System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving information input from a user; means for acquiring related data from a database based on the received information; means for analyzing the acquired data using a generative model; means for generating a strategy based on an analysis result; and means for providing the generated strategy to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] For modern sports teams, data-based strategy planning and player scouting are becoming increasingly important. However, current methods often involve manual data collection and analysis, making it difficult to efficiently obtain the necessary information. Furthermore, there is a lack of tools that can respond quickly and flexibly to situations such as games and training, where quick decisions are required. The present invention aims to solve these problems and provide a system that enables sports teams to quickly and effectively plan data-based strategies. [Means for solving the problem]

[0005] The present invention is a system including a means for receiving information input by a user, a means for retrieving related data from a database based on the received information, a means for analyzing the retrieved data using a generative model, a means for generating a strategy based on the analysis results, and a means for providing the generated strategy to the user. In particular, the generative model utilizes a machine learning algorithm and has a function for interacting with the user using a chatbot, enabling rapid and flexible data-based strategy planning.

[0006] "Means for receiving information input from a user" refers to an interface or function that allows a user to input information into the system and receive that input.

[0007] "Means for obtaining related data from a database based on received information" refers to a process or function for searching and obtaining related data from a database based on received user information.

[0008] "Means of analyzing acquired data using a generative model" refers to the processing or functionality for analyzing data using a generative model (especially a model using a machine learning algorithm) based on information acquired from a database.

[0009] "Means for generating a strategy based on the analysis results" refers to the processing or function for automatically generating appropriate strategies or proposals based on the analysis results of the generative model.

[0010] "Means for providing generated strategies to the user" refers to an output interface or function for communicating and displaying generated strategies and suggestions to the user.

[0011] "The generative model uses a machine learning algorithm" means that the generative model that performs data analysis utilizes a machine learning algorithm.

[0012] "Interacting with a user using a chatbot" refers to receiving input from a user and generating and providing a response using an interactive interface called a chatbot. [Brief explanation of the drawings]

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

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

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

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

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

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

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

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

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

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

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

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0034] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. Specific embodiments of this system will be described below.

[0035] System Overview:

[0036] This system includes a series of processes: input of information from users, acquisition of related data from a database, data analysis using a generative model, strategy generation, and provision of the generated strategy. The system has three main components: a server, a terminal, and a user.

[0037] What the program does:

[0038] Data Entry:

[0039] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot provides an intuitive user interface and enables quick data entry.

[0040] Data reception:

[0041] The terminal receives input from the user and sends it to the server. The input data is sent to the server in a standardized format (e.g., JSON).

[0042] Data Acquisition:

[0043] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[0044] Data Analysis:

[0045] The server inputs the acquired information into a generative model to analyze optimal player selection and strategy. The generative model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation.

[0046] Strategy Generation:

[0047] The server generates specific strategy proposals based on the analysis results obtained from the generative model, for example, by proposing a strategy in the form of "It would be optimal to use pitcher Matsuda in the next game."

[0048] Strategy provided:

[0049] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0050] Examples:

[0051] scenario:

[0052] Ask the system which pitcher to use in the next game.

[0053] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[0054] 2. The device receives the user's input and sends it to the server in a standardized format (JSON).

[0055] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[0056] 4. The server analyzes this data using a generative model to identify the best pitcher.

[0057] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game."

[0058] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[0059] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[0060] As described above, the system of the present invention can analyze data based on user input and provide instant and flexible strategy proposals, enabling sports teams to quickly and effectively develop tactics and improve their chances of winning a game.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[0064] Step 2:

[0065] The terminal receives input data from the user. The received data is converted into JSON format and then sent to the server. For example, the converted data will be in the format "{"query": "Which pitcher is best for the next game?"".

[0066] Step 3:

[0067] The server receives the JSON data sent from the device, parses the received data, extracts the necessary information, and then begins preparations to access the database.

[0068] Step 4:

[0069] The server queries the database to retrieve relevant data, specifically the performance data for the team's pitchers over the past 10 games and the most recent performance data for the opposing batters.

[0070] Step 5:

[0071] The server preprocesses the acquired data, including standardizing, normalizing, and imputing missing values, so that the data is ready to be input to the generative model.

[0072] Step 6:

[0073] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and current situation.

[0074] Step 7:

[0075] The generative model analyzes the data and sends the results back to the server, such as "Pitcher Matsuda is the best for the next game."

[0076] Step 8:

[0077] The server receives the results from the generative model and generates a strategy proposal based on the analysis results. The strategy proposal is a specific statement such as, "It would be best to use pitcher Matsuda in the next game."

[0078] Step 9:

[0079] The server formats the generated strategy proposal in JSON format and sends it to the device, for example, "{"recommendation": "It is best to use pitcher Matsuda in the next game"}".

[0080] Step 10:

[0081] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and then displays the strategy proposal on the user interface.

[0082] Step 11:

[0083] The user checks the strategy suggestion displayed on the device screen, saying, "It is best to use pitcher Matsuda in the next game." Based on this information, the user decides which pitcher to use in the next game.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] There is a growing need for a system that can quickly and effectively analyze data and propose optimal strategies in the strategic planning and scouting of sports teams. Conventional methods require the time-consuming task of collecting and analyzing data individually, making it difficult to plan strategies efficiently. The objective of this invention is to provide a system that can be intuitively used by users and that centrally performs everything from data analysis to strategy proposals.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes: [terminal means for receiving information input by a user; [means for transmitting the information received by the terminal to the server in a standardized format; [means for acquiring related data from a database based on the information received by the server; [means for performing analysis using a generative model with the acquired data by the server; [means for the server to generate a strategy based on the analysis results; and [means for providing the generated strategy to the user via the terminal.] This enables the user to easily input the necessary information and quickly acquire a strategy based on the analysis results.

[0089] A "user" is an entity that uses the system to input information and receives strategies provided as analysis results.

[0090] A "terminal" is a device that receives information from a user and transmits it to a server. Examples include PCs, smartphones, and tablets.

[0091] The "server" is a computer system that retrieves relevant data from a database based on received information, analyzes the data using a generative model, and generates and provides a strategy.

[0092] A "database" is a system that stores related information and provides data in response to queries from a server.

[0093] A "generative model" is a model that uses machine learning algorithms to analyze data and identify optimal strategies.

[0094] A "chatbot" is an interface for collecting information through dialogue with users and sending it to a system.

[0095] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate analytical results.

[0096] A "prompt sentence" is an input sentence given to a generative AI model, and is the basic information that the model uses for analysis.

[0097] A "standardized format" is a format in which information is structured according to certain rules and is primarily used for exchanging data between systems. Examples include the JSON format.

[0098] A "strategy" is a specific action plan proposed based on the results of analysis by the generative model.

[0099] The "analysis result" is the final output of the analysis performed by the generative model based on the input data.

[0100] The present invention relates to a data analysis system for supporting strategic planning and scouting for sports teams. Specific embodiments of this system will be described below.

[0101] The system's main components are a user, a device, and a server. The user inputs information into the system via a chatbot. The device receives the information and sends it to the server in a standardized format (e.g., JSON). The server then retrieves relevant data from a database based on the information and performs data analysis using a generative AI model. Based on the analysis results, the server generates a strategy and provides it to the user via the device.

[0102] Hardware and software used

[0103] Server: A high-performance server for performing data analysis and strategy generation (e.g., Amazon Web Services, Google Cloud Platform)

[0104] Terminal: The device on which the user enters input and confirms strategic proposals (e.g., PC, smartphone, tablet)

[0105] Chatbot interface: Tools that allow users to input information intuitively (e.g., Dialogflow, Microsoft Bot Framework)

[0106] Generative AI models: Machine learning models for data analysis (e.g., TensorFlow, PyTorch)

[0107] Operation flow

[0108] 1. A user inputs a query such as "Which pitcher should be used in the next game?" in natural language via a chatbot. For example, a user opens the chatbot's user interface from a smartphone or PC browser, inputs a query in the text field, and presses the send button.

[0109] 2. The terminal receives input from the user and converts the data into a standardized format (JSON). The terminal parses the user's input text and converts it into JSON format such as { "query": "Which pitcher should be used in the next game?"}

[0110] 3. The device sends the converted data to the server. The device sends the JSON data via the network as a POST request to a specific API endpoint on the server.

[0111] 4. The server receives the data sent from the device. The server's API receives the request and extracts the JSON data from the request body.

[0112] 5. The server retrieves the necessary relevant information from the database based on the received data. The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[0113] 6. The server inputs the acquired data into a generative AI model for data analysis. The server invokes a machine learning model (e.g., TensorFlow) and passes the performance data as input to the model. The model performs the analysis and identifies the optimal pitcher.

[0114] 7. The server generates a specific strategy proposal based on the analysis results obtained from the generative AI model. The server applies the analysis results (e.g., pitcher's name) to a template for expressing them in natural language, and generates a sentence such as, "It is best to use pitcher Matsuda in the next game."

[0115] 8. The server sends the generated strategy proposal to the terminal. The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[0116] 9. The terminal displays the strategy proposal received from the server to the user. The terminal extracts the strategy proposal from the response body and displays the proposal on the chatbot's UI.

[0117] 10. The user checks the strategy suggestions displayed on the device screen and makes a decision based on them. The user reads the suggestions displayed on the chatbot screen and decides on the pitcher for the next game.

[0118] Examples of prompt statements

[0119] "Which pitcher should we use in the next game?

[0120] Analyze the optimal pitcher based on past performance and the performance of opposing batters, and propose a specific strategy.

[0121] In this way, this system can quickly and effectively analyze data and propose optimal strategies to sports teams, significantly improving the efficiency of strategic planning and scouting for sports teams.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] A user accesses the system and inputs the query "Which pitcher should be used in the next game?" in natural language through the chatbot.

[0125] Input: The user enters a query into the chatbot's input field and presses the submit button.

[0126] Output: A query in natural language form is generated.

[0127] Specific operation: The user opens the chatbot screen in a smartphone or PC browser, enters "Which pitcher should be used in the next game?" in the text field, and presses the send button.

[0128] Step 2:

[0129] The terminal receives input from the user and converts the information into a standardized format (JSON).

[0130] Input: The natural language query entered by the user.

[0131] Output: Data in a standardized format (e.g. JSON).

[0132] Specific operation: The device parses the user's input text and converts it into JSON format, such as { "query": "Which pitcher should be used in the next game?"}.

[0133] Step 3:

[0134] The terminal transmits the converted data to the server.

[0135] Input: A query expressed in a standardized format (JSON).

[0136] Output: A POST request to the server.

[0137] Specific operation: The terminal sends JSON data via the network as a POST request to a specific API endpoint on the server.

[0138] Step 4:

[0139] The server receives the data sent from the terminal.

[0140] Input: JSON format data sent from the terminal.

[0141] Output: Internal data structure that parses the received JSON data.

[0142] Specific operation: The server API receives the request and extracts the JSON data from the request body.

[0143] Step 5:

[0144] The server retrieves the necessary relevant information from a database based on the received data.

