system

Abstract

Provide a system. 【Solution means】 Means for receiving a data request and analyzing the required data type and format; Means for verifying the authentication and authorization of the received request; Means for optimizing data extraction logic based on past extraction history; Means for extracting data from the enterprise's information sources; Means for converting the extracted data into the requested format; Means for sending the converted data to the requester; Means for recording each request and its processing result; A system including the above.

Description

Technical Field

[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 and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] When introducing a plurality of artificial intelligence agents in an enterprise, it is necessary to individually adjust data acquisition and formatting according to the requirements of each agent, which requires a great deal of labor and time. Also, it is difficult to effectively optimize access to data sources and manage them securely. There is a need for a mechanism to reduce the complexity, burden, and security risks of such processes.

Means for Solving the Problems

[0005] This invention provides a system for unified management of data access between a company's information sources and multiple AI agents. The system includes means for receiving data requests and analyzing the details of the requests, means for verifying the authentication and authorization of the requests, means for optimizing data extraction logic based on past extraction history, means for extracting data from the information sources, means for converting the data into a requested format, means for transmitting the converted data, and means for recording each request and its processing results. This enables the efficient and secure delivery of data.

[0006] A "data request" is a request sent with the purpose of obtaining specific information.

[0007] "Data type" refers to the type or category to which the requested data belongs.

[0008] "Format" refers to the way data is represented or its structure.

[0009] Authentication is the process of verifying that an access request is genuine.

[0010] "Authorization" is the process of determining whether a particular request is permitted.

[0011] "Extraction history" refers to a record of data extraction operations performed in the past.

[0012] "Data extraction logic" refers to the algorithms and procedures used to obtain specific data from a source.

[0013] "A company's information source" refers to the location or system where data managed within a company is stored.

[0014] A "cache" is a mechanism for temporarily storing data, which improves the speed of data access.

[0015] A "request" is a demand for the system to provide data or services.

[0016] A "record" is an act or process of storing and preserving specific events or data.

Brief Description of the Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It 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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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), etc.

[0021] 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.

[0022] 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.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention provides a system for efficiently and securely exchanging data between a company's information sources and multiple artificial intelligence agents. In this system, the server functions as a data access agent, uniformly processing data requests from various AI agents.

[0039] When the server receives a data request from a user (AI agent), it analyzes the data type and format contained in the request. Next, the server verifies the validity and authorization of the request based on the authentication information provided by the user. After authentication and authorization are complete, the server refers to past data extraction history to determine the optimal data extraction logic. This process improves the efficiency of data acquisition and reduces the burden on the company's data sources.

[0040] Once the data is extracted, the server formats it into the requested format. This format conversion makes the data easily usable by the AI ​​agent. Finally, the server sends the formatted data to the user.

[0041] Furthermore, the server meticulously records each request and its outcome, which is used for future optimization and security audits. This improves transparency and reliability throughout the entire data access process.

[0042] As a concrete example, if a user submits a request to analyze customer purchase data, the server parses the request and verifies, based on authentication information, that it is an authorized request. Next, it selects the optimal data extraction method, extracts the necessary data, converts it to JSON format, and sends it to the user. In this way, the present invention simplifies and streamlines data access between companies and AI agents.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives data requests sent by the user (AI agent). These requests include the type and format of the data required.

[0046] Step 2:

[0047] The server verifies the authentication information in the request message to confirm the user's identity. Next, it determines whether the user has access rights to the requested data.

[0048] Step 3:

[0049] The server refers to the history of past data extractions to determine the most efficient data extraction method. This includes optimizing database queries and making effective use of the cache.

[0050] Step 4:

[0051] The server extracts data from the company's information sources using a predetermined method. If the required data spans multiple sources, parallel processes are used to efficiently collect the data.

[0052] Step 5:

[0053] The server formats the extracted data into the format requested by the user. Data formatting may include processes such as filtering and aggregation.

[0054] Step 6:

[0055] The server sends the formatted data to the user. The data sent includes metadata and status information as needed.

[0056] Step 7:

[0057] The server meticulously records processed requests and their results, saving them as logs. This log information is used for future performance analysis and security audits.

[0058] (Example 1)

[0059] 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."

[0060] In modern information systems, it is crucial for diverse artificial intelligence agents to efficiently and securely acquire and utilize data from corporate information sources. However, a lack of optimization in data request analysis, authentication, and extraction processes leads to increased load on corporate systems and decreased efficiency in information utilization. Furthermore, insufficient recording of each request and its processing results poses a challenge in ensuring transparency and reliability of data access.

[0061] 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.

[0062] In this invention, the server includes means for receiving data requests and analyzing the requested data attributes and format, means for verifying authentication and authorization information of the received request, and means for optimizing the information extraction process based on past extraction history. This enables efficient and secure data access.

[0063] A "data request" refers to a request from a user to a server that specifies particular data attributes or formats.

[0064] "Authentication information" refers to information used to verify that the user making the data request is a legitimate user.

[0065] "Authorization information" refers to information used to verify whether a user has the necessary permissions to access the data they are requesting.

[0066] "Information extraction processing" refers to the process of retrieving requested data from a company's information sources.

[0067] "Information source" refers to the location and system where information is stored, including databases and storage systems both inside and outside a company.

[0068] "Format" refers to the specific structure or format in which data is represented.

[0069] "Records" refers to the process or specific stored data of saving information about data requests and their responses and results, making it available for later review and analysis.

[0070] "Constraint control" refers to methods and functions for applying policies and rules regarding data access and managing the permission status of requests.

[0071] "Temporary memory" refers to memory and storage solutions that enable the storage and access of data for short periods of time for efficient data processing.

[0072] This invention provides a system for efficiently and securely exchanging data between a company's information source and multiple artificial intelligence (AI) agents. The server acts as a data access agent, uniformly processing data requests from various AI agents. Specifically, the server uses a database management system (DBMS) and authentication software to analyze data requests from users and verify authentication and authorization information.

[0073] The server optimizes the information extraction process by referring to past data extraction history, efficiently extracting the requested data from the company's information sources. Database operations such as SQL queries are utilized in this process. The extracted data is then converted to formats such as JSON as requested. This is done using a data format conversion library executed within the server.

[0074] After data conversion is complete, the server sends this data to the user (AI agent), who can then use it for analysis and learning models. In addition, the server records each request and its processing results, thus saving a history of data access that can be referenced when needed. This feature can be useful for subsequent optimization and security audits.

[0075] For example, if a user requests "sales data for the first half of 2023," the server receives this request and performs analysis. Once authentication is complete, it selects the optimal information extraction process and extracts the requested sales data. The extracted data is converted to JSON format and sent to the user. This system is particularly advantageous when using generative AI models, as users can efficiently obtain data by prompting the generative AI model with a message such as "Please provide sales data for the first half of 2023 in JSON format."

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server receives data requests from users. Specifically, a request message from the user is delivered to the server as input, and its contents include data attributes and format. The server parses this data request and identifies the requested data type and format. The parsing results are then passed on to the next processing step.

[0079] Step 2:

[0080] The server verifies authentication and authorization for the received data request. Inputs include authentication information provided by the user and access control information held within the server. Based on this, the server performs an authorization process to determine if the request is legitimate. If the request is permitted, it outputs an authentication result flag to proceed to the next step.

[0081] Step 3:

[0082] The server refers to past data extraction history to determine the optimal information extraction process. The inputs are past data extraction records and the attributes of the current data request. Based on this, the server selects an information extraction method, such as an SQL query, to determine the most efficient data retrieval method. The output of this step is the selected extraction logic.

[0083] Step 4:

[0084] The server extracts data from the company's information sources using a predetermined information extraction process. The input includes the location of the information source to access and the extraction logic. The server connects to the specified database management system and retrieves the necessary data according to the extraction logic. The output is the extracted raw data.

[0085] Step 5:

[0086] The server converts the extracted raw data into the requested format. The input includes the extracted raw data and the requested format information (e.g., JSON format). The server uses a data format conversion library to format the data to the specified format. The formatted output data is then used in the next step.

[0087] Step 6:

[0088] The server sends the transformed data to the user. The input consists of the formatted data and the user's connection information. The server uses a network protocol to send the data to the user and confirms that the request has been completed. The output is the data that reached the user.

[0089] Step 7:

[0090] The server meticulously records each request and its processing results. Input includes the request details, the results obtained at each processing step, and the overall response time. The server stores this information in a logging system to create records for later analysis and auditing. Output is the updated log data.

[0091] (Application Example 1)

[0092] 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."

[0093] There is a need to improve efficiency and security in data access between corporate databases and multiple artificial intelligence agents. Furthermore, a system is required that allows data center administrators using mobile devices to quickly and securely retrieve information. In addition, optimal data extraction based on information extraction history and clear access control for all requests are necessary.

[0094] 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.

[0095] In this invention, the server includes means for receiving data requests and analyzing the type and format of the requested information, means for verifying the authentication and authorization of the received request, and means for optimizing the information extraction principle based on past extraction history. This enables data center administrators to efficiently and securely obtain information using portable terminals.

[0096] A "data request" is a request to obtain specific information or data.

[0097] "Type of information" refers to the classification or category of data that is requested to be acquired.

[0098] "Format" refers to the specific format or structure in which data is presented.

[0099] "Analysis" is the process of understanding data requirements and extracting their details.

[0100] "Authentication" is the act of verifying that the person sending the request is legitimate.

[0101] "Permissions" are attributes that indicate the scope or permission to access data.

[0102] "Extraction history" refers to a record of information retrieval performed in the past.

[0103] A "principle" refers to the basic methods or logic used to extract information.

[0104] A "portable terminal" is a small, portable electronic device used for accessing information.

[0105] A "data center administrator" is a person responsible for overseeing and managing the information and systems within a data center.

[0106] This invention provides a system for efficiently and securely facilitating information access between a company's database and an AI agent. The server receives a data request and analyzes the type and format of the information contained in the request. After analysis, the server verifies the authentication information of the user who submitted the request and confirms that the user's authority is appropriate. After authentication and authority verification are complete, the server optimizes the information extraction principle using past extraction history and extracts the most relevant information from the company's database.

[0107] The extracted information is converted to a requested format, taking into account access from mobile devices. This system is designed to allow data center administrators and other users to efficiently access the information using mobile devices such as smartphones and tablets. The server logs the entire process for later optimization and security audits.

[0108] As a concrete example, consider a scenario where a data center administrator uses a smartphone to retrieve company sales data weekly. In response to this request, the server can quickly extract the sales data, convert it to JSON format, and send it to the administrator's terminal. This allows the administrator to quickly retrieve and analyze important data even when away from the office.

[0109] An example of a prompt for the generated AI model would be: "Describe an overview of an efficient data access system for a data center. Key functions include data request analysis, authentication verification, selection of optimal data extraction logic, and format conversion."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The user's terminal sends a data request to the server. The input is a request specifying the type and format of information needed. The server receives this request as output.

[0113] Step 2:

[0114] The server analyzes the content of the received data request to identify the type and format of the information. This analysis provides the server with the information necessary for the next processing step. The input is the data request from the user, and the output is the analysis result.

[0115] Step 3:

[0116] The server verifies the user's authentication information. It requires the user's authentication information as input and determines if the permissions are appropriate. The output is the result of the authentication and permission check.

[0117] Step 4:

[0118] The server refers to past extraction history and selects the optimal information extraction logic. The input is the past data extraction history, and the output is the selected extraction logic. In this process, the server makes decisions to enable efficient extraction.

