might enter, "Please tell me how to proceed with the project that was decided at the meeting in May of last year."

[1057] Step 6:

[1058] The server sends a query to a sentiment analysis system, which then analyzes the user's emotional state. The input is the query data, and the output is the sentiment analysis result. The sentiment analysis system uses natural language processing techniques (e.g., Sentiment Analysis API) to evaluate the user's emotional state from the query text. For example, it might analyze that the user is in an anxious state.

[1059] Step 7:

[1060] The server sends queries and sentiment information to a generative artificial intelligence model based on the sentiment analysis results. The input is query data and sentiment analysis results, and the output is the generated response. For example, the prompt "The user is feeling anxious. Please tell me about the project progress that was decided at the meeting last May." is sent to the generative artificial intelligence model. The generative artificial intelligence model searches the database for relevant information and generates an appropriate response.

[1061] Step 8:

[1062] The server provides the user with a generated response. The input is the generated response, and the output is the response displayed on the user's terminal. For example, it might provide a response such as, "Please rest assured. At the meeting in May of last year, the following procedure was decided: Task A will be handled by B, and Task C will be handled by D."

[1063] This series of steps enables the system to efficiently retrieve and analyze past email information and generate and provide appropriate responses tailored to the user's emotional state.

[1064] (Application Example 2)

[1065] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1066] Conventional email analysis systems analyze text data from emails and provide answers to user queries. However, they cannot consider the user's emotional state, making it difficult to provide interactions optimized for the user's feelings. Furthermore, if a user is experiencing emotional stress, inappropriate responses may lead to decreased satisfaction and trust. Therefore, there is a need for a system that analyzes the user's emotional state and generates responses that reflect it.

[1067] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1068] In this invention, the server includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing emotions, means for generating answers, and means for providing answers. This makes it possible to generate and provide the optimal answer according to the user's emotional state.

[1069] "Electronic message retrieval means" refers to a means of retrieving a specific message using the application programming interface of an electronic message service provider.

[1070] "Data analysis means" refers to a means of extracting and analyzing text data from acquired electronic messages.

[1071] "Data storage means" refers to means for storing the analyzed text data in a database.

[1072] A "query receiving method" is a means of receiving inquiries (queries) from users.

[1073] An "emotional analysis tool" is a means of analyzing a user's emotional state and providing the results of that analysis.

[1074] A "response generation method" is a means of retrieving data from a database based on a received query and generating a response using generative artificial intelligence.

[1075] "Answer provision means" refers to the means of providing the generated answers to users.

[1076] "Generative artificial intelligence" is an artificial intelligence technology that generates natural language responses based on user queries.

[1077] The present invention is a system that includes means for acquiring electronic messages, means for analyzing data, means for storing data, means for receiving queries, means for analyzing sentiment, means for generating answers, and means for providing answers, thereby providing the optimal answer to the user's query according to their emotional state.

[1078] This system is configured as follows:

[1079] ---

[1080] The server obtains Google authentication credentials and configures itself to operate the Gmail API. It uses an electronic message retrieval method to retrieve emails related to mailing lists and specific labels. This retrieved text data is then analyzed by a data analysis tool, converted into text information, and stored in a database.

[1081] The terminal provides a user interface for users to input queries to the system. These queries are sent to the server by a query receiving mechanism. The server analyzes the received queries using an emotion analysis mechanism to evaluate the user's emotional state. Specifically, it reads the emotional state from the context of the query and the user's expressions, detecting states such as "excited" or "anxious."

[1082] Based on the sentiment analysis results, the server uses a response generation mechanism to send a query to a generative AI model (e.g., GPT-3) and generates a response adapted to the emotional state. In this response generation process, the content of the response is adjusted to accurately provide the necessary information while taking the user's emotions into consideration.

[1083] On the device, the user receives the generated response. Because the response is displayed through the response delivery method, the user can receive a response that takes their emotional state into consideration.