[0145] Input: User query in JSON format.

[0146] Output: Relevant database entries (e.g. pitcher's past performance, opponent's performance).

[0147] Specific operation: The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[0148] Step 6:

[0149] The server inputs the acquired data into a generative AI model and performs data analysis.

[0150] Input: Relevant data retrieved from the database.

[0151] Output: Analysis results from the generative model (e.g., optimal pitcher).

[0152] How it works: The server calls a machine learning model (e.g., TensorFlow) and passes the acquired performance data as input to the model. The model then performs analysis and identifies the best pitcher.

[0153] Step 7:

[0154] The server generates specific strategy proposals based on the analysis results obtained from the generative AI model.

[0155] Input: Analysis results from the generative AI model.

[0156] Output: Strategy suggestions in natural language format.

[0157] Specific operation: The server applies the model output (e.g., the pitcher's name) to a template for expressing it in natural language, and generates the sentence, "It would be best to use pitcher Matsuda in the next game."

[0158] Step 8:

[0159] The server transmits the generated strategy proposal to the terminal.

[0160] Input: A strategy proposal expressed in natural language.

[0161] Output: JSON data containing the strategy proposal as a response to the terminal.

[0162] Specific operation: The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[0163] Step 9:

[0164] The terminal displays the strategy proposal received from the server to the user.

[0165] Input: JSON data sent from the server.

[0166] Output: Strategy proposals displayed on the user interface.

[0167] Specific operation: The terminal extracts strategy proposals from the response body and displays them on the chatbot's UI.

[0168] Step 10:

[0169] The user checks the strategy proposals displayed on the terminal screen and makes a decision based on them.

[0170] Input: Strategy proposals displayed on the terminal screen.

[0171] Output: Deciding which pitcher to use in the next game.

[0172] Specific operation: The user confirms the strategy suggestion displayed on the chatbot screen, "It would be best to use pitcher Matsuda in the next game," and decides to pitch Matsuda for the next game.

[0173] (Application example 1)

[0174] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0175] Planning maintenance for industrial equipment and optimizing production lines are important issues for efficient factory operation. However, manually managing the operating status and past maintenance records of each piece of equipment and performing maintenance at the appropriate time is difficult, increasing the risk of equipment failure and production loss. Therefore, there is a need for efficient strategy proposals based on the analysis of real-time data.

[0176] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0177] In this invention, the server includes: [means for receiving information input by a user;] [means for acquiring related data from a database based on the received information;] [means for analyzing the acquired data using a generative model;] [means for generating a strategy based on the analysis results;] [means for providing the generated strategy to the user;] [means for acquiring the operating status and maintenance records of industrial equipment; and [means for making maintenance predictions for industrial equipment using a machine learning algorithm.] This makes it possible to efficiently manage the operating status and past maintenance records of each piece of equipment and predict the appropriate timing for maintenance.

[0178] A "user" is a person or organization that operates the system and provides input information.

[0179] "Information" means data or requests provided by a user to a server.

[0180] A "database" is a collection of data that stores and manages related information in an organized manner.

[0181] A "generative model" is a system that uses machine learning algorithms to analyze input data and generate a specific output.

[0182] "Analysis" is the process of examining data in detail and drawing specific conclusions or strategies.

[0183] A "strategy" is a plan or policy for achieving a specific objective.

[0184] "Providing" is the act of presenting the generated strategies and information to the user.

[0185] "Industrial equipment" refers to machinery and equipment used within a factory.

[0186] "Operation status" refers to information that indicates the operating state and efficiency of industrial equipment.

[0187] "Maintenance records" refer to the past maintenance history of industrial equipment.

[0188] A "machine learning algorithm" is a computer algorithm that learns patterns and trends from large amounts of data and makes predictions and classifications.

[0189] "Maintenance prediction" is the process of using machine learning algorithms to predict when future maintenance will be required.

[0190] The present invention relates to a data analysis system for supporting maintenance planning and optimization of production lines in industrial facilities. Specific embodiments of this system will be described below.

[0191] System Overview:

[0192] This system has three main components: the user, the server, and the terminal, and includes a series of processes that cover everything from data input to maintenance prediction, strategy generation, and strategy provision. The main processes are information input from the user, data analysis on the server, and provision of the analysis results.

[0193] Hardware and software:

[0194] Server: A server for database management and running machine learning model analysis (e.g., AWS EC2 instance).

[0195] Device: A smartphone or tablet where users can enter information and check strategic proposals.

[0196] Industrial robots: Robots used in factories for data collection and interfacing (e.g., Pepper).

[0197] What the program does:

[0198] Data Entry:

[0199] Users access the system via a chatbot and input the necessary information, for example, to inquire about the next machine that needs maintenance. An intuitive user interface is provided, allowing for quick data entry.

[0200] Data reception:

[0201] The terminal receives input from the user and sends it to the server in a standardized format (e.g., JSON).

[0202] Data Acquisition:

[0203] When the server receives the data sent by the user, it retrieves related information from the database based on that information, such as the operating status of industrial equipment and past maintenance records.

[0204] Data Analysis:

[0205] The server inputs the acquired information into a generative model and analyzes the optimal maintenance targets and production line optimization. The generative model uses a machine learning algorithm (e.g., Random Forest Classifier) ​​to perform highly accurate analysis based on past data and the current situation.

[0206] Strategy Generation:

[0207] The server generates specific strategy proposals based on the analysis results obtained from the generative model. For example, it generates a strategy in the form of "Unit A is the next unit to undergo maintenance."

[0208] Strategy provided:

[0209] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0210] Examples:

[0211] For example, consider a case where a user types into a chatbot, "Please tell me which machine should be maintained next." The system analyzes past maintenance records and operation data and responds, "The next machine that needs maintenance is Unit A."

[0212] Example prompt sentence:

[0213] "Please tell me which machines will undergo the next maintenance. Machine A has 5,000 operating hours, 30 days before its last maintenance, and an error rate of 5%. Machine B has 3,000 operating hours, 15 days before its last maintenance, and an error rate of 3%. Machine C has 6,000 operating hours, 60 days before its last maintenance, and an error rate of 10%."

[0214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0215] Step 1:

[0216] The user accesses the chatbot using a terminal and inputs a question such as, "Please tell me which machine should be maintained next." The input data is in text format, and this question is registered in the system.

[0217] Input: User inquiry about the machine to be maintained

[0218] Output: Send a query to the chatbot

[0219] Step 2:

[0220] The terminal receives user input, converts it into a standardized format (JSON), and sends it to the server.

[0221] Input: User text input

[0222] Output: Standardized query data (JSON)

[0223] Step 3:

[0224] The server analyzes the received query data and retrieves the operating status and past maintenance records of the industrial equipment from the relevant database.

[0225] Input: Standardized query data (JSON)

[0226] Output: Operation status and maintenance records of industrial equipment

[0227] Step 4:

[0228] The server inputs the acquired data into a machine learning algorithm (generative model) to make maintenance predictions. Specifically, it identifies the equipment that next requires maintenance using information such as the operating hours, last maintenance date, and error rate for each piece of equipment.

[0229] Input: Operation status and maintenance record data

[0230] Output: Prediction of optimal machine maintenance targets

[0231] Step 5:

[0232] The server generates specific maintenance strategy proposals based on the analysis results obtained from the generative model, and expresses the conclusion in text form, such as "Unit A should be the next to undergo maintenance."

[0233] Input: Maintenance forecast results

[0234] Output: Strategy proposal (text format)

[0235] Step 6:

[0236] The server converts the generated strategy proposal into a standardized format (JSON) and sends it to the terminal.

[0237] Input: Strategy proposal (text format)

[0238] Output: Standardized strategy data (JSON)

[0239] Step 7:

[0240] The terminal analyzes the strategy data received from the server and displays strategy proposals to the user, who then checks the maintenance strategy on the terminal screen and makes decisions based on it.

[0241] Input: Standardized strategy data (JSON)

[0242] Output: Strategy proposals displayed to the user

[0243] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0244] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. In particular, by combining it with an emotion engine that recognizes the user's emotions, more effective strategy proposals can be realized. Specific embodiments of this system are described below.

[0245] System Overview:

[0246] This system encompasses a series of processes: inputting information from the user, retrieving relevant data from a database, analyzing the data using a generative model, generating a strategy, and providing the generated strategy. Furthermore, it uses an emotion engine to recognize the user's emotions and adjusts the strategy analysis based on the results. The system has three main components: a server, a terminal, and a user.

[0247] What the program does:

[0248] Data Entry:

[0249] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot responds intuitively to the user's input, and the emotion engine reads emotions from the input.

[0250] Data reception:

[0251] The device receives input data from the user and sends it to the server in a standardized format (e.g., JSON), including the user's emotional data recognized by the emotion engine.

[0252] Data Acquisition:

[0253] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[0254] Data Analysis:

[0255] The server inputs the acquired information into a generative model and analyzes the optimal player selection and strategy. The generative model uses a machine learning algorithm to perform highly accurate analysis based on past data and the current situation. It also adjusts the strategic analysis so that the analysis results from the emotion engine have an impact.

[0256] Strategy Generation:

[0257] The server generates specific strategy proposals based on the analysis results obtained from the generative model. The generated strategy proposals are written in the form of "It would be best to use pitcher Matsuda in the next game." The server also makes proposals that take the user's emotions into consideration.

[0258] Strategy provided:

[0259] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0260] Examples:

[0261] scenario:

[0262] Ask the system which pitcher to use in the next game.

[0263] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[0264] 2. The device receives the user's input and sends it to the server in a standardized format (JSON), including the user's emotion as recognized by the emotion engine.

[0265] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[0266] 4. The server analyzes this data using a generative model and identifies the best pitcher based on the results of the emotion engine.

[0267] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game." If the user is feeling nervous, the server adds a message that gives the user a sense of relief, such as, "Don't worry, use pitcher Matsuda."

[0268] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[0269] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[0270] As described above, the system of the present invention combines user input with analysis by the emotion engine to provide fast, flexible, and data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[0271] The processing flow will be explained below.

[0272] Step 1:

[0273] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[0274] Step 2:

[0275] The device receives input data from the user and converts it into JSON format. For example, the converted data will be in the format of "{"query": "Which pitcher is best for the next game?"". The emotion engine also identifies the user's emotion from the user's facial expression and input text, and sends the emotion data to the server.

[0276] Step 3:

[0277] The server receives the JSON data and emotion data sent from the device, analyzes the received data, extracts the necessary information, and then prepares to access the database.

[0278] Step 4:

[0279] The server queries the database based on the received information to retrieve relevant data, specifically the performance data of the team's pitcher from the past 10 games and the most recent performance data of the opposing team's batters.

[0280] Step 5:

[0281] The server preprocesses the acquired data, which includes standardizing, normalizing, and imputing missing values, etc. This process prepares the data for input into the generative model.

[0282] Step 6:

[0283] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and the current situation. Additionally, the extracted emotional data is also input into the model, influencing the analysis.