[0119] Step 5:

[0120] The server extracts the necessary information from the company's database. The input is the selected logic and information from the database, and the output is the extracted information. The server efficiently retrieves the data.

[0121] Step 6:

[0122] The server converts the extracted information into a format specified by the user. The input is the extracted information, and the output is formatted data. The server shapes the data according to the user's request.

[0123] Step 7:

[0124] The server sends the converted data to the user's terminal. The input is formatted data, and the output is the data that reaches the user's terminal. The server delivers the data correctly.

[0125] Step 8:

[0126] The server meticulously records each request and its processing results. The input consists of all operation logs, and the output is the recorded log data. The server uses this information to prepare for future optimizations and security audits.

[0127] 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.

[0128] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. In addition to the functions of conventional data access agents, this system incorporates an emotion engine that recognizes user emotions. This allows for the optimal customization of data processing priorities and content based on the emotions expressed by the user.

[0129] The server receives data requests from users and parses the requested data type and format as usual. In addition, the sentiment engine analyzes the user's emotions based on their statements and written documents and determines their emotional state. By understanding the user's emotional state, such as whether they are feeling urgent or facing a specific problem, the server can dynamically change the priority of data provision.

[0130] Furthermore, the server can provide personalized support and recommendations as needed, based on the emotional data obtained by the emotion engine. For example, if the server determines that a user is experiencing stress, it can prioritize providing data and resources that can help reduce that stress. This personalized approach allows users to quickly obtain information that is relevant to their situation.

[0131] As a concrete example, when a user initiates an interaction, the server uses an emotion engine to analyze their emotions from the text message or voice message. If the emotion engine determines that the user is expressing dissatisfaction, the server prioritizes extracting information to resolve that dissatisfaction, converts the format, and responds quickly. At the same time, the server meticulously records this request and its processing results to help improve the service in the future.

[0132] As described above, the present invention, which includes an emotion engine, effectively improves the data access process between companies and AI agents, enabling personalized responses that are tailored to the user's situation and emotions.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server receives data requests from the user (AI agent). These requests include information about the type and format of the data required.

[0136] Step 2:

[0137] The server parses the received request and verifies the authentication information for the data request. At this point, it determines whether the user has the appropriate access rights.

[0138] Step 3:

[0139] The server uses an emotion engine to analyze the user's emotional state. Based on messages and voice data provided by the user, it identifies the emotion and evaluates the degree of dissatisfaction or urgency.

[0140] Step 4:

[0141] The server determines the priority of data delivery based on the user's emotional state obtained through sentiment analysis. If the request is urgent, data processing is given top priority.

[0142] Step 5:

[0143] The server selects the most efficient data extraction logic by referring to past extraction history and collects the necessary data from the company's information sources.

[0144] Step 6:

[0145] The server converts the extracted data into the format requested by the user. Filtering and data formatting are performed during this process.

[0146] Step 7:

[0147] The server quickly sends formatted data to the user. In particular, if the sentiment engine determines that the user is dissatisfied, it prioritizes providing information suitable for resolving the problem.

[0148] Step 8:

[0149] The server meticulously records each request and its processing result. This recorded information is later analyzed to improve the service.

[0150] (Example 2)

[0151] 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".

[0152] Information provision systems require flexible and efficient data access that responds to users' emotions and circumstances. However, conventional systems provide uniform data without considering user emotions, making it difficult to provide individualized support that meets user needs.

[0153] 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.

[0154] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format; means for analyzing the user's emotions using an emotion analysis engine and dynamically adjusting the priority of data provision based on the emotion data; and means for providing personalized support or recommendations based on the emotion data. This enables flexible and efficient data access that is tailored to the user's emotions and needs.

[0155] A "data request" is a request that a user sends to a system to obtain specific information or data.

[0156] "Data type" is an attribute that indicates the type of data, and includes formats such as text, numbers, and images.

[0157] A "format" is a type of data that defines its structure, and includes formats such as JSON and XML.

[0158] A "sentiment analysis engine" is a software component that analyzes a user's speech and text to identify their emotions and state.

[0159] "Personalized support" refers to a service that provides dedicated information and data tailored to the user's specific emotions and needs.

[0160] "Corporate information sources" refer to databases and information systems owned by a company, which function as sources from which data is extracted.

[0161] "Conversion" refers to the process of adapting extracted data to a format that meets the user's requirements.

[0162] "Recording" means saving each request and its processing results, and keeping them in a database for later analysis and reference.

[0163] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. This system incorporates an emotion analysis engine to recognize user emotions, thereby optimally customizing data processing priorities and content based on the emotions expressed by the user.

[0164] The server receives data requests from users and parses the requested data type and format. This parsing utilizes a network interface for data communication and a processor for data processing. The sentiment analysis engine analyzes text data contained in user statements and documents and determines the emotional state based on natural language processing techniques. This process uses a generative AI model to score and classify the user's emotions.

[0165] For example, if a user sends a request saying, "I'm in a hurry. I need the information now," the sentiment analysis engine will analyze the user's urgency, and based on the results, the server will prioritize processing this request. The server can also provide personalized support and recommendations that are appropriate to the user's emotions. For example, if the user is feeling stressed, it will provide information and resources that can help reduce stress.

[0166] An example of a prompt for a generative AI model might be, "Please tell me how to determine if a user is experiencing stress and how to optimize the service based on that emotion." This enables flexible data provision tailored to individual user needs.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server receives data requests from users and parses the requested data type and format. As input, it receives the request message sent by the user, parses it to identify the data type (e.g., text, number) and format (e.g., JSON, XML). As output, it stores the parsing results in an internal data structure and passes them on to subsequent processing. Specifically, the network module captures the request, and the parser extracts the data and format information.

[0170] Step 2:

[0171] The server activates an emotion analysis engine to analyze the emotions from the user's statements or written materials. It receives the user's text data as input and generates an emotion score using natural language processing. As output, it retrieves the analyzed emotion data (e.g., positive, negative, neutral) and saves it as the basis for prioritization. Specifically, a generative AI model performs emotion analysis on the text and outputs the scoring results.

[0172] Step 3:

[0173] The server dynamically adjusts the priority of data provision based on the acquired sentiment data. It takes the sentiment score generated in step 2 as input and uses this score to set the request priority. As output, it updates the request queue with the applied priority. Specifically, the prioritization algorithm evaluates the sentiment score and reorganizes the process queue.

[0174] Step 4:

[0175] The server generates and provides personalized support and recommendations to users based on sentiment data. It uses the user's sentiment score and past request history as input to select appropriate support information and recommendations. As output, it generates personalized content and adds it to the response data provided to the user. Specifically, the recommendation engine queries the corresponding database to extract the most suitable resources.

[0176] Step 5:

[0177] The server generates a response message to the user, converts it to a predetermined format, and then sends it to the user. It receives extracted data and individualized support information as input and constructs the message according to the requested format. As output, it sends the formatted data to the user and logs the request and processing results. Specifically, the formatter formats the message, and the transmitter sends it over the network.

[0178] (Application Example 2)

[0179] 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".

[0180] Traditional data access management systems, by providing requested data uniformly without considering user emotions, could potentially lead to decreased user satisfaction. Furthermore, their inability to respond flexibly to user situations and emotions often resulted in a lack of prompt responses, especially in situations requiring immediate attention. This highlighted the challenge of improving the customer experience in corporate customer service.

[0181] 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.

[0182] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format, means for analyzing data sent from the user and determining the emotional state, and means for changing the priority of data provision based on the determined emotional state. This enables rapid and personalized data provision and support in response to the user's emotions.

[0183] A "means for receiving data requests" is a mechanism for receiving information requests sent from an external source and for initially recognizing their contents.

[0184] "Means for parsing data type and format" refers to a function for understanding the type and format described in a received data request and determining appropriate processing.

[0185] "Means of verifying authentication and authorization" are mechanisms that are responsible for verifying whether an incoming request is legitimate and determining whether it is from an authorized user.

[0186] "Methods for optimizing data extraction logic" refer to functions that analyze past usage history and select the optimal extraction method in order to improve the efficiency of data retrieval.

[0187] "Means of extracting data from information sources" refers to the process of retrieving necessary information from a company's database or other information sources.

[0188] "Means of converting to the requested format" refers to the technology used to reconstruct extracted data into a format specified by the user.

[0189] "Means for transmitting converted data" refers to means that enable the delivery of format-converted information to the requester.

[0190] "Means for recording requests and their processing results" refers to a mechanism for saving a history of data requests and their responses.

[0191] "A means of analyzing user-generated data and determining emotional state" refers to an engine that analyzes text and audio provided by users to determine their psychological state.

[0192] "A means of changing the priority of data provision based on emotional state" refers to a function that dynamically adjusts which information is prioritized based on the user's emotions.

[0193] "Means of providing personalized support" refers to the process of providing assistance that is customized to the user's specific needs and emotional state.

[0194] The system to realize this application utilizes smartphones and servers as its main hardware. When the server receives a data request sent by the user, it parses the requested data type and format and verifies the user's authentication and authorization. Next, it extracts the necessary data from the company's information source and converts the extracted data into the requested format.

[0195] Furthermore, this system uses an emotion engine to analyze the user's emotional state from their transmitted data. The emotion engine uses natural language processing technology (e.g., Google® Cloud Natural Language API) to analyze the user's text and voice and determine their emotional state. Based on the resulting emotional data, data provision priorities are dynamically adjusted, providing personalized support and recommendations.

[0196] The server also uses AI models (e.g., OpenAI® GPT-3®) to generate responses based on user interaction. These responses are tailored to the user's state and provide immediate assistance as needed.

[0197] To give a specific example, if a user connects to customer support using their smartphone and expresses dissatisfaction that their order hasn't arrived yet, the system analyzes this information. The emotion engine identifies the emotion of dissatisfaction and provides information to quickly resolve the issue. It also sends a prompt to the generative AI model saying, "It appears the user is dissatisfied with their order. As a response, generate a message that will calm the customer and indicate prompt action to resolve the problem," and generates an appropriate response.

[0198] Thus, the present invention embodies a system that provides advanced personalized data access and support based on user emotions, thereby improving the customer experience.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The server receives data requests from users. At this time, the user provides text messages or voice data as input. The server retrieves this data and performs preprocessing to extract information about the requested data type and format.

[0202] Step 2:

[0203] The server verifies user authentication and authorization before accessing the information source. This step requires a user ID or authentication token as input. The server checks the database to confirm that the request is legitimate and proceeds with data extraction only if permitted.

[0204] Step 3:

[0205] The server activates the emotion engine and analyzes the user's transmitted data. Text messages and voice data are provided as input, and the emotional state (e.g., dissatisfaction, relief, urgency) is analyzed as output. The emotion engine uses natural language processing techniques to extract emotional characteristics and passes the results to the next step.

[0206] Step 4:

[0207] The server dynamically adjusts the priority of data provision based on the analyzed emotional states. It receives the analyzed emotional states as input and generates a prioritized data sequence as output. In this process, it is configured to prioritize responses for emotions of high urgency.

[0208] Step 5:

[0209] The server extracts data from corporate sources and converts it to the requested format. Here, a prioritized list of data is used as input, and formatted data is generated as output. Information collection and transformation are performed using efficient database queries and formatting algorithms.

[0210] Step 6:

[0211] The terminal sends the converted data to the user. The input is formatted data, and the output includes the display for the user. The terminal receives the data to display and provides the information in the most appropriate way for the user's device.

[0212] Step 7:

[0213] The server uses an AI model to generate responses tailored to the user's emotional state. The user's emotional state and related data are provided as input, and a customized message is generated as output. The generating AI model uses prompts to create flexible and appropriate responses.