[1084] Hardware and software to be used

[1085] Hardware: Servers (cloud or on-premises), user devices (smartphones, head-mounted displays, etc.)

[1086] Software: Gmail API, SQLite, TensorFlow, Generative AI models (e.g., OpenAI's GPT-3)

[1087] Specific example

[1088] For example, if a user enters the query "Tell me about the latest promotions," the sentiment analysis tool will determine that the user is "interested." Based on this result, a generative AI model will generate a response containing more engaging content, such as "Would you like to see our latest promotions? Certain items are currently 20% off." Finally, this response will be displayed on the device and provided to the user.

[1089] Example of a prompt

[1090] Query: "Tell me about your latest promotions."

[1091] Sentiment analysis results: "Interest"

[1092] AI response: "Here's our latest promotion. Certain products are currently available at 20% off."

[1093] Thus, the present invention can provide a better user experience by providing information that is tailored to the user's emotional state.

[1094] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1095] Step 1:

[1096] The server retrieves electronic messages through the application programming interface of the electronic message service provider. The input consists of authentication information and the message label to be retrieved, while the output is a list of retrieved messages. The server receives the retrieved messages in batches.

[1097] Step 2:

[1098] The server analyzes received electronic messages using data analysis tools. The input is a list of acquired messages, and the output is the analyzed text data. The server extracts the text portion from the messages and performs grammatical analysis and keyword extraction.

[1099] Step 3:

[1100] The server stores the parsed text data in a database. The input is the parsed text data, and the output is the parsed data stored in the database. The server inserts the corresponding data into the appropriate table in the database.

[1101] Step 4:

[1102] The user enters a query through a terminal and sends it to the server via a query receiving mechanism. The input is the user's query, and the output is the query sent to the server. Query processing begins when the user enters a query.

[1103] Step 5:

[1104] The server analyzes the received query using sentiment analysis tools. The input is the user's query, and the output is an evaluation of the emotional state based on the query. The server analyzes the content and wording of the query to determine the user's emotions.

[1105] Step 6:

[1106] The server sends queries to a generating AI model based on sentiment analysis results, and generates the optimal response. The input is the sentiment analysis results and the query, and the output is the generated response. The generating AI model retrieves appropriate information from the database and generates a response in natural language.

[1107] Step 7:

[1108] The server sends the generated response to the terminal via the response delivery mechanism. The input is the generated response, and the output is the transmission of the response to the terminal. By the server sending the response to the terminal, the user can receive the appropriate response.

[1109] Step 8:

[1110] The user reviews the response generated on their device and then takes the next action. The input is the submitted response, and the output is the user's next action. Based on the response, the user makes the next inquiry or takes the next action.

[1111] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1112] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1113] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1114] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1115] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1116] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1117] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1118] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1119] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1120] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1121] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1122] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1123] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1124] 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.

[1125] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1126] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1127] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1128] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1129] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1130] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1131] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1132] The following is further disclosed regarding the embodiments described above.

[1133] (Claim 1)

[1134] Methods for obtaining email addresses,

[1135] A data analysis means for analyzing text data obtained using the aforementioned email acquisition means,

[1136] A data storage means for storing the analyzed text data in a database,

[1137] A query receiving mechanism that accepts queries from users,

[1138] A response generation means that retrieves data from a database based on a query received by the query receiving means, and sends it to a generative artificial intelligence to generate a response,

[1139] A means for providing the generated response to the user,

[1140] A system that includes this.

[1141] (Claim 2)

[1142] The system according to claim 1, wherein the email acquisition means acquires emails using an API of an email service provider.

[1143] (Claim 3)

[1144] The system according to claim 1, wherein the data analysis means extracts and analyzes the text portion of an email.

[1145] "Example 1"

[1146] (Claim 1)

[1147] A means of obtaining authentication information,

[1148] An email retrieval means that retrieves emails from an email service provider's API using the aforementioned authentication information,

[1149] A data analysis means for analyzing text data obtained using the aforementioned email acquisition means,

[1150] A data storage means for storing the analyzed text data in a database,

[1151] A query receiving mechanism that accepts queries from users,

[1152] A response generation means that retrieves data from a database based on a query received by the query receiving means, and sends it to a generative artificial intelligence to generate a response,

[1153] A means for providing the generated response to the user,

[1154] A system that includes this.