[0284] Step 7:

[0285] The generative model analyzes the data and sends the results back to the server, such as whether pitcher Matsuda is the best for the next game.

[0286] Step 8:

[0287] The server generates a strategy proposal based on the analysis results obtained from the generative model. The generated strategy proposal is expressed in the form of "It is best to use pitcher Matsuda in the next game." In addition, an additional message (e.g., "Please feel free to use pitcher Matsuda") is generated based on the emotion data to give the user a sense of security.

[0288] Step 9:

[0289] The server formats the generated strategy proposal in JSON format and sends it to the terminal. For example, it may have the format "{"recommendation": "It is best to use pitcher Matsuda in the next game", "additionalMessage": "Please feel free to use pitcher Matsuda"}".

[0290] Step 10:

[0291] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and displays strategy suggestions and additional messages on the user interface.

[0292] Step 11:

[0293] The user checks the strategy suggestion displayed on the device screen, "It is best to use pitcher Matsuda in the next game," along with the additional message, "Please feel free to use pitcher Matsuda." Based on this information, the user decides which pitcher to use in the next game.

[0294] Example 2

[0295] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0296] Conventional strategic planning and scouting systems for sports teams are unable to propose strategies that take user emotions into account, making it difficult to improve the user experience or increase the adoption rate of strategies. Furthermore, the lack of an intuitive interface for dialogue using chatbots can sometimes reduce the accuracy and efficiency of user input. To solve these problems, it is important to recognize user emotions and reflect them in strategic planning.

[0297] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0298] In this invention, the server includes: [means for receiving information input by a user and recognizing emotions using an emotion engine]; [means for retrieving relevant data from a database based on the received information and emotions]; and [means for analyzing the retrieved data and emotions using a generative AI model]. This makes it possible [to quickly provide more accurate strategy proposals while taking into account the user's emotions].

[0299] A "user" is an entity that accesses the system, inputs information, and receives strategic proposals.

[0300] "Input information" is text data that the user provides to the system, including questions and instructions such as which players should be used in the next game.

[0301] An "emotion engine" is software or an algorithm that analyzes information input by a user and recognizes the user's emotions (e.g., tension, anxiety, joy, etc.) based on that information.

[0302] The "database" is a system for storing and managing user-input information and related data based on emotions (for example, players' past performances and opponent data).

[0303] "Related data" refers to information necessary for strategy planning (for example, player performance data and information on the opposing team) that is acquired from a database based on user input.

[0304] A "generative AI model" is a model that uses machine learning algorithms to analyze input data and related data and generate optimal strategic proposals.

[0305] "Analysis" is the process of deriving the optimal strategy based on data obtained using a generative AI model and user emotional data.

[0306] A "strategy" is a specific player selection and tactical policy for the next match proposed based on the results of analysis by the generative AI model.

[0307] "Providing" refers to the act of transmitting the generated strategy from the server to the user via the terminal, and allowing the user to confirm and make a decision.

[0308] A "chatbot" is software that automatically interacts between a user and a system, and is an interface that accepts user input and returns appropriate responses.

[0309] The present invention is a data analysis system for supporting strategic planning and scouting in sports teams, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose more effective strategies. Specific embodiments of this system are described below.

[0310] Overall system configuration

[0311] This system is mainly composed of three components: a server, a terminal, and a user. The server is responsible for accessing the database, analyzing data using a generative AI model, and generating strategies. The terminal receives information input from the user and displays the analysis results and proposals. The user mainly operates the terminal to input information and receive strategy proposals from the system.

[0312] Hardware and software used

[0313] The server is equipped with a high-performance processor and large amounts of memory and storage. Specifically, cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used. MySQL and PostgreSQL are commonly used as databases.

[0314] Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Furthermore, advanced generative models such as OpenAI's GPT-3 are adopted for natural language processing. Sentiment analysis APIs from Microsoft's Azure Cognitive Services can be used as emotion engines.

[0315] What the program does

[0316] User input of information

[0317] Users access the system and use the chatbot to input specific questions, such as which pitcher should be used in the next game. The device receives the user's input and uses an emotion engine to recognize the user's emotions.

[0318] Receiving and processing input data

[0319] The device receives the question and emotion data entered by the user and sends it to the server in a standardized format (e.g., JSON). When the server receives this data, it retrieves related data from a database. For example, if the user enters "Which pitcher should we use in the next game?", the server retrieves the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[0320] Data analysis and strategy generation

[0321] The server inputs the acquired information into a generative AI model, which analyzes the optimal player selection and strategy. The generative AI model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation. It also takes into account the results of the emotion engine and reflects this in its strategic analysis. Based on the analysis results, it generates specific strategy suggestions, such as "It is best to use a specific pitcher in the next game."

[0322] Providing strategic proposals

[0323] The server sends the generated strategy proposal to the terminal, which displays it to the user, who then checks the generated strategy on the terminal and decides on a pitcher for the next game based on it.

[0324] Specific examples

[0325] An example of a prompt is:

[0326] In response to the question, "Which pitcher should we use in the next game?", the system analyzes the situation and makes strategic suggestions such as, "It would be best to use a specific pitcher in the next game. You may be nervous, but rest assured considering their track record."

[0327] In this way, the system of the present invention can combine user input with analysis by the emotion engine to quickly and flexibly provide data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[0328] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0329] Step 1:

[0330] Users access the system using a web browser or mobile app. They input a specific question in natural language into the chatbot interface, such as "Which pitcher should be used in the next game?" The emotion engine then analyzes the user's input and identifies emotions such as "I'm nervous."

[0331] Input: User's question (in text format)

[0332] Output: User's question and emotion data (text format and emotion labels)

[0333] Step 2:

[0334] The device receives questions and emotion data entered by the user, converts this data into a standardized format (e.g., JSON format), and sends it to the server.

[0335] Input: User question and emotion data (text format and emotion labels)

[0336] Output: Standardized data (JSON format)

[0337] Step 3:

[0338] The server receives the JSON data sent from the device, parses it, and sends a query to the database. The query contains information related to the user's question (e.g., the past performance of the team's pitcher, the performance of the opposing team's batters).

[0339] Input: Standardized data (JSON format)

[0340] Output: A list of database queries and the associated data retrieved.

[0341] Step 4:

[0342] The server retrieves relevant information from a database, including the past performance of the team's pitchers and the performance of the opposing batters, and stores the retrieved data temporarily for use in the next analysis step.

[0343] Input: Database query

[0344] Output: Related data (e.g., pitcher's past performance, batter's performance)

[0345] Step 5:

[0346] The server inputs the acquired relevant data into the generative AI model and begins analysis. The generative AI model analyzes the data using machine learning algorithms (e.g., TensorFlow or PyTorch) and proposes optimal player selection. It also incorporates the results of the emotion engine into the analysis and makes adjustments based on emotions.

[0347] Input: Related data (e.g., pitcher's past performance, batter's performance) and emotion data

[0348] Output: Analysis results (e.g., optimal pitcher suggestions)

[0349] Step 6:

[0350] The server generates specific strategy suggestions based on the analysis results obtained from the generative AI model. For example, it generates a strategy statement such as, "It is best to use a specific pitcher in the next game." The message is also adjusted to reflect the user's emotions.

[0351] Input: Analysis results (e.g., optimal pitcher suggestions)

[0352] Output: Strategy proposal (strategy statement in text format)

[0353] Step 7:

[0354] The server sends the generated strategy proposal to the terminal, which displays the proposal to the user. The user checks the proposed strategy on the terminal and decides on a pitcher for the next game based on the information.

[0355] Input: Strategy proposal (strategy statement in text format)

[0356] Output: Providing strategies to the user (strategy suggestions displayed on the device screen)

[0357] (Application example 2)

[0358] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0359] In today's market, users' shopping experiences are becoming increasingly diverse, and they are seeking personalized recommendations tailored to their individual needs. However, systems that adequately meet these demands are still limited. Furthermore, technology for generating appropriate product recommendations and messages based on users' emotions has not been fully established. Therefore, there is a need to reduce the stress and difficulties users experience when shopping and provide a more comfortable and satisfying shopping experience.

[0360] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring related data from a database based on information input by a user and emotional data of the user, means for analyzing the acquired data and emotional data using a generative model, and means for generating strategies or product proposals based on the analysis results. This enables personalized product proposals that reflect the user's emotions.

[0361] The "means for receiving information input by a user" is a function that allows the system to receive information such as text or voice input by a user via a terminal.

[0362] The "means for retrieving related data from a database based on received information and user emotion data" is a function for searching and retrieving related information from a database using information received from a user and the user emotion data analyzed by the emotion engine.

[0363] "Means for analyzing acquired data and emotion data using a generative model" refers to a function for inputting information and emotion data acquired from a database into a generative model based on a machine learning algorithm and performing analysis.

[0364] The "means for generating a strategy or product proposal based on the analysis results" is a function for generating a strategy or product proposal in a concrete form based on the analysis results obtained by the generative model.

[0365] The "means for providing the generated strategy or product proposal to the user" is a function for presenting the generated strategy or product proposal to the user via the terminal.

[0366] This invention is a data analysis system for mail-order sites that recognizes user emotions and makes appropriate product suggestions based on those emotions. A specific embodiment of this system is described below.

[0367] System configuration

[0368] This system encompasses a series of processes: inputting information from the user, retrieving related data from a database, analyzing the data using a generative model, generating suggestions, and delivering the generated suggestions. It also uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions based on the results. The system has three main components: a server, a terminal, and a user.

[0369] Hardware and software used

[0370] Hardware:

[0371] Smartphone (device)

[0372] server

[0373] software:

[0374] Emotion Engine API (Emotion Analysis)

[0375] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0376] Database System

[0377] Natural Language Generation (NLG) models

[0378] UI engine (e.g. React Native)

[0379] Network Communication Interface

[0380] Detailed explanation of the process

[0381] Data Entry and Receipt

[0382] A user enters product-related keywords and review content into a shopping app. The emotion engine reads emotions from the user's input and facial expressions (using the smartphone camera). The input data and emotion data are sent from the smartphone to the server in JSON format.

[0383] Data Acquisition

[0384] The server retrieves related product information, reviews, and recommended product data from a database based on the received user input data and emotion data. The connected database includes a database that stores detailed product information and user reviews.

[0385] Data analysis

[0386] The server inputs this acquired information into a generative model and makes product recommendations that take the user's emotional state into account. Machine learning libraries such as TensorFlow and PyTorch are used to analyze the generative model.

[0387] Proposal generation and delivery

[0388] The server generates product suggestions based on the analysis results obtained from the generative model, corresponding to the user's emotions. The generated product suggestions are presented with a message, such as "These earphones have sound quality that will relax you." The suggested products and messages are sent to a smartphone app and displayed to the user.

[0389] Specific examples

[0390] scenario

[0391] Here is a specific usage scenario where a user enters "I want new earphones" into a shopping app.

[0392] Prompt Sentence Examples

[0393] "I want new earphones."