[0214] Step 8:

[0215] The server records all requests and their processing results. Processed request data is provided as input, and logs are stored in the database as output. These logs are useful for future system improvements and troubleshooting.

[0216] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating 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.

[0217] 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] In the smart glasses 214, 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.

[0231] Next, the identification processing performed by the identification 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 glasses 214 will be referred to as the "terminal".

[0232] This invention provides a system for efficiently and securely exchanging data between a company's information sources and multiple artificial intelligence agents. In this system, the server functions as a data access agent, uniformly processing data requests from various AI agents.

[0233] When the server receives a data request from a user (AI agent), it analyzes the data type and format contained in the request. Next, the server verifies the validity and authorization of the request based on the authentication information provided by the user. After authentication and authorization are complete, the server refers to past data extraction history to determine the optimal data extraction logic. This process improves the efficiency of data acquisition and reduces the burden on the company's data sources.

[0234] Once the data is extracted, the server formats it into the requested format. This format conversion makes the data easily usable by the AI ​​agent. Finally, the server sends the formatted data to the user.

[0235] Furthermore, the server meticulously records each request and its outcome, which is used for future optimization and security audits. This improves transparency and reliability throughout the entire data access process.

[0236] As a concrete example, if a user submits a request to analyze customer purchase data, the server parses the request and verifies, based on authentication information, that it is an authorized request. Next, it selects the optimal data extraction method, extracts the necessary data, converts it to JSON format, and sends it to the user. In this way, the present invention simplifies and streamlines data access between companies and AI agents.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] The server receives data requests sent by the user (AI agent). These requests include the type and format of the data required.

[0240] Step 2:

[0241] The server verifies the authentication information in the request message to confirm the user's identity. Next, it determines whether the user has access rights to the requested data.

[0242] Step 3:

[0243] The server refers to the history of past data extractions to determine the most efficient data extraction method. This includes optimizing database queries and making effective use of the cache.

[0244] Step 4:

[0245] The server extracts data from the company's information sources using a predetermined method. If the required data spans multiple sources, parallel processes are used to efficiently collect the data.

[0246] Step 5:

[0247] The server formats the extracted data into the format requested by the user. Data formatting may include processes such as filtering and aggregation.

[0248] Step 6:

[0249] The server sends the formatted data to the user. The data sent includes metadata and status information as needed.

[0250] Step 7:

[0251] The server meticulously records processed requests and their results, saving them as logs. This log information is used for future performance analysis and security audits.

[0252] (Example 1)

[0253] 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."

[0254] In modern information systems, it is crucial for diverse artificial intelligence agents to efficiently and securely acquire and utilize data from corporate information sources. However, a lack of optimization in data request analysis, authentication, and extraction processes leads to increased load on corporate systems and decreased efficiency in information utilization. Furthermore, insufficient recording of each request and its processing results poses a challenge in ensuring transparency and reliability of data access.

[0255] 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.

[0256] In this invention, the server includes means for receiving data requests and analyzing the requested data attributes and format, means for verifying authentication and authorization information of the received request, and means for optimizing the information extraction process based on past extraction history. This enables efficient and secure data access.

[0257] A "data request" refers to a request from a user to a server that specifies particular data attributes or formats.

[0258] "Authentication information" refers to information used to verify that the user making the data request is a legitimate user.

[0259] "Authorization information" refers to information used to verify whether a user has the necessary permissions to access the data they are requesting.

[0260] "Information extraction processing" refers to the process of retrieving requested data from a company's information sources.

[0261] "Information source" refers to the location and system where information is stored, including databases and storage systems both inside and outside a company.

[0262] "Format" refers to the specific structure or format in which data is represented.

[0263] "Records" refers to the process or specific stored data of saving information about data requests and their responses and results, making it available for later review and analysis.

[0264] "Constraint control" refers to methods and functions for applying policies and rules regarding data access and managing the permission status of requests.

[0265] "Temporary memory" refers to memory and storage solutions that enable the storage and access of data for short periods of time for efficient data processing.

[0266] This invention provides a system for efficiently and securely exchanging data between a company's information source and multiple artificial intelligence (AI) agents. The server acts as a data access agent, uniformly processing data requests from various AI agents. Specifically, the server uses a database management system (DBMS) and authentication software to analyze data requests from users and verify authentication and authorization information.

[0267] The server optimizes the information extraction process by referring to past data extraction history, efficiently extracting the requested data from the company's information sources. Database operations such as SQL queries are utilized in this process. The extracted data is then converted to formats such as JSON as requested. This is done using a data format conversion library executed within the server.

[0268] After data conversion is complete, the server sends this data to the user (AI agent), who can then use it for analysis and learning models. In addition, the server records each request and its processing results, thus saving a history of data access that can be referenced when needed. This feature can be useful for subsequent optimization and security audits.

[0269] For example, if a user requests "sales data for the first half of 2023," the server receives this request and performs analysis. Once authentication is complete, it selects the optimal information extraction process and extracts the requested sales data. The extracted data is converted to JSON format and sent to the user. This system is particularly advantageous when using generative AI models, as users can efficiently obtain data by prompting the generative AI model with a message such as "Please provide sales data for the first half of 2023 in JSON format."

[0270] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0271] Step 1:

[0272] The server receives data requests from users. Specifically, a request message from the user is delivered to the server as input, and its contents include data attributes and format. The server parses this data request and identifies the requested data type and format. The parsing results are then passed on to the next processing step.

[0273] Step 2:

[0274] The server verifies authentication and authorization for the received data request. Inputs include authentication information provided by the user and access control information held within the server. Based on this, the server performs an authorization process to determine if the request is legitimate. If the request is permitted, it outputs an authentication result flag to proceed to the next step.

[0275] Step 3:

[0276] The server refers to past data extraction history to determine the optimal information extraction process. The inputs are past data extraction records and the attributes of the current data request. Based on this, the server selects an information extraction method, such as an SQL query, to determine the most efficient data retrieval method. The output of this step is the selected extraction logic.

[0277] Step 4:

[0278] The server extracts data from the enterprise's information sources using the determined information extraction process. The input includes the location of the information source to access and the extraction logic. The server connects to the specified database management system and retrieves the required data according to the extraction logic. As output, the extracted raw data is obtained.

[0279] Step 5:

[0280] The server converts the extracted raw data into the required format. The input includes the extracted raw data and the required format information (e.g., JSON format). The server uses a data format conversion library to format the data into the specified format. The outputted formatted data is used in the next step.

[0281] Step 6:

[0282] The server sends the converted data to the user. The input includes the formatted data and the user's connection information. The server uses a network protocol to send the data to the user and confirm that the request has been completed. The output is the data that reaches the user.

[0283] Step 7:

[0284] The server records each request and its processing results in detail. The input includes the request content, the results obtained at each step of the processing, and the overall response time. The server saves this in a logging system and creates records for later analysis and auditing. The output is the updated log data.

[0285] (Application Example 1)

[0286] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0287] In data access between an enterprise database and multiple artificial intelligence agents, there is a need to improve efficiency and security. Also, a system is required that enables a data center administrator using a portable terminal to quickly and securely obtain information. Furthermore, optimal data extraction based on the history of information extraction and clear authority management for all requests are needed.

[0288] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0289] In this invention, the server includes means for receiving a data request, analyzing the type and format of the requested information, means for authenticating the received request and confirming the authority, and means for optimizing the principle of information extraction based on the past extraction history. Thereby, it becomes possible for a data center administrator to efficiently and securely obtain information using a portable terminal.

[0290] A "data request" is a request for obtaining specific information or data.

[0291] The "type of information" is the classification or category of the data for which acquisition is requested.

[0292] The "format" is a specific format or structure in which the data is formatted.

[0293] "Analysis" is a process of understanding a data request and extracting its details.

[0294] "Authentication" is an act of confirming that the person sending the request is legitimate.

[0295] "Authority" is an attribute indicating the range or permission to access data.

[0296] The "extraction history" is a record of past information acquisitions.

[0297] A "principle" refers to the basic methods or logic used to extract information.

[0298] A "portable terminal" is a small, portable electronic device used for accessing information.

[0299] A "data center administrator" is a person responsible for overseeing and managing the information and systems within a data center.

[0300] This invention provides a system for efficiently and securely facilitating information access between a company's database and an AI agent. The server receives a data request and analyzes the type and format of the information contained in the request. After analysis, the server verifies the authentication information of the user who submitted the request and confirms that the user's authority is appropriate. After authentication and authority verification are complete, the server optimizes the information extraction principle using past extraction history and extracts the most relevant information from the company's database.

[0301] The extracted information is converted to a requested format, taking into account access from mobile devices. This system is designed to allow data center administrators and other users to efficiently access the information using mobile devices such as smartphones and tablets. The server logs the entire process for later optimization and security audits.

[0302] As a concrete example, consider a scenario where a data center administrator uses a smartphone to retrieve company sales data weekly. In response to this request, the server can quickly extract the sales data, convert it to JSON format, and send it to the administrator's terminal. This allows the administrator to quickly retrieve and analyze important data even when away from the office.

[0303] Examples of prompt texts for the generated AI model are in the form of "Please explain the outline of an efficient data access system for a data center. The key functions include data request analysis, authentication confirmation, selection of optimal data extraction logic, and format conversion."

[0304] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0305] Step 1:

[0306] The user's terminal sends a data request to the server. The input is a request specifying the type and format of the required information. As output, the server receives this request.

[0307] Step 2:

[0308] The server analyzes the content of the received data request and identifies the type and format of the information. Through this analysis, the server obtains the information necessary for the next process. The input is the data request from the user, and the output is the analysis result.

[0309] Step 3:

[0310] The server checks the user's authentication information. As input, the user's authentication information is required to determine whether the permissions are appropriate. The output is the result of the authentication and permission check.

[0311] Step 4:

[0312] The server refers to the past extraction history and selects the optimal information extraction logic. The input is the past data extraction history, and the output is the selected extraction logic. In this process, the server makes a judgment to enable efficient extraction.

[0313] Step 5:

[0314] The server extracts the necessary information from the company's database. The input is the selected logic and information from the database, and the output is the extracted information. The server efficiently retrieves the data.

[0315] Step 6:

[0316] The server converts the extracted information into a format specified by the user. The input is the extracted information, and the output is formatted data. The server shapes the data according to the user's request.

[0317] Step 7:

[0318] The server sends the converted data to the user's terminal. The input is formatted data, and the output is the data that reaches the user's terminal. The server delivers the data correctly.

[0319] Step 8:

[0320] The server meticulously records each request and its processing results. The input consists of all operation logs, and the output is the recorded log data. The server uses this information to prepare for future optimizations and security audits.

[0321] 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.

[0322] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. In addition to the functions of conventional data access agents, this system incorporates an emotion engine that recognizes user emotions. This allows for the optimal customization of data processing priorities and content based on the emotions expressed by the user.

[0323] The server receives data requests from users and parses the requested data type and format as usual. In addition, the sentiment engine analyzes the user's emotions based on their statements and written documents and determines their emotional state. By understanding the user's emotional state, such as whether they are feeling urgent or facing a specific problem, the server can dynamically change the priority of data provision.

[0324] Furthermore, the server can provide personalized support and recommendations as needed, based on the emotional data obtained by the emotion engine. For example, if the server determines that a user is experiencing stress, it can prioritize providing data and resources that can help reduce that stress. This personalized approach allows users to quickly obtain information that is relevant to their situation.