[1155] (Claim 2)

[1156] The system according to claim 1, wherein the data analysis means analyzes email text data using natural language processing technology.

[1157] (Claim 3)

[1158] The system according to claim 1, wherein the response generation means generates a response by sending a prompt sentence to a generative artificial intelligence.

[1159] "Application Example 1"

[1160] (Claim 1)

[1161] Methods for obtaining email addresses,

[1162] A data analysis means for analyzing text data obtained using the aforementioned email acquisition means,

[1163] A data storage means for storing the analyzed text data in a database,

[1164] A query receiving mechanism that accepts queries from users,

[1165] A response generation means that retrieves data from a database based on a query received by the query receiving means, and sends it to a generative artificial intelligence to generate a response,

[1166] A means for providing the generated response to the user,

[1167] The generated response is displayed on the display of a wearable device, and

[1168] A system that includes this.

[1169] (Claim 2)

[1170] The system according to claim 1, wherein the email acquisition means acquires emails using an API of an email service provider.

[1171] (Claim 3)

[1172] The system according to claim 1, wherein the data analysis means extracts and analyzes the text portion of an email, and the analyzed text data is converted into a format suitable for a smart device.

[1173] "Example 2 of combining an emotion engine"

[1174] (Claim 1)

[1175] Methods for obtaining email addresses,

[1176] A data analysis means for analyzing text data obtained using the aforementioned email acquisition means,

[1177] A data storage means for storing the analyzed text data in a database,

[1178] A query receiving mechanism that accepts queries from users,

[1179] A response generation means that retrieves data from a database based on a query received by the query receiving means, and sends it to a generative artificial intelligence model to generate a response,

[1180] An emotion analysis means that analyzes the user's emotional state and provides the analysis results to the response generation means,

[1181] A means for providing the generated response to the user,

[1182] A system that includes this.

[1183] (Claim 2)

[1184] The system according to claim 1, wherein the email acquisition means acquires emails using an API of an email service provider.

[1185] (Claim 3)

[1186] The system according to claim 1, wherein the data analysis means extracts and analyzes the text portion of an email.

[1187] "Application example 2 when combining with an emotional engine"

[1188] (Claim 1)

[1189] Means of receiving electronic messages,

[1190] A data analysis means for analyzing text data acquired using the electronic message acquisition means,

[1191] A data storage means for storing the analyzed text data in a database,

[1192] A query receiving mechanism that accepts queries from users,

[1193] A response generation means that retrieves data from a database based on a query received by the query receiving means, and sends it to a generative artificial intelligence to generate a response,

[1194] A means for providing the generated response to the user,

[1195] An emotion analysis means analyzes the emotional state of the user, and based on the analysis results, the response generation means generates a response that is appropriate to the emotional state.

[1196] A system that includes this.

[1197] (Claim 2)

[1198] The system according to claim 1, wherein the electronic message acquisition means acquires messages using the application programming interface of an electronic message service provider.

[1199] (Claim 3)

[1200] The system according to claim 1, wherein the data analysis means extracts and analyzes the text portion of a message. [Explanation of Symbols]

[1201] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Methods for obtaining email addresses, A data analysis means for analyzing text data obtained using the aforementioned email acquisition means, A data storage means for storing the analyzed text data in a database, A query receiving mechanism that accepts queries from users, A response generation means that retrieves data from a database based on a query received by the query receiving means, and sends it to a generative artificial intelligence to generate a response, A means for providing the generated response to the user, A system that includes this.

2. The system according to claim 1, wherein the email acquisition means acquires emails using an API of an email service provider.

3. The system according to claim 1, wherein the data analysis means extracts and analyzes the text portion of an email.

Images