[0394] This system allows users to receive product suggestions that match their emotions, resulting in a more comfortable and satisfying shopping experience.

[0395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0396] Step 1:

[0397] Users enter product-related keywords and review content into the shopping app. At this time, the smartphone camera captures the user's facial expressions, which are then analyzed by the emotion engine API to generate emotion data. The input here is the user's text input and facial expression data, and emotion data is output based on this.

[0398] Step 2:

[0399] The device receives the user's input data and the emotion data recognized by the emotion engine, and sends them to the server in a standardized format (e.g., JSON). In this process, the text input data and emotion data are transferred together to the server.

[0400] Step 3:

[0401] The server analyzes the received user input data and emotion data and retrieves related information from the database based on the analysis. Specifically, detailed product information, user reviews, and related ratings are retrieved from the database. Here, the input data and emotion data are used to query the relevant database and retrieve the relevant product information.

[0402] Step 4:

[0403] The server inputs the acquired data and emotional data into a generative model to generate optimal product suggestions corresponding to the user's emotional state. At this time, each piece of data is analyzed using a machine learning algorithm (e.g., TensorFlow, PyTorch). The input data is product information and emotional data acquired from a database, and product suggestions are output based on that.

[0404] Step 5:

[0405] The server generates a suggested message based on the analysis results obtained from the generative model. For example, a specific message such as "These earphones have a sound quality that will relax you" is generated. The generated message has appropriate content that reflects the user's emotional state.

[0406] Step 6:

[0407] The server sends the generated product proposal and proposal message to the terminal, which receives them and displays them to the user. The output here is the proposed product and message displayed on the user's terminal.

[0408] Step 7:

[0409] Users can check the suggested products and messages on their device screen and consider purchasing the products based on them. By receiving suggestions that take their emotions into consideration, users can have a more comfortable shopping experience.

[0410] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0411] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0413] [Second embodiment]

[0414] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0415] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0416] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0418] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0420] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0421] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0422] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0423] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0425] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0426] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. Specific embodiments of this system will be described below.

[0427] System Overview:

[0428] This system includes a series of processes: input of information from users, acquisition of related data from a database, data analysis using a generative model, strategy generation, and provision of the generated strategy. The system has three main components: a server, a terminal, and a user.

[0429] What the program does:

[0430] Data Entry:

[0431] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot provides an intuitive user interface and enables quick data entry.

[0432] Data reception:

[0433] The terminal receives input from the user and sends it to the server. The input data is sent to the server in a standardized format (e.g., JSON).

[0434] Data Acquisition:

[0435] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[0436] Data Analysis:

[0437] The server inputs the acquired information into a generative model to analyze optimal player selection and strategy. The generative model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation.

[0438] Strategy Generation:

[0439] The server generates specific strategy proposals based on the analysis results obtained from the generative model, for example, by proposing a strategy in the form of "It would be optimal to use pitcher Matsuda in the next game."

[0440] Strategy provided:

[0441] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0442] Examples:

[0443] scenario:

[0444] Ask the system which pitcher to use in the next game.

[0445] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[0446] 2. The device receives the user's input and sends it to the server in a standardized format (JSON).

[0447] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[0448] 4. The server analyzes this data using a generative model to identify the best pitcher.

[0449] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game."

[0450] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[0451] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[0452] As described above, the system of the present invention can analyze data based on user input and provide instant and flexible strategy proposals, enabling sports teams to quickly and effectively develop tactics and improve their chances of winning a game.

[0453] The processing flow will be explained below.

[0454] Step 1:

[0455] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[0456] Step 2:

[0457] The terminal receives input data from the user. The received data is converted into JSON format and then sent to the server. For example, the converted data will be in the format "{"query": "Which pitcher is best for the next game?"".

[0458] Step 3:

[0459] The server receives the JSON data sent from the device, parses the received data, extracts the necessary information, and then begins preparations to access the database.

[0460] Step 4:

[0461] The server queries the database to retrieve relevant data, specifically the performance data for the team's pitchers over the past 10 games and the most recent performance data for the opposing batters.

[0462] Step 5:

[0463] The server preprocesses the acquired data, including standardizing, normalizing, and imputing missing values, so that the data is ready to be input to the generative model.

[0464] Step 6:

[0465] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and current situation.

[0466] Step 7:

[0467] The generative model analyzes the data and sends the results back to the server, such as "Pitcher Matsuda is the best for the next game."

[0468] Step 8:

[0469] The server receives the results from the generative model and generates a strategy proposal based on the analysis results. The strategy proposal is a specific statement such as, "It would be best to use pitcher Matsuda in the next game."

[0470] Step 9:

[0471] The server formats the generated strategy proposal in JSON format and sends it to the device, for example, "{"recommendation": "It is best to use pitcher Matsuda in the next game"}".

[0472] Step 10:

[0473] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and then displays the strategy proposal on the user interface.

[0474] Step 11:

[0475] The user checks the strategy suggestion displayed on the device screen, saying, "It is best to use pitcher Matsuda in the next game." Based on this information, the user decides which pitcher to use in the next game.

[0476] Example 1

[0477] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0478] There is a growing need for a system that can quickly and effectively analyze data and propose optimal strategies in the strategic planning and scouting of sports teams. Conventional methods require the time-consuming task of collecting and analyzing data individually, making it difficult to plan strategies efficiently. The objective of this invention is to provide a system that can be intuitively used by users and that centrally performs everything from data analysis to strategy proposals.

[0479] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0480] In this invention, the server includes: [terminal means for receiving information input by a user; [means for transmitting the information received by the terminal to the server in a standardized format; [means for acquiring related data from a database based on the information received by the server; [means for performing analysis using a generative model with the acquired data by the server; [means for the server to generate a strategy based on the analysis results; and [means for providing the generated strategy to the user via the terminal.] This enables the user to easily input the necessary information and quickly acquire a strategy based on the analysis results.

[0481] A "user" is an entity that uses the system to input information and receives strategies provided as analysis results.

[0482] A "terminal" is a device that receives information from a user and transmits it to a server. Examples include PCs, smartphones, and tablets.

[0483] The "server" is a computer system that retrieves relevant data from a database based on received information, analyzes the data using a generative model, and generates and provides a strategy.

[0484] A "database" is a system that stores related information and provides data in response to queries from a server.

[0485] A "generative model" is a model that uses machine learning algorithms to analyze data and identify optimal strategies.

[0486] A "chatbot" is an interface for collecting information through dialogue with users and sending it to a system.

[0487] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate analytical results.

[0488] A "prompt sentence" is an input sentence given to a generative AI model, and is the basic information that the model uses for analysis.

[0489] A "standardized format" is a format in which information is structured according to certain rules and is primarily used for exchanging data between systems. Examples include the JSON format.

[0490] A "strategy" is a specific action plan proposed based on the results of analysis by the generative model.

[0491] The "analysis result" is the final output of the analysis performed by the generative model based on the input data.

[0492] The present invention relates to a data analysis system for supporting strategic planning and scouting for sports teams. Specific embodiments of this system will be described below.

[0493] The system's main components are a user, a device, and a server. The user inputs information into the system via a chatbot. The device receives the information and sends it to the server in a standardized format (e.g., JSON). The server then retrieves relevant data from a database based on the information and performs data analysis using a generative AI model. Based on the analysis results, the server generates a strategy and provides it to the user via the device.

[0494] Hardware and software used

[0495] Server: A high-performance server for performing data analysis and strategy generation (e.g., Amazon Web Services, Google Cloud Platform)

[0496] Terminal: The device on which the user enters input and confirms strategic proposals (e.g., PC, smartphone, tablet)

[0497] Chatbot interface: Tools that allow users to input information intuitively (e.g., Dialogflow, Microsoft Bot Framework)

[0498] Generative AI models: Machine learning models for data analysis (e.g., TensorFlow, PyTorch)

[0499] Operation flow

[0500] 1. A user inputs a query such as "Which pitcher should be used in the next game?" in natural language via a chatbot. For example, a user opens the chatbot's user interface from a smartphone or PC browser, inputs a query in the text field, and presses the send button.

[0501] 2. The terminal receives input from the user and converts the data into a standardized format (JSON). The terminal parses the user's input text and converts it into JSON format such as { "query": "Which pitcher should be used in the next game?"}

[0502] 3. The device sends the converted data to the server. The device sends the JSON data via the network as a POST request to a specific API endpoint on the server.

[0503] 4. The server receives the data sent from the device. The server's API receives the request and extracts the JSON data from the request body.

[0504] 5. The server retrieves the necessary relevant information from the database based on the received data. The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[0505] 6. The server inputs the acquired data into a generative AI model for data analysis. The server invokes a machine learning model (e.g., TensorFlow) and passes the performance data as input to the model. The model performs the analysis and identifies the optimal pitcher.

[0506] 7. The server generates a specific strategy proposal based on the analysis results obtained from the generative AI model. The server applies the analysis results (e.g., pitcher's name) to a template for expressing them in natural language, and generates a sentence such as, "It is best to use pitcher Matsuda in the next game."

[0507] 8. The server sends the generated strategy proposal to the terminal. The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[0508] 9. The terminal displays the strategy proposal received from the server to the user. The terminal extracts the strategy proposal from the response body and displays the proposal on the chatbot's UI.

[0509] 10. The user checks the strategy suggestions displayed on the device screen and makes a decision based on them. The user reads the suggestions displayed on the chatbot screen and decides on the pitcher for the next game.

[0510] Examples of prompt statements

[0511] "Which pitcher should we use in the next game?

[0512] Analyze the optimal pitcher based on past performance and the performance of opposing batters, and propose a specific strategy.

[0513] In this way, this system can quickly and effectively analyze data and propose optimal strategies to sports teams, significantly improving the efficiency of strategic planning and scouting for sports teams.

[0514] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0515] Step 1:

[0516] A user accesses the system and inputs the query "Which pitcher should be used in the next game?" in natural language through the chatbot.

[0517] Input: The user enters a query into the chatbot's input field and presses the submit button.

[0518] Output: A query in natural language form is generated.

[0519] Specific operation: The user opens the chatbot screen in a smartphone or PC browser, enters "Which pitcher should be used in the next game?" in the text field, and presses the send button.

[0520] Step 2:

[0521] The terminal receives input from the user and converts the information into a standardized format (JSON).

[0522] Input: The natural language query entered by the user.

[0523] Output: Data in a standardized format (e.g. JSON).

[0524] Specific operation: The device parses the user's input text and converts it into JSON format, such as { "query": "Which pitcher should be used in the next game?"}.

[0525] Step 3:

[0526] The terminal transmits the converted data to the server.

[0527] Input: A query expressed in a standardized format (JSON).

[0528] Output: A POST request to the server.

[0529] Specific operation: The terminal sends JSON data via the network as a POST request to a specific API endpoint on the server.

[0530] Step 4:

[0531] The server receives the data sent from the terminal.

[0532] Input: JSON format data sent from the terminal.

[0533] Output: Internal data structure that parses the received JSON data.

[0534] Specific operation: The server API receives the request and extracts the JSON data from the request body.