[0325] As a concrete example, when a user initiates an interaction, the server uses an emotion engine to analyze their emotions from the text message or voice message. If the emotion engine determines that the user is expressing dissatisfaction, the server prioritizes extracting information to resolve that dissatisfaction, converts the format, and responds quickly. At the same time, the server meticulously records this request and its processing results to help improve the service in the future.

[0326] As described above, the present invention, which includes an emotion engine, effectively improves the data access process between companies and AI agents, enabling personalized responses that are tailored to the user's situation and emotions.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The server receives data requests from the user (AI agent). These requests include information about the type and format of the data required.

[0330] Step 2:

[0331] The server parses the received request and verifies the authentication information for the data request. At this point, it determines whether the user has the appropriate access rights.

[0332] Step 3:

[0333] The server uses an emotion engine to analyze the user's emotional state. Based on messages and voice data provided by the user, it identifies the emotion and evaluates the degree of dissatisfaction or urgency.

[0334] Step 4:

[0335] The server determines the priority of data delivery based on the user's emotional state obtained through sentiment analysis. If the request is urgent, data processing is given top priority.

[0336] Step 5:

[0337] The server selects the most efficient data extraction logic by referring to past extraction history and collects the necessary data from the company's information sources.

[0338] Step 6:

[0339] The server converts the extracted data into the format requested by the user. Filtering and data formatting are performed during this process.

[0340] Step 7:

[0341] The server quickly sends formatted data to the user. In particular, if the sentiment engine determines that the user is dissatisfied, it prioritizes providing information suitable for resolving the problem.

[0342] Step 8:

[0343] The server meticulously records each request and its processing result. This recorded information is later analyzed to improve the service.

[0344] (Example 2)

[0345] 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".

[0346] Information provision systems require flexible and efficient data access that responds to users' emotions and circumstances. However, conventional systems provide uniform data without considering user emotions, making it difficult to provide individualized support that meets user needs.

[0347] 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.

[0348] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format; means for analyzing the user's emotions using an emotion analysis engine and dynamically adjusting the priority of data provision based on the emotion data; and means for providing personalized support or recommendations based on the emotion data. This enables flexible and efficient data access that is tailored to the user's emotions and needs.

[0349] A "data request" is a request that a user sends to a system to obtain specific information or data.

[0350] "Data type" is an attribute that indicates the type of data, and includes formats such as text, numbers, and images.

[0351] A "format" is a type of data that defines its structure, and includes formats such as JSON and XML.

[0352] A "sentiment analysis engine" is a software component that analyzes a user's speech and text to identify their emotions and state.

[0353] "Personalized support" refers to a service that provides dedicated information and data tailored to the user's specific emotions and needs.

[0354] "Corporate information sources" refer to databases and information systems owned by a company, which function as sources from which data is extracted.

[0355] "Conversion" refers to the process of adapting extracted data to a format that meets the user's requirements.

[0356] "Recording" means saving each request and its processing results, and keeping them in a database for later analysis and reference.

[0357] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. This system incorporates an emotion analysis engine to recognize user emotions, thereby optimally customizing data processing priorities and content based on the emotions expressed by the user.

[0358] The server receives data requests from users and parses the requested data type and format. This parsing utilizes a network interface for data communication and a processor for data processing. The sentiment analysis engine analyzes text data contained in user statements and documents and determines the emotional state based on natural language processing techniques. This process uses a generative AI model to score and classify the user's emotions.

[0359] For example, if a user sends a request saying, "I'm in a hurry. I need the information now," the sentiment analysis engine will analyze the user's urgency, and based on the results, the server will prioritize processing this request. The server can also provide personalized support and recommendations that are appropriate to the user's emotions. For example, if the user is feeling stressed, it will provide information and resources that can help reduce stress.

[0360] An example of a prompt for a generative AI model might be, "Please tell me how to determine if a user is experiencing stress and how to optimize the service based on that emotion." This enables flexible data provision tailored to individual user needs.

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] The server receives data requests from users and parses the requested data type and format. As input, it receives the request message sent by the user, parses it to identify the data type (e.g., text, number) and format (e.g., JSON, XML). As output, it stores the parsing results in an internal data structure and passes them on to subsequent processing. Specifically, the network module captures the request, and the parser extracts the data and format information.

[0364] Step 2:

[0365] The server activates an emotion analysis engine to analyze the emotions from the user's statements or written materials. It receives the user's text data as input and generates an emotion score using natural language processing. As output, it retrieves the analyzed emotion data (e.g., positive, negative, neutral) and saves it as the basis for prioritization. Specifically, a generative AI model performs emotion analysis on the text and outputs the scoring results.

[0366] Step 3:

[0367] The server dynamically adjusts the priority of data provision based on the acquired sentiment data. It takes the sentiment score generated in step 2 as input and uses this score to set the request priority. As output, it updates the request queue with the applied priority. Specifically, the prioritization algorithm evaluates the sentiment score and reorganizes the process queue.

[0368] Step 4:

[0369] The server generates and provides personalized support and recommendations to users based on sentiment data. It uses the user's sentiment score and past request history as input to select appropriate support information and recommendations. As output, it generates personalized content and adds it to the response data provided to the user. Specifically, the recommendation engine queries the corresponding database to extract the most suitable resources.

[0370] Step 5:

[0371] The server generates a response message to the user, converts it to a predetermined format, and then sends it to the user. It receives extracted data and individualized support information as input and constructs the message according to the requested format. As output, it sends the formatted data to the user and logs the request and processing results. Specifically, the formatter formats the message, and the transmitter sends it over the network.

[0372] (Application Example 2)

[0373] 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."

[0374] Traditional data access management systems, by providing requested data uniformly without considering user emotions, could potentially lead to decreased user satisfaction. Furthermore, their inability to respond flexibly to user situations and emotions often resulted in a lack of prompt responses, especially in situations requiring immediate attention. This highlighted the challenge of improving the customer experience in corporate customer service.

[0375] 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.

[0376] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format, means for analyzing data sent from the user and determining the emotional state, and means for changing the priority of data provision based on the determined emotional state. This enables rapid and personalized data provision and support in response to the user's emotions.

[0377] A "means for receiving data requests" is a mechanism for receiving information requests sent from an external source and for initially recognizing their contents.

[0378] "Means for parsing data type and format" refers to a function for understanding the type and format described in a received data request and determining appropriate processing.

[0379] "Means of verifying authentication and authorization" are mechanisms that are responsible for verifying whether an incoming request is legitimate and determining whether it is from an authorized user.

[0380] "Methods for optimizing data extraction logic" refer to functions that analyze past usage history and select the optimal extraction method in order to improve the efficiency of data retrieval.

[0381] "Means of extracting data from information sources" refers to the process of retrieving necessary information from a company's database or other information sources.

[0382] "Means of converting to the requested format" refers to the technology used to reconstruct extracted data into a format specified by the user.

[0383] "Means for transmitting converted data" refers to means that enable the delivery of format-converted information to the requester.

[0384] "Means for recording requests and their processing results" refers to a mechanism for saving a history of data requests and their responses.

[0385] "A means of analyzing user-generated data and determining emotional state" refers to an engine that analyzes text and audio provided by users to determine their psychological state.

[0386] "A means of changing the priority of data provision based on emotional state" refers to a function that dynamically adjusts which information is prioritized based on the user's emotions.

[0387] "Means of providing personalized support" refers to the process of providing assistance that is customized to the user's specific needs and emotional state.

[0388] The system to realize this application utilizes smartphones and servers as its main hardware. When the server receives a data request sent by the user, it parses the requested data type and format and verifies the user's authentication and authorization. Next, it extracts the necessary data from the company's information source and converts the extracted data into the requested format.

[0389] Furthermore, this system uses an emotion engine to analyze the user's emotional state from their outgoing data. The emotion engine uses natural language processing techniques (e.g., Google Cloud Natural Language API) to analyze the user's text and voice and determine their emotional state. Based on the resulting emotional data, data provision priorities are dynamically adjusted, providing personalized support and recommendations.

[0390] The server also uses AI models (e.g., OpenAI GPT-3) to generate responses based on user interaction. These responses are tailored to the user's state and provide immediate assistance as needed.

[0391] To give a specific example, if a user connects to customer support using their smartphone and expresses dissatisfaction that their order hasn't arrived yet, the system analyzes this information. The emotion engine identifies the emotion of dissatisfaction and provides information to quickly resolve the issue. It also sends a prompt to the generative AI model saying, "It appears the user is dissatisfied with their order. As a response, generate a message that will calm the customer and indicate prompt action to resolve the problem," and generates an appropriate response.

[0392] Thus, the present invention embodies a system that provides advanced personalized data access and support based on user emotions, thereby improving the customer experience.

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The server receives data requests from users. At this time, the user provides text messages or voice data as input. The server retrieves this data and performs preprocessing to extract information about the requested data type and format.

[0396] Step 2:

[0397] The server verifies user authentication and authorization before accessing the information source. This step requires a user ID or authentication token as input. The server checks the database to confirm that the request is legitimate and proceeds with data extraction only if permitted.

[0398] Step 3:

[0399] The server activates the emotion engine and analyzes the user's transmitted data. Text messages and voice data are provided as input, and the emotional state (e.g., dissatisfaction, relief, urgency) is analyzed as output. The emotion engine uses natural language processing techniques to extract emotional characteristics and passes the results to the next step.

[0400] Step 4:

[0401] The server dynamically adjusts the priority of data provision based on the analyzed emotional states. It receives the analyzed emotional states as input and generates a prioritized data sequence as output. In this process, it is configured to prioritize responses for emotions of high urgency.

[0402] Step 5:

[0403] The server extracts data from corporate sources and converts it to the requested format. Here, a prioritized list of data is used as input, and formatted data is generated as output. Information collection and transformation are performed using efficient database queries and formatting algorithms.

[0404] Step 6:

[0405] The terminal sends the converted data to the user. The input is formatted data, and the output includes the display for the user. The terminal receives the data to display and provides the information in the most appropriate way for the user's device.

[0406] Step 7:

[0407] The server uses an AI model to generate responses tailored to the user's emotional state. The user's emotional state and related data are provided as input, and a customized message is generated as output. The generating AI model uses prompts to create flexible and appropriate responses.

[0408] Step 8:

[0409] The server records all requests and their processing results. Processed request data is provided as input, and logs are stored in the database as output. These logs are useful for future system improvements and troubleshooting.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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".

[0426] This invention provides a system for efficiently and securely exchanging data between a company's information sources and multiple artificial intelligence agents. In this system, the server functions as a data access agent, uniformly processing data requests from various AI agents.

[0427] When the server receives a data request from a user (AI agent), it analyzes the data type and format contained in the request. Next, the server verifies the validity and authorization of the request based on the authentication information provided by the user. After authentication and authorization are complete, the server refers to past data extraction history to determine the optimal data extraction logic. This process improves the efficiency of data acquisition and reduces the burden on the company's data sources.

[0428] Once the data is extracted, the server formats it into the requested format. This format conversion makes the data easily usable by the AI ​​agent. Finally, the server sends the formatted data to the user.

[0429] Furthermore, the server meticulously records each request and its outcome, which is used for future optimization and security audits. This improves transparency and reliability throughout the entire data access process.

[0430] As a concrete example, if a user submits a request to analyze customer purchase data, the server parses the request and verifies, based on authentication information, that it is an authorized request. Next, it selects the optimal data extraction method, extracts the necessary data, converts it to JSON format, and sends it to the user. In this way, the present invention simplifies and streamlines data access between companies and AI agents.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] The server receives data requests sent by the user (AI agent). These requests include the type and format of the data required.