[0535] Step 5:

[0536] The server retrieves the necessary relevant information from a database based on the received data.

[0537] Input: User query in JSON format.

[0538] Output: Relevant database entries (e.g. pitcher's past performance, opponent's performance).

[0539] Specific operation: The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[0540] Step 6:

[0541] The server inputs the acquired data into a generative AI model and performs data analysis.

[0542] Input: Relevant data retrieved from the database.

[0543] Output: Analysis results from the generative model (e.g., optimal pitcher).

[0544] How it works: The server calls a machine learning model (e.g., TensorFlow) and passes the acquired performance data as input to the model. The model then performs analysis and identifies the best pitcher.

[0545] Step 7:

[0546] The server generates specific strategy proposals based on the analysis results obtained from the generative AI model.

[0547] Input: Analysis results from the generative AI model.

[0548] Output: Strategy suggestions in natural language format.

[0549] Specific operation: The server applies the model output (e.g., the pitcher's name) to a template for expressing it in natural language, and generates the sentence, "It would be best to use pitcher Matsuda in the next game."

[0550] Step 8:

[0551] The server transmits the generated strategy proposal to the terminal.

[0552] Input: A strategy proposal expressed in natural language.

[0553] Output: JSON data containing the strategy proposal as a response to the terminal.

[0554] Specific operation: The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[0555] Step 9:

[0556] The terminal displays the strategy proposal received from the server to the user.

[0557] Input: JSON data sent from the server.

[0558] Output: Strategy proposals displayed on the user interface.

[0559] Specific operation: The terminal extracts strategy proposals from the response body and displays them on the chatbot's UI.

[0560] Step 10:

[0561] The user checks the strategy proposals displayed on the terminal screen and makes a decision based on them.

[0562] Input: Strategy proposals displayed on the terminal screen.

[0563] Output: Deciding which pitcher to use in the next game.

[0564] Specific operation: The user confirms the strategy suggestion displayed on the chatbot screen, "It would be best to use pitcher Matsuda in the next game," and decides to pitch Matsuda for the next game.

[0565] (Application example 1)

[0566] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] Planning maintenance for industrial equipment and optimizing production lines are important issues for efficient factory operation. However, manually managing the operating status and past maintenance records of each piece of equipment and performing maintenance at the appropriate time is difficult, increasing the risk of equipment failure and production loss. Therefore, there is a need for efficient strategy proposals based on the analysis of real-time data.

[0568] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0569] In this invention, the server includes: [means for receiving information input by a user;] [means for acquiring related data from a database based on the received information;] [means for analyzing the acquired data using a generative model;] [means for generating a strategy based on the analysis results;] [means for providing the generated strategy to the user;] [means for acquiring the operating status and maintenance records of industrial equipment; and [means for making maintenance predictions for industrial equipment using a machine learning algorithm.] This makes it possible to efficiently manage the operating status and past maintenance records of each piece of equipment and predict the appropriate timing for maintenance.

[0570] A "user" is a person or organization that operates the system and provides input information.

[0571] "Information" means data or requests provided by a user to a server.

[0572] A "database" is a collection of data that stores and manages related information in an organized manner.

[0573] A "generative model" is a system that uses machine learning algorithms to analyze input data and generate a specific output.

[0574] "Analysis" is the process of examining data in detail and drawing specific conclusions or strategies.

[0575] A "strategy" is a plan or policy for achieving a specific objective.

[0576] "Providing" is the act of presenting the generated strategies and information to the user.

[0577] "Industrial equipment" refers to machinery and equipment used within a factory.

[0578] "Operation status" refers to information that indicates the operating state and efficiency of industrial equipment.

[0579] "Maintenance records" refer to the past maintenance history of industrial equipment.

[0580] A "machine learning algorithm" is a computer algorithm that learns patterns and trends from large amounts of data and makes predictions and classifications.

[0581] "Maintenance prediction" is the process of using machine learning algorithms to predict when future maintenance will be required.

[0582] The present invention relates to a data analysis system for supporting maintenance planning and optimization of production lines in industrial facilities. Specific embodiments of this system will be described below.

[0583] System Overview:

[0584] This system has three main components: the user, the server, and the terminal, and includes a series of processes that cover everything from data input to maintenance prediction, strategy generation, and strategy provision. The main processes are information input from the user, data analysis on the server, and provision of the analysis results.

[0585] Hardware and software:

[0586] Server: A server for database management and running machine learning model analysis (e.g., AWS EC2 instance).

[0587] Device: A smartphone or tablet where users can enter information and check strategic proposals.

[0588] Industrial robots: Robots used in factories for data collection and interfacing (e.g., Pepper).

[0589] What the program does:

[0590] Data Entry:

[0591] Users access the system via a chatbot and input the necessary information, for example, to inquire about the next machine that needs maintenance. An intuitive user interface is provided, allowing for quick data entry.

[0592] Data reception:

[0593] The terminal receives input from the user and sends it to the server in a standardized format (e.g., JSON).

[0594] Data Acquisition:

[0595] When the server receives the data sent by the user, it retrieves related information from the database based on that information, such as the operating status of industrial equipment and past maintenance records.

[0596] Data Analysis:

[0597] The server inputs the acquired information into a generative model and analyzes the optimal maintenance targets and production line optimization. The generative model uses a machine learning algorithm (e.g., Random Forest Classifier) ​​to perform highly accurate analysis based on past data and the current situation.

[0598] Strategy Generation:

[0599] The server generates specific strategy proposals based on the analysis results obtained from the generative model. For example, it generates a strategy in the form of "Unit A is the next unit to undergo maintenance."

[0600] Strategy provided:

[0601] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0602] Examples:

[0603] For example, consider a case where a user types into a chatbot, "Please tell me which machine should be maintained next." The system analyzes past maintenance records and operation data and responds, "The next machine that needs maintenance is Unit A."

[0604] Example prompt sentence:

[0605] "Please tell me which machines will undergo the next maintenance. Machine A has 5,000 operating hours, 30 days before its last maintenance, and an error rate of 5%. Machine B has 3,000 operating hours, 15 days before its last maintenance, and an error rate of 3%. Machine C has 6,000 operating hours, 60 days before its last maintenance, and an error rate of 10%."

[0606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0607] Step 1:

[0608] The user accesses the chatbot using a terminal and inputs a question such as, "Please tell me which machine should be maintained next." The input data is in text format, and this question is registered in the system.

[0609] Input: User inquiry about the machine to be maintained

[0610] Output: Send a query to the chatbot

[0611] Step 2:

[0612] The terminal receives user input, converts it into a standardized format (JSON), and sends it to the server.

[0613] Input: User text input

[0614] Output: Standardized query data (JSON)

[0615] Step 3:

[0616] The server analyzes the received query data and retrieves the operating status and past maintenance records of the industrial equipment from the relevant database.

[0617] Input: Standardized query data (JSON)

[0618] Output: Operation status and maintenance records of industrial equipment

[0619] Step 4:

[0620] The server inputs the acquired data into a machine learning algorithm (generative model) to make maintenance predictions. Specifically, it identifies the equipment that next requires maintenance using information such as the operating hours, last maintenance date, and error rate for each piece of equipment.

[0621] Input: Operation status and maintenance record data

[0622] Output: Prediction of optimal machine maintenance targets

[0623] Step 5:

[0624] The server generates specific maintenance strategy proposals based on the analysis results obtained from the generative model, and expresses the conclusion in text form, such as "Unit A should be the next to undergo maintenance."

[0625] Input: Maintenance forecast results

[0626] Output: Strategy proposal (text format)

[0627] Step 6:

[0628] The server converts the generated strategy proposal into a standardized format (JSON) and sends it to the terminal.

[0629] Input: Strategy proposal (text format)

[0630] Output: Standardized strategy data (JSON)

[0631] Step 7:

[0632] The terminal analyzes the strategy data received from the server and displays strategy proposals to the user, who then checks the maintenance strategy on the terminal screen and makes decisions based on it.

[0633] Input: Standardized strategy data (JSON)

[0634] Output: Strategy proposals displayed to the user

[0635] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0636] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. In particular, by combining it with an emotion engine that recognizes the user's emotions, more effective strategy proposals can be realized. Specific embodiments of this system are described below.

[0637] System Overview:

[0638] This system encompasses a series of processes: inputting information from the user, retrieving relevant data from a database, analyzing the data using a generative model, generating a strategy, and providing the generated strategy. Furthermore, it uses an emotion engine to recognize the user's emotions and adjusts the strategy analysis based on the results. The system has three main components: a server, a terminal, and a user.

[0639] What the program does:

[0640] Data Entry:

[0641] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot responds intuitively to the user's input, and the emotion engine reads emotions from the input.

[0642] Data reception:

[0643] The device receives input data from the user and sends it to the server in a standardized format (e.g., JSON), including the user's emotional data recognized by the emotion engine.

[0644] Data Acquisition:

[0645] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[0646] Data Analysis:

[0647] The server inputs the acquired information into a generative model and analyzes the optimal player selection and strategy. The generative model uses a machine learning algorithm to perform highly accurate analysis based on past data and the current situation. It also adjusts the strategic analysis so that the analysis results from the emotion engine have an impact.

[0648] Strategy Generation:

[0649] The server generates specific strategy proposals based on the analysis results obtained from the generative model. The generated strategy proposals are written in the form of "It would be best to use pitcher Matsuda in the next game." The server also makes proposals that take the user's emotions into consideration.

[0650] Strategy provided:

[0651] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0652] Examples:

[0653] scenario:

[0654] Ask the system which pitcher to use in the next game.

[0655] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[0656] 2. The device receives the user's input and sends it to the server in a standardized format (JSON), including the user's emotion as recognized by the emotion engine.

[0657] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[0658] 4. The server analyzes this data using a generative model and identifies the best pitcher based on the results of the emotion engine.

[0659] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game." If the user is feeling nervous, the server adds a message that gives the user a sense of relief, such as, "Don't worry, use pitcher Matsuda."

[0660] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[0661] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[0662] As described above, the system of the present invention combines user input with analysis by the emotion engine to provide fast, flexible, and data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[0663] The processing flow will be explained below.

[0664] Step 1:

[0665] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[0666] Step 2:

[0667] The device receives input data from the user and converts it into JSON format. For example, the converted data will be in the format of "{"query": "Which pitcher is best for the next game?"". The emotion engine also identifies the user's emotion from the user's facial expression and input text, and sends the emotion data to the server.

[0668] Step 3:

[0669] The server receives the JSON data and emotion data sent from the device, analyzes the received data, extracts the necessary information, and then prepares to access the database.

[0670] Step 4:

[0671] The server queries the database based on the received information to retrieve relevant data, specifically the performance data of the team's pitcher from the past 10 games and the most recent performance data of the opposing team's batters.

[0672] Step 5:

[0673] The server preprocesses the acquired data, which includes standardizing, normalizing, and imputing missing values, etc. This process prepares the data for input into the generative model.

[0674] Step 6:

[0675] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and the current situation. Additionally, the extracted emotional data is also input into the model, influencing the analysis.

[0676] Step 7:

[0677] The generative model analyzes the data and sends the results back to the server, such as whether pitcher Matsuda is the best for the next game.

[0678] Step 8:

[0679] The server generates a strategy proposal based on the analysis results obtained from the generative model. The generated strategy proposal is expressed in the form of "It is best to use pitcher Matsuda in the next game." In addition, an additional message (e.g., "Please feel free to use pitcher Matsuda") is generated based on the emotion data to give the user a sense of security.

[0680] Step 9:

[0681] The server formats the generated strategy proposal in JSON format and sends it to the terminal. For example, it may have the format "{"recommendation": "It is best to use pitcher Matsuda in the next game", "additionalMessage": "Please feel free to use pitcher Matsuda"}".

[0682] Step 10:

[0683] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and displays strategy suggestions and additional messages on the user interface.

[0684] Step 11:

[0685] The user checks the strategy suggestion displayed on the device screen, "It is best to use pitcher Matsuda in the next game," along with the additional message, "Please feel free to use pitcher Matsuda." Based on this information, the user decides which pitcher to use in the next game.

[0686] Example 2

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

[0688] Conventional strategic planning and scouting systems for sports teams are unable to propose strategies that take user emotions into account, making it difficult to improve the user experience or increase the adoption rate of strategies. Furthermore, the lack of an intuitive interface for dialogue using chatbots can sometimes reduce the accuracy and efficiency of user input. To solve these problems, it is important to recognize user emotions and reflect them in strategic planning.

[0689] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0690] In this invention, the server includes: [means for receiving information input by a user and recognizing emotions using an emotion engine]; [means for retrieving relevant data from a database based on the received information and emotions]; and [means for analyzing the retrieved data and emotions using a generative AI model]. This makes it possible [to quickly provide more accurate strategy proposals while taking into account the user's emotions].

[0691] A "user" is an entity that accesses the system, inputs information, and receives strategic proposals.

[0692] "Input information" is text data that the user provides to the system, including questions and instructions such as which players should be used in the next game.

[0693] An "emotion engine" is software or an algorithm that analyzes information input by a user and recognizes the user's emotions (e.g., tension, anxiety, joy, etc.) based on that information.

[0694] The "database" is a system for storing and managing user-input information and related data based on emotions (for example, players' past performances and opponent data).

[0695] "Related data" refers to information necessary for strategy planning (for example, player performance data and information on the opposing team) that is acquired from a database based on user input.

[0696] A "generative AI model" is a model that uses machine learning algorithms to analyze input data and related data and generate optimal strategic proposals.

[0697] "Analysis" is the process of deriving the optimal strategy based on data obtained using a generative AI model and user emotional data.

[0698] A "strategy" is a specific player selection and tactical policy for the next match proposed based on the results of analysis by the generative AI model.

[0699] "Providing" refers to the act of transmitting the generated strategy from the server to the user via the terminal, and allowing the user to confirm and make a decision.

[0700] A "chatbot" is software that automatically interacts between a user and a system, and is an interface that accepts user input and returns appropriate responses.

[0701] The present invention is a data analysis system for supporting strategic planning and scouting in sports teams, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose more effective strategies. Specific embodiments of this system are described below.

[0702] Overall system configuration

[0703] This system is mainly composed of three components: a server, a terminal, and a user. The server is responsible for accessing the database, analyzing data using a generative AI model, and generating strategies. The terminal receives information input from the user and displays the analysis results and proposals. The user mainly operates the terminal to input information and receive strategy proposals from the system.

[0704] Hardware and software used

[0705] The server is equipped with a high-performance processor and large amounts of memory and storage. Specifically, cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used. MySQL and PostgreSQL are commonly used as databases.

[0706] Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Furthermore, advanced generative models such as OpenAI's GPT-3 are adopted for natural language processing. Sentiment analysis APIs from Microsoft's Azure Cognitive Services can be used as emotion engines.

[0707] What the program does

[0708] User input of information

[0709] Users access the system and use the chatbot to input specific questions, such as which pitcher should be used in the next game. The device receives the user's input and uses an emotion engine to recognize the user's emotions.

[0710] Receiving and processing input data

[0711] The device receives the question and emotion data entered by the user and sends it to the server in a standardized format (e.g., JSON). When the server receives this data, it retrieves related data from a database. For example, if the user enters "Which pitcher should we use in the next game?", the server retrieves the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[0712] Data analysis and strategy generation

[0713] The server inputs the acquired information into a generative AI model, which analyzes the optimal player selection and strategy. The generative AI model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation. It also takes into account the results of the emotion engine and reflects this in its strategic analysis. Based on the analysis results, it generates specific strategy suggestions, such as "It is best to use a specific pitcher in the next game."

[0714] Providing strategic proposals

[0715] The server sends the generated strategy proposal to the terminal, which displays it to the user, who then checks the generated strategy on the terminal and decides on a pitcher for the next game based on it.

[0716] Specific examples

[0717] An example of a prompt is:

[0718] In response to the question, "Which pitcher should we use in the next game?", the system analyzes the situation and makes strategic suggestions such as, "It would be best to use a specific pitcher in the next game. You may be nervous, but rest assured considering their track record."

[0719] In this way, the system of the present invention can combine user input with analysis by the emotion engine to quickly and flexibly provide data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[0720] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] Users access the system using a web browser or mobile app. They input a specific question in natural language into the chatbot interface, such as "Which pitcher should be used in the next game?" The emotion engine then analyzes the user's input and identifies emotions such as "I'm nervous."

[0723] Input: User's question (in text format)

[0724] Output: User's question and emotion data (text format and emotion labels)

[0725] Step 2:

[0726] The device receives questions and emotion data entered by the user, converts this data into a standardized format (e.g., JSON format), and sends it to the server.

[0727] Input: User question and emotion data (text format and emotion labels)

[0728] Output: Standardized data (JSON format)

[0729] Step 3:

[0730] The server receives the JSON data sent from the device, parses it, and sends a query to the database. The query contains information related to the user's question (e.g., the past performance of the team's pitcher, the performance of the opposing team's batters).

[0731] Input: Standardized data (JSON format)

[0732] Output: A list of database queries and the associated data retrieved.

[0733] Step 4:

[0734] The server retrieves relevant information from a database, including the past performance of the team's pitchers and the performance of the opposing batters, and stores the retrieved data temporarily for use in the next analysis step.

[0735] Input: Database query

[0736] Output: Related data (e.g., pitcher's past performance, batter's performance)

[0737] Step 5:

[0738] The server inputs the acquired relevant data into the generative AI model and begins analysis. The generative AI model analyzes the data using machine learning algorithms (e.g., TensorFlow or PyTorch) and proposes optimal player selection. It also incorporates the results of the emotion engine into the analysis and makes adjustments based on emotions.

[0739] Input: Related data (e.g., pitcher's past performance, batter's performance) and emotion data

[0740] Output: Analysis results (e.g., optimal pitcher suggestions)

[0741] Step 6:

[0742] The server generates specific strategy suggestions based on the analysis results obtained from the generative AI model. For example, it generates a strategy statement such as, "It is best to use a specific pitcher in the next game." The message is also adjusted to reflect the user's emotions.

[0743] Input: Analysis results (e.g., optimal pitcher suggestions)

[0744] Output: Strategy proposal (strategy statement in text format)

[0745] Step 7:

[0746] The server sends the generated strategy proposal to the terminal, which displays the proposal to the user. The user checks the proposed strategy on the terminal and decides on a pitcher for the next game based on the information.

[0747] Input: Strategy proposal (strategy statement in text format)

[0748] Output: Providing strategies to the user (strategy suggestions displayed on the device screen)

[0749] (Application example 2)

[0750] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0751] In today's market, users' shopping experiences are becoming increasingly diverse, and they are seeking personalized recommendations tailored to their individual needs. However, systems that adequately meet these demands are still limited. Furthermore, technology for generating appropriate product recommendations and messages based on users' emotions has not been fully established. Therefore, there is a need to reduce the stress and difficulties users experience when shopping and provide a more comfortable and satisfying shopping experience.

[0752] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring related data from a database based on information input by a user and emotional data of the user, means for analyzing the acquired data and emotional data using a generative model, and means for generating strategies or product proposals based on the analysis results. This enables personalized product proposals that reflect the user's emotions.

[0753] The "means for receiving information input by a user" is a function that allows the system to receive information such as text or voice input by a user via a terminal.

[0754] The "means for retrieving related data from a database based on received information and user emotion data" is a function for searching and retrieving related information from a database using information received from a user and the user emotion data analyzed by the emotion engine.

[0755] "Means for analyzing acquired data and emotion data using a generative model" refers to a function for inputting information and emotion data acquired from a database into a generative model based on a machine learning algorithm and performing analysis.

[0756] The "means for generating a strategy or product proposal based on the analysis results" is a function for generating a strategy or product proposal in a concrete form based on the analysis results obtained by the generative model.

[0757] The "means for providing the generated strategy or product proposal to the user" is a function for presenting the generated strategy or product proposal to the user via the terminal.

[0758] This invention is a data analysis system for mail-order sites that recognizes user emotions and makes appropriate product suggestions based on those emotions. A specific embodiment of this system is described below.

[0759] System configuration

[0760] This system encompasses a series of processes: inputting information from the user, retrieving related data from a database, analyzing the data using a generative model, generating suggestions, and delivering the generated suggestions. It also uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions based on the results. The system has three main components: a server, a terminal, and a user.

[0761] Hardware and software used

[0762] Hardware:

[0763] Smartphone (device)

[0764] server

[0765] software:

[0766] Emotion Engine API (Emotion Analysis)

[0767] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0768] Database System

[0769] Natural Language Generation (NLG) models

[0770] UI engine (e.g. React Native)

[0771] Network Communication Interface

[0772] Detailed explanation of the process

[0773] Data Entry and Receipt

[0774] A user enters product-related keywords and review content into a shopping app. The emotion engine reads emotions from the user's input and facial expressions (using the smartphone camera). The input data and emotion data are sent from the smartphone to the server in JSON format.

[0775] Data Acquisition

[0776] The server retrieves related product information, reviews, and recommended product data from a database based on the received user input data and emotion data. The connected database includes a database that stores detailed product information and user reviews.

[0777] Data analysis

[0778] The server inputs this acquired information into a generative model and makes product recommendations that take the user's emotional state into account. Machine learning libraries such as TensorFlow and PyTorch are used to analyze the generative model.

[0779] Proposal generation and delivery

[0780] The server generates product suggestions based on the analysis results obtained from the generative model, corresponding to the user's emotions. The generated product suggestions are presented with a message, such as "These earphones have sound quality that will relax you." The suggested products and messages are sent to a smartphone app and displayed to the user.

[0781] Specific examples

[0782] scenario

[0783] Here is a specific usage scenario where a user enters "I want new earphones" into a shopping app.

[0784] Prompt Sentence Examples

[0785] "I want new earphones."