[0434] Step 2:

[0435] The server verifies the authentication information in the request message to confirm the user's identity. Next, it determines whether the user has access rights to the requested data.

[0436] Step 3:

[0437] The server refers to the history of past data extractions to determine the most efficient data extraction method. This includes optimizing database queries and making effective use of the cache.

[0438] Step 4:

[0439] The server extracts data from the company's information sources using a predetermined method. If the required data spans multiple sources, parallel processes are used to efficiently collect the data.

[0440] Step 5:

[0441] The server formats the extracted data into the format requested by the user. Data formatting may include processes such as filtering and aggregation.

[0442] Step 6:

[0443] The server sends the formatted data to the user. The data sent includes metadata and status information as needed.

[0444] Step 7:

[0445] The server meticulously records processed requests and their results, saving them as logs. This log information is used for future performance analysis and security audits.

[0446] (Example 1)

[0447] 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."

[0448] In modern information systems, it is crucial for diverse artificial intelligence agents to efficiently and securely acquire and utilize data from corporate information sources. However, a lack of optimization in data request analysis, authentication, and extraction processes leads to increased load on corporate systems and decreased efficiency in information utilization. Furthermore, insufficient recording of each request and its processing results poses a challenge in ensuring transparency and reliability of data access.

[0449] 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.

[0450] In this invention, the server includes means for receiving data requests and analyzing the requested data attributes and format, means for verifying authentication and authorization information of the received request, and means for optimizing the information extraction process based on past extraction history. This enables efficient and secure data access.

[0451] A "data request" refers to a request from a user to a server that specifies particular data attributes or formats.

[0452] "Authentication information" refers to information used to verify that the user making the data request is a legitimate user.

[0453] "Authorization information" refers to information used to verify whether a user has the necessary permissions to access the data they are requesting.

[0454] "Information extraction processing" refers to the process of retrieving requested data from a company's information sources.

[0455] "Information source" refers to the location and system where information is stored, including databases and storage systems both inside and outside a company.

[0456] "Format" refers to the specific structure or format in which data is represented.

[0457] "Records" refers to the process or specific stored data of saving information about data requests and their responses and results, making it available for later review and analysis.

[0458] "Constraint control" refers to methods and functions for applying policies and rules regarding data access and managing the permission status of requests.

[0459] "Temporary memory" refers to memory and storage solutions that enable the storage and access of data for short periods of time for efficient data processing.

[0460] This invention provides a system for efficiently and securely exchanging data between a company's information source and multiple artificial intelligence (AI) agents. The server acts as a data access agent, uniformly processing data requests from various AI agents. Specifically, the server uses a database management system (DBMS) and authentication software to analyze data requests from users and verify authentication and authorization information.

[0461] The server optimizes the information extraction process by referring to past data extraction history, efficiently extracting the requested data from the company's information sources. Database operations such as SQL queries are utilized in this process. The extracted data is then converted to formats such as JSON as requested. This is done using a data format conversion library executed within the server.

[0462] After data conversion is complete, the server sends this data to the user (AI agent), who can then use it for analysis and learning models. In addition, the server records each request and its processing results, thus saving a history of data access that can be referenced when needed. This feature can be useful for subsequent optimization and security audits.

[0463] For example, if a user requests "sales data for the first half of 2023," the server receives this request and performs analysis. Once authentication is complete, it selects the optimal information extraction process and extracts the requested sales data. The extracted data is converted to JSON format and sent to the user. This system is particularly advantageous when using generative AI models, as users can efficiently obtain data by prompting the generative AI model with a message such as "Please provide sales data for the first half of 2023 in JSON format."

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The server receives data requests from users. Specifically, a request message from the user is delivered to the server as input, and its contents include data attributes and format. The server parses this data request and identifies the requested data type and format. The parsing results are then passed on to the next processing step.

[0467] Step 2:

[0468] The server verifies authentication and authorization for the received data request. Inputs include authentication information provided by the user and access control information held within the server. Based on this, the server performs an authorization process to determine if the request is legitimate. If the request is permitted, it outputs an authentication result flag to proceed to the next step.

[0469] Step 3:

[0470] The server refers to past data extraction history to determine the optimal information extraction process. The inputs are past data extraction records and the attributes of the current data request. Based on this, the server selects an information extraction method, such as an SQL query, to determine the most efficient data retrieval method. The output of this step is the selected extraction logic.

[0471] Step 4:

[0472] The server extracts data from the company's information sources using a predetermined information extraction process. The input includes the location of the information source to access and the extraction logic. The server connects to the specified database management system and retrieves the necessary data according to the extraction logic. The output is the extracted raw data.

[0473] Step 5:

[0474] The server converts the extracted raw data into the requested format. The input includes the extracted raw data and the requested format information (e.g., JSON format). The server uses a data format conversion library to format the data to the specified format. The formatted output data is then used in the next step.

[0475] Step 6:

[0476] The server sends the transformed data to the user. The input consists of the formatted data and the user's connection information. The server uses a network protocol to send the data to the user and confirms that the request has been completed. The output is the data that reached the user.

[0477] Step 7:

[0478] The server meticulously records each request and its processing results. Input includes the request details, the results obtained at each processing step, and the overall response time. The server stores this information in a logging system to create records for later analysis and auditing. Output is the updated log data.

[0479] (Application Example 1)

[0480] 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."

[0481] There is a need to improve efficiency and security in data access between corporate databases and multiple artificial intelligence agents. Furthermore, a system is required that allows data center administrators using mobile devices to quickly and securely retrieve information. In addition, optimal data extraction based on information extraction history and clear access control for all requests are necessary.

[0482] 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.

[0483] In this invention, the server includes means for receiving data requests and analyzing the type and format of the requested information, means for verifying the authentication and authorization of the received request, and means for optimizing the information extraction principle based on past extraction history. This enables data center administrators to efficiently and securely obtain information using portable terminals.

[0484] A "data request" is a request to obtain specific information or data.

[0485] "Type of information" refers to the classification or category of data that is requested to be acquired.

[0486] "Format" refers to the specific format or structure in which data is presented.

[0487] "Analysis" is the process of understanding data requirements and extracting their details.

[0488] "Authentication" is the act of verifying that the person sending the request is legitimate.

[0489] "Permissions" are attributes that indicate the scope or permission to access data.

[0490] "Extraction history" refers to a record of information retrieval performed in the past.

[0491] A "principle" refers to the basic methods or logic used to extract information.

[0492] A "portable terminal" is a small, portable electronic device used for accessing information.

[0493] A "data center administrator" is a person responsible for overseeing and managing the information and systems within a data center.

[0494] This invention provides a system for efficiently and securely facilitating information access between a company's database and an AI agent. The server receives a data request and analyzes the type and format of the information contained in the request. After analysis, the server verifies the authentication information of the user who submitted the request and confirms that the user's authority is appropriate. After authentication and authority verification are complete, the server optimizes the information extraction principle using past extraction history and extracts the most relevant information from the company's database.

[0495] The extracted information is converted to a requested format, taking into account access from mobile devices. This system is designed to allow data center administrators and other users to efficiently access the information using mobile devices such as smartphones and tablets. The server logs the entire process for later optimization and security audits.

[0496] As a concrete example, consider a scenario where a data center administrator uses a smartphone to retrieve company sales data weekly. In response to this request, the server can quickly extract the sales data, convert it to JSON format, and send it to the administrator's terminal. This allows the administrator to quickly retrieve and analyze important data even when away from the office.

[0497] An example of a prompt for the generated AI model would be: "Describe an overview of an efficient data access system for a data center. Key functions include data request analysis, authentication verification, selection of optimal data extraction logic, and format conversion."

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] The user's terminal sends a data request to the server. The input is a request specifying the type and format of information needed. The server receives this request as output.

[0501] Step 2:

[0502] The server analyzes the content of the received data request to identify the type and format of the information. This analysis provides the server with the information necessary for the next processing step. The input is the data request from the user, and the output is the analysis result.

[0503] Step 3:

[0504] The server verifies the user's authentication information. It requires the user's authentication information as input and determines if the permissions are appropriate. The output is the result of the authentication and permission check.

[0505] Step 4:

[0506] The server refers to past extraction history and selects the optimal information extraction logic. The input is the past data extraction history, and the output is the selected extraction logic. In this process, the server makes decisions to enable efficient extraction.

[0507] Step 5:

[0508] The server extracts the necessary information from the company's database. The input is the selected logic and information from the database, and the output is the extracted information. The server efficiently retrieves the data.

[0509] Step 6:

[0510] The server converts the extracted information into a format specified by the user. The input is the extracted information, and the output is formatted data. The server shapes the data according to the user's request.

[0511] Step 7:

[0512] The server sends the converted data to the user's terminal. The input is formatted data, and the output is the data that reaches the user's terminal. The server delivers the data correctly.

[0513] Step 8:

[0514] The server meticulously records each request and its processing results. The input consists of all operation logs, and the output is the recorded log data. The server uses this information to prepare for future optimizations and security audits.

[0515] 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.

[0516] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. In addition to the functions of conventional data access agents, this system incorporates an emotion engine that recognizes user emotions. This allows for the optimal customization of data processing priorities and content based on the emotions expressed by the user.

[0517] The server receives data requests from users and parses the requested data type and format as usual. In addition, the sentiment engine analyzes the user's emotions based on their statements and written documents and determines their emotional state. By understanding the user's emotional state, such as whether they are feeling urgent or facing a specific problem, the server can dynamically change the priority of data provision.

[0518] Furthermore, the server can provide personalized support and recommendations as needed, based on the emotional data obtained by the emotion engine. For example, if the server determines that a user is experiencing stress, it can prioritize providing data and resources that can help reduce that stress. This personalized approach allows users to quickly obtain information that is relevant to their situation.

[0519] As a concrete example, when a user initiates an interaction, the server uses an emotion engine to analyze their emotions from the text message or voice message. If the emotion engine determines that the user is expressing dissatisfaction, the server prioritizes extracting information to resolve that dissatisfaction, converts the format, and responds quickly. At the same time, the server meticulously records this request and its processing results to help improve the service in the future.

[0520] As described above, the present invention, which includes an emotion engine, effectively improves the data access process between companies and AI agents, enabling personalized responses that are tailored to the user's situation and emotions.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] The server receives data requests from the user (AI agent). These requests include information about the type and format of the data required.

[0524] Step 2:

[0525] The server parses the received request and verifies the authentication information for the data request. At this point, it determines whether the user has the appropriate access rights.

[0526] Step 3:

[0527] The server uses an emotion engine to analyze the user's emotional state. Based on messages and voice data provided by the user, it identifies the emotion and evaluates the degree of dissatisfaction or urgency.

[0528] Step 4:

[0529] The server determines the priority of data delivery based on the user's emotional state obtained through sentiment analysis. If the request is urgent, data processing is given top priority.

[0530] Step 5:

[0531] The server selects the most efficient data extraction logic by referring to past extraction history and collects the necessary data from the company's information sources.

[0532] Step 6:

[0533] The server converts the extracted data into the format requested by the user. Filtering and data formatting are performed during this process.

[0534] Step 7:

[0535] The server quickly sends formatted data to the user. In particular, if the sentiment engine determines that the user is dissatisfied, it prioritizes providing information suitable for resolving the problem.

[0536] Step 8:

[0537] The server meticulously records each request and its processing result. This recorded information is later analyzed to improve the service.

[0538] (Example 2)

[0539] 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."

[0540] Information provision systems require flexible and efficient data access that responds to users' emotions and circumstances. However, conventional systems provide uniform data without considering user emotions, making it difficult to provide individualized support that meets user needs.

[0541] 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.

[0542] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format; means for analyzing the user's emotions using an emotion analysis engine and dynamically adjusting the priority of data provision based on the emotion data; and means for providing personalized support or recommendations based on the emotion data. This enables flexible and efficient data access that is tailored to the user's emotions and needs.

[0543] A "data request" is a request that a user sends to a system to obtain specific information or data.

[0544] "Data type" is an attribute that indicates the type of data, and includes formats such as text, numbers, and images.

[0545] A "format" is a type of data that defines its structure, and includes formats such as JSON and XML.

[0546] A "sentiment analysis engine" is a software component that analyzes a user's speech and text to identify their emotions and state.

[0547] "Personalized support" refers to a service that provides dedicated information and data tailored to the user's specific emotions and needs.

[0548] "Corporate information sources" refer to databases and information systems owned by a company, which function as sources from which data is extracted.

[0549] "Conversion" refers to the process of adapting extracted data to a format that meets the user's requirements.

[0550] "Recording" means saving each request and its processing results, and keeping them in a database for later analysis and reference.

[0551] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. This system incorporates an emotion analysis engine to recognize user emotions, thereby optimally customizing data processing priorities and content based on the emotions expressed by the user.

[0552] The server receives data requests from users and parses the requested data type and format. This parsing utilizes a network interface for data communication and a processor for data processing. The sentiment analysis engine analyzes text data contained in user statements and documents and determines the emotional state based on natural language processing techniques. This process uses a generative AI model to score and classify the user's emotions.

[0553] For example, if a user sends a request saying, "I'm in a hurry. I need the information now," the sentiment analysis engine will analyze the user's urgency, and based on the results, the server will prioritize processing this request. The server can also provide personalized support and recommendations that are appropriate to the user's emotions. For example, if the user is feeling stressed, it will provide information and resources that can help reduce stress.

[0554] An example of a prompt for a generative AI model might be, "Please tell me how to determine if a user is experiencing stress and how to optimize the service based on that emotion." This enables flexible data provision tailored to individual user needs.

[0555] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0556] Step 1:

[0557] The server receives data requests from users and parses the requested data type and format. As input, it receives the request message sent by the user, parses it to identify the data type (e.g., text, number) and format (e.g., JSON, XML). As output, it stores the parsing results in an internal data structure and passes them on to subsequent processing. Specifically, the network module captures the request, and the parser extracts the data and format information.

[0558] Step 2:

[0559] The server activates an emotion analysis engine to analyze the emotions from the user's statements or written materials. It receives the user's text data as input and generates an emotion score using natural language processing. As output, it retrieves the analyzed emotion data (e.g., positive, negative, neutral) and saves it as the basis for prioritization. Specifically, a generative AI model performs emotion analysis on the text and outputs the scoring results.

[0560] Step 3:

[0561] The server dynamically adjusts the priority of data provision based on the acquired sentiment data. It takes the sentiment score generated in step 2 as input and uses this score to set the request priority. As output, it updates the request queue with the applied priority. Specifically, the prioritization algorithm evaluates the sentiment score and reorganizes the process queue.

[0562] Step 4:

[0563] The server generates and provides personalized support and recommendations to users based on sentiment data. It uses the user's sentiment score and past request history as input to select appropriate support information and recommendations. As output, it generates personalized content and adds it to the response data provided to the user. Specifically, the recommendation engine queries the corresponding database to extract the most suitable resources.

[0564] Step 5:

[0565] The server generates a response message to the user, converts it to a predetermined format, and then sends it to the user. It receives extracted data and individualized support information as input and constructs the message according to the requested format. As output, it sends the formatted data to the user and logs the request and processing results. Specifically, the formatter formats the message, and the transmitter sends it over the network.

[0566] (Application Example 2)

[0567] 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."

[0568] Traditional data access management systems, by providing requested data uniformly without considering user emotions, could potentially lead to decreased user satisfaction. Furthermore, their inability to respond flexibly to user situations and emotions often resulted in a lack of prompt responses, especially in situations requiring immediate attention. This highlighted the challenge of improving the customer experience in corporate customer service.

[0569] 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.

[0570] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format, means for analyzing data sent from the user and determining the emotional state, and means for changing the priority of data provision based on the determined emotional state. This enables rapid and personalized data provision and support in response to the user's emotions.

[0571] A "means for receiving data requests" is a mechanism for receiving information requests sent from an external source and for initially recognizing their contents.

[0572] "Means for parsing data type and format" refers to a function for understanding the type and format described in a received data request and determining appropriate processing.

[0573] "Means of verifying authentication and authorization" are mechanisms that are responsible for verifying whether an incoming request is legitimate and determining whether it is from an authorized user.

[0574] "Methods for optimizing data extraction logic" refer to functions that analyze past usage history and select the optimal extraction method in order to improve the efficiency of data retrieval.

[0575] "Means of extracting data from information sources" refers to the process of retrieving necessary information from a company's database or other information sources.

[0576] "Means of converting to the requested format" refers to the technology used to reconstruct extracted data into a format specified by the user.

[0577] "Means for transmitting converted data" refers to means that enable the delivery of format-converted information to the requester.

[0578] "Means for recording requests and their processing results" refers to a mechanism for saving a history of data requests and their responses.

[0579] "A means of analyzing user-generated data and determining emotional state" refers to an engine that analyzes text and audio provided by users to determine their psychological state.

[0580] "A means of changing the priority of data provision based on emotional state" refers to a function that dynamically adjusts which information is prioritized based on the user's emotions.

[0581] "Means of providing personalized support" refers to the process of providing assistance that is customized to the user's specific needs and emotional state.

[0582] The system to realize this application utilizes smartphones and servers as its main hardware. When the server receives a data request sent by the user, it parses the requested data type and format and verifies the user's authentication and authorization. Next, it extracts the necessary data from the company's information source and converts the extracted data into the requested format.

[0583] Furthermore, this system uses an emotion engine to analyze the user's emotional state from their outgoing data. The emotion engine uses natural language processing techniques (e.g., Google Cloud Natural Language API) to analyze the user's text and voice and determine their emotional state. Based on the resulting emotional data, data provision priorities are dynamically adjusted, providing personalized support and recommendations.

[0584] The server also uses AI models (e.g., OpenAI GPT-3) to generate responses based on user interaction. These responses are tailored to the user's state and provide immediate assistance as needed.

[0585] To give a specific example, if a user connects to customer support using their smartphone and expresses dissatisfaction that their order hasn't arrived yet, the system analyzes this information. The emotion engine identifies the emotion of dissatisfaction and provides information to quickly resolve the issue. It also sends a prompt to the generative AI model saying, "It appears the user is dissatisfied with their order. As a response, generate a message that will calm the customer and indicate prompt action to resolve the problem," and generates an appropriate response.

[0586] Thus, the present invention embodies a system that provides advanced personalized data access and support based on user emotions, thereby improving the customer experience.

[0587] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0588] Step 1:

[0589] The server receives data requests from users. At this time, the user provides text messages or voice data as input. The server retrieves this data and performs preprocessing to extract information about the requested data type and format.

[0590] Step 2:

[0591] The server verifies user authentication and authorization before accessing the information source. This step requires a user ID or authentication token as input. The server checks the database to confirm that the request is legitimate and proceeds with data extraction only if permitted.

[0592] Step 3:

[0593] The server activates the emotion engine and analyzes the user's transmitted data. Text messages and voice data are provided as input, and the emotional state (e.g., dissatisfaction, relief, urgency) is analyzed as output. The emotion engine uses natural language processing techniques to extract emotional characteristics and passes the results to the next step.

[0594] Step 4:

[0595] The server dynamically adjusts the priority of data provision based on the analyzed emotional states. It receives the analyzed emotional states as input and generates a prioritized data sequence as output. In this process, it is configured to prioritize responses for emotions of high urgency.

[0596] Step 5:

[0597] The server extracts data from corporate sources and converts it to the requested format. Here, a prioritized list of data is used as input, and formatted data is generated as output. Information collection and transformation are performed using efficient database queries and formatting algorithms.

[0598] Step 6:

[0599] The terminal sends the converted data to the user. The input is formatted data, and the output includes the display for the user. The terminal receives the data to display and provides the information in the most appropriate way for the user's device.

[0600] Step 7:

[0601] The server uses an AI model to generate responses tailored to the user's emotional state. The user's emotional state and related data are provided as input, and a customized message is generated as output. The generating AI model uses prompts to create flexible and appropriate responses.

[0602] Step 8:

[0603] The server records all requests and their processing results. Processed request data is provided as input, and logs are stored in the database as output. These logs are useful for future system improvements and troubleshooting.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] 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.

[0610] 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).

[0611] 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.

[0612] 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.

[0613] 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).

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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".

[0621] This invention provides a system for efficiently and securely exchanging data between a company's information sources and multiple artificial intelligence agents. In this system, the server functions as a data access agent, uniformly processing data requests from various AI agents.

[0622] When the server receives a data request from a user (AI agent), it analyzes the data type and format contained in the request. Next, the server verifies the validity and authorization of the request based on the authentication information provided by the user. After authentication and authorization are complete, the server refers to past data extraction history to determine the optimal data extraction logic. This process improves the efficiency of data acquisition and reduces the burden on the company's data sources.

[0623] Once the data is extracted, the server formats it into the requested format. This format conversion makes the data easily usable by the AI ​​agent. Finally, the server sends the formatted data to the user.

[0624] Furthermore, the server meticulously records each request and its outcome, which is used for future optimization and security audits. This improves transparency and reliability throughout the entire data access process.

[0625] As a concrete example, if a user submits a request to analyze customer purchase data, the server parses the request and verifies, based on authentication information, that it is an authorized request. Next, it selects the optimal data extraction method, extracts the necessary data, converts it to JSON format, and sends it to the user. In this way, the present invention simplifies and streamlines data access between companies and AI agents.

[0626] The following describes the processing flow.

[0627] Step 1:

[0628] The server receives data requests sent by the user (AI agent). These requests include the type and format of the data required.

[0629] Step 2:

[0630] The server verifies the authentication information in the request message to confirm the user's identity. Next, it determines whether the user has access rights to the requested data.

[0631] Step 3:

[0632] The server refers to the history of past data extractions to determine the most efficient data extraction method. This includes optimizing database queries and making effective use of the cache.

[0633] Step 4:

[0634] The server extracts data from the company's information sources using a predetermined method. If the required data spans multiple sources, parallel processes are used to efficiently collect the data.

[0635] Step 5:

[0636] The server formats the extracted data into the format requested by the user. Data formatting may include processes such as filtering and aggregation.

[0637] Step 6:

[0638] The server sends the formatted data to the user. The data sent includes metadata and status information as needed.

[0639] Step 7:

[0640] The server meticulously records processed requests and their results, saving them as logs. This log information is used for future performance analysis and security audits.

[0641] (Example 1)

[0642] 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".

[0643] In modern information systems, it is crucial for diverse artificial intelligence agents to efficiently and securely acquire and utilize data from corporate information sources. However, a lack of optimization in data request analysis, authentication, and extraction processes leads to increased load on corporate systems and decreased efficiency in information utilization. Furthermore, insufficient recording of each request and its processing results poses a challenge in ensuring transparency and reliability of data access.

[0644] 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.

[0645] In this invention, the server includes means for receiving data requests and analyzing the requested data attributes and format, means for verifying authentication and authorization information of the received request, and means for optimizing the information extraction process based on past extraction history. This enables efficient and secure data access.