[0786] This system allows users to receive product suggestions that match their emotions, resulting in a more comfortable and satisfying shopping experience.

[0787] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0788] Step 1:

[0789] Users enter product-related keywords and review content into the shopping app. At this time, the smartphone camera captures the user's facial expressions, which are then analyzed by the emotion engine API to generate emotion data. The input here is the user's text input and facial expression data, and emotion data is output based on this.

[0790] Step 2:

[0791] The device receives the user's input data and the emotion data recognized by the emotion engine, and sends them to the server in a standardized format (e.g., JSON). In this process, the text input data and emotion data are transferred together to the server.

[0792] Step 3:

[0793] The server analyzes the received user input data and emotion data and retrieves related information from the database based on the analysis. Specifically, detailed product information, user reviews, and related ratings are retrieved from the database. Here, the input data and emotion data are used to query the relevant database and retrieve the relevant product information.

[0794] Step 4:

[0795] The server inputs the acquired data and emotional data into a generative model to generate optimal product suggestions corresponding to the user's emotional state. At this time, each piece of data is analyzed using a machine learning algorithm (e.g., TensorFlow, PyTorch). The input data is product information and emotional data acquired from a database, and product suggestions are output based on that.

[0796] Step 5:

[0797] The server generates a suggested message based on the analysis results obtained from the generative model. For example, a specific message such as "These earphones have a sound quality that will relax you" is generated. The generated message has appropriate content that reflects the user's emotional state.

[0798] Step 6:

[0799] The server sends the generated product proposal and proposal message to the terminal, which receives them and displays them to the user. The output here is the proposed product and message displayed on the user's terminal.

[0800] Step 7:

[0801] Users can check the suggested products and messages on their device screen and consider purchasing the products based on them. By receiving suggestions that take their emotions into consideration, users can have a more comfortable shopping experience.

[0802] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0803] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0804] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0805] [Third embodiment]

[0806] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0807] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0808] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0809] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0810] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0811] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0812] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0813] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0814] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0815] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0816] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0817] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0818] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. Specific embodiments of this system will be described below.

[0819] System Overview:

[0820] This system includes a series of processes: input of information from users, acquisition of related data from a database, data analysis using a generative model, strategy generation, and provision of the generated strategy. The system has three main components: a server, a terminal, and a user.

[0821] What the program does:

[0822] Data Entry:

[0823] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot provides an intuitive user interface and enables quick data entry.

[0824] Data reception:

[0825] The terminal receives input from the user and sends it to the server. The input data is sent to the server in a standardized format (e.g., JSON).

[0826] Data Acquisition:

[0827] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[0828] Data Analysis:

[0829] The server inputs the acquired information into a generative model to analyze optimal player selection and strategy. The generative model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation.

[0830] Strategy Generation:

[0831] The server generates specific strategy proposals based on the analysis results obtained from the generative model, for example, by proposing a strategy in the form of "It would be optimal to use pitcher Matsuda in the next game."

[0832] Strategy provided:

[0833] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0834] Examples:

[0835] scenario:

[0836] Ask the system which pitcher to use in the next game.

[0837] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[0838] 2. The device receives the user's input and sends it to the server in a standardized format (JSON).

[0839] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[0840] 4. The server analyzes this data using a generative model to identify the best pitcher.

[0841] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game."

[0842] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[0843] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[0844] As described above, the system of the present invention can analyze data based on user input and provide instant and flexible strategy proposals, enabling sports teams to quickly and effectively develop tactics and improve their chances of winning a game.

[0845] The processing flow will be explained below.

[0846] Step 1:

[0847] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[0848] Step 2:

[0849] The terminal receives input data from the user. The received data is converted into JSON format and then sent to the server. For example, the converted data will be in the format "{"query": "Which pitcher is best for the next game?"".

[0850] Step 3:

[0851] The server receives the JSON data sent from the device, parses the received data, extracts the necessary information, and then begins preparations to access the database.

[0852] Step 4:

[0853] The server queries the database to retrieve relevant data, specifically the performance data for the team's pitchers over the past 10 games and the most recent performance data for the opposing batters.

[0854] Step 5:

[0855] The server preprocesses the acquired data, including standardizing, normalizing, and imputing missing values, so that the data is ready to be input to the generative model.

[0856] Step 6:

[0857] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and current situation.

[0858] Step 7:

[0859] The generative model analyzes the data and sends the results back to the server, such as "Pitcher Matsuda is the best for the next game."

[0860] Step 8:

[0861] The server receives the results from the generative model and generates a strategy proposal based on the analysis results. The strategy proposal is a specific statement such as, "It would be best to use pitcher Matsuda in the next game."

[0862] Step 9:

[0863] The server formats the generated strategy proposal in JSON format and sends it to the device, for example, "{"recommendation": "It is best to use pitcher Matsuda in the next game"}".

[0864] Step 10:

[0865] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and then displays the strategy proposal on the user interface.

[0866] Step 11:

[0867] The user checks the strategy suggestion displayed on the device screen, saying, "It is best to use pitcher Matsuda in the next game." Based on this information, the user decides which pitcher to use in the next game.

[0868] Example 1

[0869] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0870] There is a growing need for a system that can quickly and effectively analyze data and propose optimal strategies in the strategic planning and scouting of sports teams. Conventional methods require the time-consuming task of collecting and analyzing data individually, making it difficult to plan strategies efficiently. The objective of this invention is to provide a system that can be intuitively used by users and that centrally performs everything from data analysis to strategy proposals.

[0871] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0872] In this invention, the server includes: [terminal means for receiving information input by a user; [means for transmitting the information received by the terminal to the server in a standardized format; [means for acquiring related data from a database based on the information received by the server; [means for performing analysis using a generative model with the acquired data by the server; [means for the server to generate a strategy based on the analysis results; and [means for providing the generated strategy to the user via the terminal.] This enables the user to easily input the necessary information and quickly acquire a strategy based on the analysis results.

[0873] A "user" is an entity that uses the system to input information and receives strategies provided as analysis results.

[0874] A "terminal" is a device that receives information from a user and transmits it to a server. Examples include PCs, smartphones, and tablets.

[0875] The "server" is a computer system that retrieves relevant data from a database based on received information, analyzes the data using a generative model, and generates and provides a strategy.

[0876] A "database" is a system that stores related information and provides data in response to queries from a server.

[0877] A "generative model" is a model that uses machine learning algorithms to analyze data and identify optimal strategies.

[0878] A "chatbot" is an interface for collecting information through dialogue with users and sending it to a system.

[0879] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate analytical results.

[0880] A "prompt sentence" is an input sentence given to a generative AI model, and is the basic information that the model uses for analysis.

[0881] A "standardized format" is a format in which information is structured according to certain rules and is primarily used for exchanging data between systems. Examples include the JSON format.

[0882] A "strategy" is a specific action plan proposed based on the results of analysis by the generative model.

[0883] The "analysis result" is the final output of the analysis performed by the generative model based on the input data.

[0884] The present invention relates to a data analysis system for supporting strategic planning and scouting for sports teams. Specific embodiments of this system will be described below.

[0885] The system's main components are a user, a device, and a server. The user inputs information into the system via a chatbot. The device receives the information and sends it to the server in a standardized format (e.g., JSON). The server then retrieves relevant data from a database based on the information and performs data analysis using a generative AI model. Based on the analysis results, the server generates a strategy and provides it to the user via the device.

[0886] Hardware and software used

[0887] Server: A high-performance server for performing data analysis and strategy generation (e.g., Amazon Web Services, Google Cloud Platform)

[0888] Terminal: The device on which the user enters input and confirms strategic proposals (e.g., PC, smartphone, tablet)

[0889] Chatbot interface: Tools that allow users to input information intuitively (e.g., Dialogflow, Microsoft Bot Framework)

[0890] Generative AI models: Machine learning models for data analysis (e.g., TensorFlow, PyTorch)

[0891] Operation flow

[0892] 1. A user inputs a query such as "Which pitcher should be used in the next game?" in natural language via a chatbot. For example, a user opens the chatbot's user interface from a smartphone or PC browser, inputs a query in the text field, and presses the send button.

[0893] 2. The terminal receives input from the user and converts the data into a standardized format (JSON). The terminal parses the user's input text and converts it into JSON format such as { "query": "Which pitcher should be used in the next game?"}

[0894] 3. The device sends the converted data to the server. The device sends the JSON data via the network as a POST request to a specific API endpoint on the server.

[0895] 4. The server receives the data sent from the device. The server's API receives the request and extracts the JSON data from the request body.

[0896] 5. The server retrieves the necessary relevant information from the database based on the received data. The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[0897] 6. The server inputs the acquired data into a generative AI model for data analysis. The server invokes a machine learning model (e.g., TensorFlow) and passes the performance data as input to the model. The model performs the analysis and identifies the optimal pitcher.

[0898] 7. The server generates a specific strategy proposal based on the analysis results obtained from the generative AI model. The server applies the analysis results (e.g., pitcher's name) to a template for expressing them in natural language, and generates a sentence such as, "It is best to use pitcher Matsuda in the next game."

[0899] 8. The server sends the generated strategy proposal to the terminal. The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[0900] 9. The terminal displays the strategy proposal received from the server to the user. The terminal extracts the strategy proposal from the response body and displays the proposal on the chatbot's UI.

[0901] 10. The user checks the strategy suggestions displayed on the device screen and makes a decision based on them. The user reads the suggestions displayed on the chatbot screen and decides on the pitcher for the next game.

[0902] Examples of prompt statements

[0903] "Which pitcher should we use in the next game?

[0904] Analyze the optimal pitcher based on past performance and the performance of opposing batters, and propose a specific strategy.

[0905] In this way, this system can quickly and effectively analyze data and propose optimal strategies to sports teams, significantly improving the efficiency of strategic planning and scouting for sports teams.

[0906] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0907] Step 1:

[0908] A user accesses the system and inputs the query "Which pitcher should be used in the next game?" in natural language through the chatbot.

[0909] Input: The user enters a query into the chatbot's input field and presses the submit button.

[0910] Output: A query in natural language form is generated.

[0911] Specific operation: The user opens the chatbot screen in a smartphone or PC browser, enters "Which pitcher should be used in the next game?" in the text field, and presses the send button.

[0912] Step 2:

[0913] The terminal receives input from the user and converts the information into a standardized format (JSON).

[0914] Input: The natural language query entered by the user.

[0915] Output: Data in a standardized format (e.g. JSON).

[0916] Specific operation: The device parses the user's input text and converts it into JSON format, such as { "query": "Which pitcher should be used in the next game?"}.

[0917] Step 3:

[0918] The terminal transmits the converted data to the server.

[0919] Input: A query expressed in a standardized format (JSON).

[0920] Output: A POST request to the server.

[0921] Specific operation: The terminal sends JSON data via the network as a POST request to a specific API endpoint on the server.

[0922] Step 4:

[0923] The server receives the data sent from the terminal.

[0924] Input: JSON format data sent from the terminal.