[0646] A "data request" refers to a request from a user to a server that specifies particular data attributes or formats.

[0647] "Authentication information" refers to information used to verify that the user making the data request is a legitimate user.

[0648] "Authorization information" refers to information used to verify whether a user has the necessary permissions to access the data they are requesting.

[0649] "Information extraction processing" refers to the process of retrieving requested data from a company's information sources.

[0650] "Information source" refers to the location and system where information is stored, including databases and storage systems both inside and outside a company.

[0651] "Format" refers to the specific structure or format in which data is represented.

[0652] "Records" refers to the process or specific stored data of saving information about data requests and their responses and results, making it available for later review and analysis.

[0653] "Constraint control" refers to methods and functions for applying policies and rules regarding data access and managing the permission status of requests.

[0654] "Temporary memory" refers to memory and storage solutions that enable the storage and access of data for short periods of time for efficient data processing.

[0655] This invention provides a system for efficiently and securely exchanging data between a company's information source and multiple artificial intelligence (AI) agents. The server acts as a data access agent, uniformly processing data requests from various AI agents. Specifically, the server uses a database management system (DBMS) and authentication software to analyze data requests from users and verify authentication and authorization information.

[0656] The server optimizes the information extraction process by referring to past data extraction history, efficiently extracting the requested data from the company's information sources. Database operations such as SQL queries are utilized in this process. The extracted data is then converted to formats such as JSON as requested. This is done using a data format conversion library executed within the server.

[0657] After data conversion is complete, the server sends this data to the user (AI agent), who can then use it for analysis and learning models. In addition, the server records each request and its processing results, thus saving a history of data access that can be referenced when needed. This feature can be useful for subsequent optimization and security audits.

[0658] For example, if a user requests "sales data for the first half of 2023," the server receives this request and performs analysis. Once authentication is complete, it selects the optimal information extraction process and extracts the requested sales data. The extracted data is converted to JSON format and sent to the user. This system is particularly advantageous when using generative AI models, as users can efficiently obtain data by prompting the generative AI model with a message such as "Please provide sales data for the first half of 2023 in JSON format."

[0659] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0660] Step 1:

[0661] The server receives data requests from users. Specifically, a request message from the user is delivered to the server as input, and its contents include data attributes and format. The server parses this data request and identifies the requested data type and format. The parsing results are then passed on to the next processing step.

[0662] Step 2:

[0663] The server verifies authentication and authorization for the received data request. Inputs include authentication information provided by the user and access control information held within the server. Based on this, the server performs an authorization process to determine if the request is legitimate. If the request is permitted, it outputs an authentication result flag to proceed to the next step.

[0664] Step 3:

[0665] The server refers to past data extraction history to determine the optimal information extraction process. The inputs are past data extraction records and the attributes of the current data request. Based on this, the server selects an information extraction method, such as an SQL query, to determine the most efficient data retrieval method. The output of this step is the selected extraction logic.

[0666] Step 4:

[0667] The server extracts data from the company's information sources using a predetermined information extraction process. The input includes the location of the information source to access and the extraction logic. The server connects to the specified database management system and retrieves the necessary data according to the extraction logic. The output is the extracted raw data.

[0668] Step 5:

[0669] The server converts the extracted raw data into the requested format. The input includes the extracted raw data and the requested format information (e.g., JSON format). The server uses a data format conversion library to format the data to the specified format. The formatted output data is then used in the next step.

[0670] Step 6:

[0671] The server sends the transformed data to the user. The input consists of the formatted data and the user's connection information. The server uses a network protocol to send the data to the user and confirms that the request has been completed. The output is the data that reached the user.

[0672] Step 7:

[0673] The server meticulously records each request and its processing results. Input includes the request details, the results obtained at each processing step, and the overall response time. The server stores this information in a logging system to create records for later analysis and auditing. Output is the updated log data.

[0674] (Application Example 1)

[0675] 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".

[0676] There is a need to improve efficiency and security in data access between corporate databases and multiple artificial intelligence agents. Furthermore, a system is required that allows data center administrators using mobile devices to quickly and securely retrieve information. In addition, optimal data extraction based on information extraction history and clear access control for all requests are necessary.

[0677] 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.

[0678] In this invention, the server includes means for receiving data requests and analyzing the type and format of the requested information, means for verifying the authentication and authorization of the received request, and means for optimizing the information extraction principle based on past extraction history. This enables data center administrators to efficiently and securely obtain information using portable terminals.

[0679] A "data request" is a request to obtain specific information or data.

[0680] "Type of information" refers to the classification or category of data that is requested to be acquired.

[0681] "Format" refers to the specific format or structure in which data is presented.

[0682] "Analysis" is the process of understanding data requirements and extracting their details.

[0683] "Authentication" is the act of verifying that the person sending the request is legitimate.

[0684] "Permissions" are attributes that indicate the scope or permission to access data.

[0685] "Extraction history" refers to a record of information retrieval performed in the past.

[0686] A "principle" refers to the basic methods or logic used to extract information.

[0687] A "portable terminal" is a small, portable electronic device used for accessing information.

[0688] A "data center administrator" is a person responsible for overseeing and managing the information and systems within a data center.

[0689] This invention provides a system for efficiently and securely facilitating information access between a company's database and an AI agent. The server receives a data request and analyzes the type and format of the information contained in the request. After analysis, the server verifies the authentication information of the user who submitted the request and confirms that the user's authority is appropriate. After authentication and authority verification are complete, the server optimizes the information extraction principle using past extraction history and extracts the most relevant information from the company's database.

[0690] The extracted information is converted to a requested format, taking into account access from mobile devices. This system is designed to allow data center administrators and other users to efficiently access the information using mobile devices such as smartphones and tablets. The server logs the entire process for later optimization and security audits.

[0691] As a concrete example, consider a scenario where a data center administrator uses a smartphone to retrieve company sales data weekly. In response to this request, the server can quickly extract the sales data, convert it to JSON format, and send it to the administrator's terminal. This allows the administrator to quickly retrieve and analyze important data even when away from the office.

[0692] An example of a prompt for the generated AI model would be: "Describe an overview of an efficient data access system for a data center. Key functions include data request analysis, authentication verification, selection of optimal data extraction logic, and format conversion."

[0693] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0694] Step 1:

[0695] The user's terminal sends a data request to the server. The input is a request specifying the type and format of information needed. The server receives this request as output.

[0696] Step 2:

[0697] The server analyzes the content of the received data request to identify the type and format of the information. This analysis provides the server with the information necessary for the next processing step. The input is the data request from the user, and the output is the analysis result.

[0698] Step 3:

[0699] The server verifies the user's authentication information. It requires the user's authentication information as input and determines if the permissions are appropriate. The output is the result of the authentication and permission check.

[0700] Step 4:

[0701] The server refers to past extraction history and selects the optimal information extraction logic. The input is the past data extraction history, and the output is the selected extraction logic. In this process, the server makes decisions to enable efficient extraction.

[0702] Step 5:

[0703] The server extracts the necessary information from the company's database. The input is the selected logic and information from the database, and the output is the extracted information. The server efficiently retrieves the data.

[0704] Step 6:

[0705] The server converts the extracted information into a format specified by the user. The input is the extracted information, and the output is formatted data. The server shapes the data according to the user's request.

[0706] Step 7:

[0707] The server sends the converted data to the user's terminal. The input is formatted data, and the output is the data that reaches the user's terminal. The server delivers the data correctly.

[0708] Step 8:

[0709] The server meticulously records each request and its processing results. The input consists of all operation logs, and the output is the recorded log data. The server uses this information to prepare for future optimizations and security audits.

[0710] 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.

[0711] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. In addition to the functions of conventional data access agents, this system incorporates an emotion engine that recognizes user emotions. This allows for the optimal customization of data processing priorities and content based on the emotions expressed by the user.

[0712] The server receives data requests from users and parses the requested data type and format as usual. In addition, the sentiment engine analyzes the user's emotions based on their statements and written documents and determines their emotional state. By understanding the user's emotional state, such as whether they are feeling urgent or facing a specific problem, the server can dynamically change the priority of data provision.

[0713] Furthermore, the server can provide personalized support and recommendations as needed, based on the emotional data obtained by the emotion engine. For example, if the server determines that a user is experiencing stress, it can prioritize providing data and resources that can help reduce that stress. This personalized approach allows users to quickly obtain information that is relevant to their situation.

[0714] As a concrete example, when a user initiates an interaction, the server uses an emotion engine to analyze their emotions from the text message or voice message. If the emotion engine determines that the user is expressing dissatisfaction, the server prioritizes extracting information to resolve that dissatisfaction, converts the format, and responds quickly. At the same time, the server meticulously records this request and its processing results to help improve the service in the future.

[0715] As described above, the present invention, which includes an emotion engine, effectively improves the data access process between companies and AI agents, enabling personalized responses that are tailored to the user's situation and emotions.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] The server receives data requests from the user (AI agent). These requests include information about the type and format of the data required.

[0719] Step 2:

[0720] The server parses the received request and verifies the authentication information for the data request. At this point, it determines whether the user has the appropriate access rights.

[0721] Step 3:

[0722] The server uses an emotion engine to analyze the user's emotional state. Based on messages and voice data provided by the user, it identifies the emotion and evaluates the degree of dissatisfaction or urgency.

[0723] Step 4:

[0724] The server determines the priority of data delivery based on the user's emotional state obtained through sentiment analysis. If the request is urgent, data processing is given top priority.

[0725] Step 5:

[0726] The server selects the most efficient data extraction logic by referring to past extraction history and collects the necessary data from the company's information sources.

[0727] Step 6:

[0728] The server converts the extracted data into the format requested by the user. Filtering and data formatting are performed during this process.

[0729] Step 7:

[0730] The server quickly sends formatted data to the user. In particular, if the sentiment engine determines that the user is dissatisfied, it prioritizes providing information suitable for resolving the problem.

[0731] Step 8:

[0732] The server meticulously records each request and its processing result. This recorded information is later analyzed to improve the service.

[0733] (Example 2)

[0734] 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".

[0735] Information provision systems require flexible and efficient data access that responds to users' emotions and circumstances. However, conventional systems provide uniform data without considering user emotions, making it difficult to provide individualized support that meets user needs.

[0736] 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.

[0737] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format; means for analyzing the user's emotions using an emotion analysis engine and dynamically adjusting the priority of data provision based on the emotion data; and means for providing personalized support or recommendations based on the emotion data. This enables flexible and efficient data access that is tailored to the user's emotions and needs.

[0738] A "data request" is a request that a user sends to a system to obtain specific information or data.

[0739] "Data type" is an attribute that indicates the type of data, and includes formats such as text, numbers, and images.

[0740] A "format" is a type of data that defines its structure, and includes formats such as JSON and XML.

[0741] A "sentiment analysis engine" is a software component that analyzes a user's speech and text to identify their emotions and state.

[0742] "Personalized support" refers to a service that provides dedicated information and data tailored to the user's specific emotions and needs.

[0743] "Corporate information sources" refer to databases and information systems owned by a company, which function as sources from which data is extracted.

[0744] "Conversion" refers to the process of adapting extracted data to a format that meets the user's requirements.

[0745] "Recording" means saving each request and its processing results, and keeping them in a database for later analysis and reference.

[0746] This invention provides a system for efficiently and flexibly managing data access between a company's information sources and multiple artificial intelligence agents. This system incorporates an emotion analysis engine to recognize user emotions, thereby optimally customizing data processing priorities and content based on the emotions expressed by the user.

[0747] The server receives data requests from users and parses the requested data type and format. This parsing utilizes a network interface for data communication and a processor for data processing. The sentiment analysis engine analyzes text data contained in user statements and documents and determines the emotional state based on natural language processing techniques. This process uses a generative AI model to score and classify the user's emotions.

[0748] For example, if a user sends a request saying, "I'm in a hurry. I need the information now," the sentiment analysis engine will analyze the user's urgency, and based on the results, the server will prioritize processing this request. The server can also provide personalized support and recommendations that are appropriate to the user's emotions. For example, if the user is feeling stressed, it will provide information and resources that can help reduce stress.

[0749] An example of a prompt for a generative AI model might be, "Please tell me how to determine if a user is experiencing stress and how to optimize the service based on that emotion." This enables flexible data provision tailored to individual user needs.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1:

[0752] The server receives data requests from users and parses the requested data type and format. As input, it receives the request message sent by the user, parses it to identify the data type (e.g., text, number) and format (e.g., JSON, XML). As output, it stores the parsing results in an internal data structure and passes them on to subsequent processing. Specifically, the network module captures the request, and the parser extracts the data and format information.

[0753] Step 2:

[0754] The server activates an emotion analysis engine to analyze the emotions from the user's statements or written materials. It receives the user's text data as input and generates an emotion score using natural language processing. As output, it retrieves the analyzed emotion data (e.g., positive, negative, neutral) and saves it as the basis for prioritization. Specifically, a generative AI model performs emotion analysis on the text and outputs the scoring results.

[0755] Step 3:

[0756] The server dynamically adjusts the priority of data provision based on the acquired sentiment data. It takes the sentiment score generated in step 2 as input and uses this score to set the request priority. As output, it updates the request queue with the applied priority. Specifically, the prioritization algorithm evaluates the sentiment score and reorganizes the process queue.

[0757] Step 4:

[0758] The server generates and provides personalized support and recommendations to users based on sentiment data. It uses the user's sentiment score and past request history as input to select appropriate support information and recommendations. As output, it generates personalized content and adds it to the response data provided to the user. Specifically, the recommendation engine queries the corresponding database to extract the most suitable resources.

[0759] Step 5:

[0760] The server generates a response message to the user, converts it to a predetermined format, and then sends it to the user. It receives extracted data and individualized support information as input and constructs the message according to the requested format. As output, it sends the formatted data to the user and logs the request and processing results. Specifically, the formatter formats the message, and the transmitter sends it over the network.

[0761] (Application Example 2)

[0762] 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".

[0763] Traditional data access management systems, by providing requested data uniformly without considering user emotions, could potentially lead to decreased user satisfaction. Furthermore, their inability to respond flexibly to user situations and emotions often resulted in a lack of prompt responses, especially in situations requiring immediate attention. This highlighted the challenge of improving the customer experience in corporate customer service.

[0764] 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.

[0765] In this invention, the server includes means for receiving data requests and analyzing the requested data type and format, means for analyzing data sent from the user and determining the emotional state, and means for changing the priority of data provision based on the determined emotional state. This enables rapid and personalized data provision and support in response to the user's emotions.

[0766] A "means for receiving data requests" is a mechanism for receiving information requests sent from an external source and for initially recognizing their contents.

[0767] "Means for parsing data type and format" refers to a function for understanding the type and format described in a received data request and determining appropriate processing.

[0768] "Means of verifying authentication and authorization" are mechanisms that are responsible for verifying whether an incoming request is legitimate and determining whether it is from an authorized user.

[0769] "Methods for optimizing data extraction logic" refer to functions that analyze past usage history and select the optimal extraction method in order to improve the efficiency of data retrieval.

[0770] "Means of extracting data from information sources" refers to the process of retrieving necessary information from a company's database or other information sources.

[0771] "Means of converting to the requested format" refers to the technology used to reconstruct extracted data into a format specified by the user.

[0772] "Means for transmitting converted data" refers to means that enable the delivery of format-converted information to the requester.

[0773] "Means for recording requests and their processing results" refers to a mechanism for saving a history of data requests and their responses.

[0774] "A means of analyzing user-generated data and determining emotional state" refers to an engine that analyzes text and audio provided by users to determine their psychological state.

[0775] "A means of changing the priority of data provision based on emotional state" refers to a function that dynamically adjusts which information is prioritized based on the user's emotions.

[0776] "Means of providing personalized support" refers to the process of providing assistance that is customized to the user's specific needs and emotional state.

[0777] The system to realize this application utilizes smartphones and servers as its main hardware. When the server receives a data request sent by the user, it parses the requested data type and format and verifies the user's authentication and authorization. Next, it extracts the necessary data from the company's information source and converts the extracted data into the requested format.

[0778] Furthermore, this system uses an emotion engine to analyze the user's emotional state from their outgoing data. The emotion engine uses natural language processing techniques (e.g., Google Cloud Natural Language API) to analyze the user's text and voice and determine their emotional state. Based on the resulting emotional data, data provision priorities are dynamically adjusted, providing personalized support and recommendations.

[0779] The server also uses AI models (e.g., OpenAI GPT-3) to generate responses based on user interaction. These responses are tailored to the user's state and provide immediate assistance as needed.

[0780] To give a specific example, if a user connects to customer support using their smartphone and expresses dissatisfaction that their order hasn't arrived yet, the system analyzes this information. The emotion engine identifies the emotion of dissatisfaction and provides information to quickly resolve the issue. It also sends a prompt to the generative AI model saying, "It appears the user is dissatisfied with their order. As a response, generate a message that will calm the customer and indicate prompt action to resolve the problem," and generates an appropriate response.

[0781] Thus, the present invention embodies a system that provides advanced personalized data access and support based on user emotions, thereby improving the customer experience.

[0782] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0783] Step 1:

[0784] The server receives data requests from users. At this time, the user provides text messages or voice data as input. The server retrieves this data and performs preprocessing to extract information about the requested data type and format.

[0785] Step 2:

[0786] The server verifies user authentication and authorization before accessing the information source. This step requires a user ID or authentication token as input. The server checks the database to confirm that the request is legitimate and proceeds with data extraction only if permitted.

[0787] Step 3:

[0788] The server activates the emotion engine and analyzes the user's transmitted data. Text messages and voice data are provided as input, and the emotional state (e.g., dissatisfaction, relief, urgency) is analyzed as output. The emotion engine uses natural language processing techniques to extract emotional characteristics and passes the results to the next step.

[0789] Step 4:

[0790] The server dynamically adjusts the priority of data provision based on the analyzed emotional states. It receives the analyzed emotional states as input and generates a prioritized data sequence as output. In this process, it is configured to prioritize responses for emotions of high urgency.

[0791] Step 5:

[0792] The server extracts data from corporate sources and converts it to the requested format. Here, a prioritized list of data is used as input, and formatted data is generated as output. Information collection and transformation are performed using efficient database queries and formatting algorithms.

[0793] Step 6:

[0794] The terminal sends the converted data to the user. The input is formatted data, and the output includes the display for the user. The terminal receives the data to display and provides the information in the most appropriate way for the user's device.

[0795] Step 7:

[0796] The server uses an AI model to generate responses tailored to the user's emotional state. The user's emotional state and related data are provided as input, and a customized message is generated as output. The generating AI model uses prompts to create flexible and appropriate responses.

[0797] Step 8:

[0798] The server records all requests and their processing results. Processed request data is provided as input, and logs are stored in the database as output. These logs are useful for future system improvements and troubleshooting.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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."

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] The following is further disclosed regarding the embodiments described above.

[0821] (Claim 1)

[0822] A means for receiving a data request and parsing the requested data type and format,

[0823] Means for verifying the authentication and authorization of received requests,

[0824] A means to optimize the data extraction logic based on past extraction history,

[0825] Methods for extracting data from corporate information sources,

[0826] A means of converting the extracted data into the requested format,

[0827] A means for sending the converted data to the requester,

[0828] A means for recording each request and its processing result,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, further comprising means for determining the permission status of a request by access control.

[0832] (Claim 3)

[0833] The system according to claim 1, further comprising means for utilizing a cache for optimized data extraction.

[0834] "Example 1"

[0835] (Claim 1)

[0836] A means for receiving a data request and parsing the requested data attributes and format,

[0837] A means of verifying the authentication and authorization information of the received request,

[0838] A means for optimizing information extraction processing based on past extraction history,

[0839] Means for extracting information from an organization's sources,

[0840] A means of converting the extracted information into the requested format,

[0841] A means for sending the converted information to the requester,

[0842] Means for recording each request and its processing results in detail,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, further comprising means for determining the permission status of a request by constraint control.

[0846] (Claim 3)

[0847] The system according to claim 1, further comprising means for utilizing temporary storage for optimized information extraction.

[0848] "Application Example 1"

[0849] (Claim 1)

[0850] A means for receiving a data request and analyzing the type and format of the requested information,

[0851] Means for verifying the authentication and authorization of received requests,

[0852] A means to optimize the principle of information extraction based on past extraction history,

[0853] Methods for extracting information from a company's database,

[0854] A means of converting the extracted information into the requested format,

[0855] A means for sending the converted information to the requester,

[0856] A means for recording each request and its processing result,

[0857] When extracting information, a means for users to efficiently access data using portable devices,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, further comprising means for determining the permission status of a request by access control.

[0861] (Claim 3)

[0862] The system according to claim 1, further comprising means for using a recording device for optimized information extraction.

[0863] "Example 2 of combining an emotion engine"

[0864] (Claim 1)

[0865] A means for receiving a data request and parsing the requested data type and format,

[0866] Means for verifying the authentication and authorization of received requests,

[0867] A means for analyzing a user's emotions using an emotion analysis engine and dynamically adjusting the priority of data provision based on that emotion data,

[0868] Means of providing personalized support or recommendations based on emotional data,

[0869] Methods for extracting data from corporate information sources,

[0870] A means of converting the extracted data into the requested format,

[0871] A means for sending the converted data to the requester,

[0872] A means for recording each request and its processing result,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, further comprising means for determining the permission status of a request by access control.

[0876] (Claim 3)

[0877] The system according to claim 1, further comprising means for utilizing a cache for optimized data extraction.

[0878] "Application example 2 when combining with an emotional engine"

[0879] (Claim 1)

[0880] A means for receiving a data request and parsing the requested data type and format,

[0881] Means for verifying the authentication and authorization of received requests,

[0882] A means to optimize the data extraction logic based on past extraction history,

[0883] Methods for extracting data from corporate information sources,

[0884] A means of converting the extracted data into the requested format,

[0885] A means for sending the converted data to the requester,

[0886] A means for recording each request and its processing result,

[0887] A means of analyzing user-generated data to determine emotional state,

[0888] A means of changing the priority of data provision based on the determined emotional state,

[0889] Means of providing individualized support according to emotional state,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, further comprising means for determining the permission status of a request by access control.

[0893] (Claim 3)

[0894] The system according to claim 1, further comprising means for utilizing a cache for optimized data extraction. [Explanation of symbols]

[0895] 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. A means for receiving a data request and parsing the requested data type and format, Means for verifying the authentication and authorization of received requests, A means to optimize the data extraction logic based on past extraction history, Methods for extracting data from corporate information sources, A means of converting the extracted data into the requested format, A means for sending the converted data to the requester, A means for recording each request and its processing result, A system that includes this.

2. The system according to claim 1, further comprising means for determining the permission status of a request by access control.

3. The system according to claim 1, further comprising means for utilizing a cache for optimized data extraction.

Images