[0925] Output: Internal data structure that parses the received JSON data.

[0926] Specific operation: The server API receives the request and extracts the JSON data from the request body.

[0927] Step 5:

[0928] The server retrieves the necessary relevant information from a database based on the received data.

[0929] Input: User query in JSON format.

[0930] Output: Relevant database entries (e.g. pitcher's past performance, opponent's performance).

[0931] Specific operation: The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[0932] Step 6:

[0933] The server inputs the acquired data into a generative AI model and performs data analysis.

[0934] Input: Relevant data retrieved from the database.

[0935] Output: Analysis results from the generative model (e.g., optimal pitcher).

[0936] How it works: The server calls a machine learning model (e.g., TensorFlow) and passes the acquired performance data as input to the model. The model then performs analysis and identifies the best pitcher.

[0937] Step 7:

[0938] The server generates specific strategy proposals based on the analysis results obtained from the generative AI model.

[0939] Input: Analysis results from the generative AI model.

[0940] Output: Strategy suggestions in natural language format.

[0941] Specific operation: The server applies the model output (e.g., the pitcher's name) to a template for expressing it in natural language, and generates the sentence, "It would be best to use pitcher Matsuda in the next game."

[0942] Step 8:

[0943] The server transmits the generated strategy proposal to the terminal.

[0944] Input: A strategy proposal expressed in natural language.

[0945] Output: JSON data containing the strategy proposal as a response to the terminal.

[0946] Specific operation: The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[0947] Step 9:

[0948] The terminal displays the strategy proposal received from the server to the user.

[0949] Input: JSON data sent from the server.

[0950] Output: Strategy proposals displayed on the user interface.

[0951] Specific operation: The terminal extracts strategy proposals from the response body and displays them on the chatbot's UI.

[0952] Step 10:

[0953] The user checks the strategy proposals displayed on the terminal screen and makes a decision based on them.

[0954] Input: Strategy proposals displayed on the terminal screen.

[0955] Output: Deciding which pitcher to use in the next game.

[0956] Specific operation: The user confirms the strategy suggestion displayed on the chatbot screen, "It would be best to use pitcher Matsuda in the next game," and decides to pitch Matsuda for the next game.

[0957] (Application example 1)

[0958] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0959] Planning maintenance for industrial equipment and optimizing production lines are important issues for efficient factory operation. However, manually managing the operating status and past maintenance records of each piece of equipment and performing maintenance at the appropriate time is difficult, increasing the risk of equipment failure and production loss. Therefore, there is a need for efficient strategy proposals based on the analysis of real-time data.

[0960] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0961] In this invention, the server includes: [means for receiving information input by a user;] [means for acquiring related data from a database based on the received information;] [means for analyzing the acquired data using a generative model;] [means for generating a strategy based on the analysis results;] [means for providing the generated strategy to the user;] [means for acquiring the operating status and maintenance records of industrial equipment; and [means for making maintenance predictions for industrial equipment using a machine learning algorithm.] This makes it possible to efficiently manage the operating status and past maintenance records of each piece of equipment and predict the appropriate timing for maintenance.

[0962] A "user" is a person or organization that operates the system and provides input information.

[0963] "Information" means data or requests provided by a user to a server.

[0964] A "database" is a collection of data that stores and manages related information in an organized manner.

[0965] A "generative model" is a system that uses machine learning algorithms to analyze input data and generate a specific output.

[0966] "Analysis" is the process of examining data in detail and drawing specific conclusions or strategies.

[0967] A "strategy" is a plan or policy for achieving a specific objective.

[0968] "Providing" is the act of presenting the generated strategies and information to the user.

[0969] "Industrial equipment" refers to machinery and equipment used within a factory.

[0970] "Operation status" refers to information that indicates the operating state and efficiency of industrial equipment.

[0971] "Maintenance records" refer to the past maintenance history of industrial equipment.

[0972] A "machine learning algorithm" is a computer algorithm that learns patterns and trends from large amounts of data and makes predictions and classifications.

[0973] "Maintenance prediction" is the process of using machine learning algorithms to predict when future maintenance will be required.

[0974] The present invention relates to a data analysis system for supporting maintenance planning and optimization of production lines in industrial facilities. Specific embodiments of this system will be described below.

[0975] System Overview:

[0976] This system has three main components: the user, the server, and the terminal, and includes a series of processes that cover everything from data input to maintenance prediction, strategy generation, and strategy provision. The main processes are information input from the user, data analysis on the server, and provision of the analysis results.

[0977] Hardware and software:

[0978] Server: A server for database management and running machine learning model analysis (e.g., AWS EC2 instance).

[0979] Device: A smartphone or tablet where users can enter information and check strategic proposals.

[0980] Industrial robots: Robots used in factories for data collection and interfacing (e.g., Pepper).

[0981] What the program does:

[0982] Data Entry:

[0983] Users access the system via a chatbot and input the necessary information, for example, to inquire about the next machine that needs maintenance. An intuitive user interface is provided, allowing for quick data entry.

[0984] Data reception:

[0985] The terminal receives input from the user and sends it to the server in a standardized format (e.g., JSON).

[0986] Data Acquisition:

[0987] When the server receives the data sent by the user, it retrieves related information from the database based on that information, such as the operating status of industrial equipment and past maintenance records.

[0988] Data Analysis:

[0989] The server inputs the acquired information into a generative model and analyzes the optimal maintenance targets and production line optimization. The generative model uses a machine learning algorithm (e.g., Random Forest Classifier) ​​to perform highly accurate analysis based on past data and the current situation.

[0990] Strategy Generation:

[0991] The server generates specific strategy proposals based on the analysis results obtained from the generative model. For example, it generates a strategy in the form of "Unit A is the next unit to undergo maintenance."

[0992] Strategy provided:

[0993] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[0994] Examples:

[0995] For example, consider a case where a user types into a chatbot, "Please tell me which machine should be maintained next." The system analyzes past maintenance records and operation data and responds, "The next machine that needs maintenance is Unit A."

[0996] Example prompt sentence:

[0997] "Please tell me which machines will undergo the next maintenance. Machine A has 5,000 operating hours, 30 days before its last maintenance, and an error rate of 5%. Machine B has 3,000 operating hours, 15 days before its last maintenance, and an error rate of 3%. Machine C has 6,000 operating hours, 60 days before its last maintenance, and an error rate of 10%."

[0998] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0999] Step 1:

[1000] The user accesses the chatbot using a terminal and inputs a question such as, "Please tell me which machine should be maintained next." The input data is in text format, and this question is registered in the system.

[1001] Input: User inquiry about the machine to be maintained

[1002] Output: Send a query to the chatbot

[1003] Step 2:

[1004] The terminal receives user input, converts it into a standardized format (JSON), and sends it to the server.

[1005] Input: User text input

[1006] Output: Standardized query data (JSON)

[1007] Step 3:

[1008] The server analyzes the received query data and retrieves the operating status and past maintenance records of the industrial equipment from the relevant database.

[1009] Input: Standardized query data (JSON)

[1010] Output: Operation status and maintenance records of industrial equipment

[1011] Step 4:

[1012] The server inputs the acquired data into a machine learning algorithm (generative model) to make maintenance predictions. Specifically, it identifies the equipment that next requires maintenance using information such as the operating hours, last maintenance date, and error rate for each piece of equipment.

[1013] Input: Operation status and maintenance record data

[1014] Output: Prediction of optimal machine maintenance targets

[1015] Step 5:

[1016] The server generates specific maintenance strategy proposals based on the analysis results obtained from the generative model, and expresses the conclusion in text form, such as "Unit A should be the next to undergo maintenance."

[1017] Input: Maintenance forecast results

[1018] Output: Strategy proposal (text format)

[1019] Step 6:

[1020] The server converts the generated strategy proposal into a standardized format (JSON) and sends it to the terminal.

[1021] Input: Strategy proposal (text format)

[1022] Output: Standardized strategy data (JSON)

[1023] Step 7:

[1024] The terminal analyzes the strategy data received from the server and displays strategy proposals to the user, who then checks the maintenance strategy on the terminal screen and makes decisions based on it.

[1025] Input: Standardized strategy data (JSON)

[1026] Output: Strategy proposals displayed to the user

[1027] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1028] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. In particular, by combining it with an emotion engine that recognizes the user's emotions, more effective strategy proposals can be realized. Specific embodiments of this system are described below.

[1029] System Overview:

[1030] This system encompasses a series of processes: inputting information from the user, retrieving relevant data from a database, analyzing the data using a generative model, generating a strategy, and providing the generated strategy. Furthermore, it uses an emotion engine to recognize the user's emotions and adjusts the strategy analysis based on the results. The system has three main components: a server, a terminal, and a user.

[1031] What the program does:

[1032] Data Entry:

[1033] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot responds intuitively to the user's input, and the emotion engine reads emotions from the input.

[1034] Data reception:

[1035] The device receives input data from the user and sends it to the server in a standardized format (e.g., JSON), including the user's emotional data recognized by the emotion engine.

[1036] Data Acquisition:

[1037] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[1038] Data Analysis:

[1039] The server inputs the acquired information into a generative model and analyzes the optimal player selection and strategy. The generative model uses a machine learning algorithm to perform highly accurate analysis based on past data and the current situation. It also adjusts the strategic analysis so that the analysis results from the emotion engine have an impact.

[1040] Strategy Generation:

[1041] The server generates specific strategy proposals based on the analysis results obtained from the generative model. The generated strategy proposals are written in the form of "It would be best to use pitcher Matsuda in the next game." The server also makes proposals that take the user's emotions into consideration.

[1042] Strategy provided:

[1043] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[1044] Examples:

[1045] scenario:

[1046] Ask the system which pitcher to use in the next game.

[1047] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[1048] 2. The device receives the user's input and sends it to the server in a standardized format (JSON), including the user's emotion as recognized by the emotion engine.

[1049] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[1050] 4. The server analyzes this data using a generative model and identifies the best pitcher based on the results of the emotion engine.

[1051] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game." If the user is feeling nervous, the server adds a message that gives the user a sense of relief, such as, "Don't worry, use pitcher Matsuda."

[1052] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[1053] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[1054] As described above, the system of the present invention combines user input with analysis by the emotion engine to provide fast, flexible, and data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[1055] The processing flow will be explained below.

[1056] Step 1:

[1057] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[1058] Step 2:

[1059] The device receives input data from the user and converts it into JSON format. For example, the converted data will be in the format of "{"query": "Which pitcher is best for the next game?"". The emotion engine also identifies the user's emotion from the user's facial expression and input text, and sends the emotion data to the server.

[1060] Step 3:

[1061] The server receives the JSON data and emotion data sent from the device, analyzes the received data, extracts the necessary information, and then prepares to access the database.

[1062] Step 4:

[1063] The server queries the database based on the received information to retrieve relevant data, specifically the performance data of the team's pitcher from the past 10 games and the most recent performance data of the opposing team's batters.

[1064] Step 5:

[1065] The server preprocesses the acquired data, which includes standardizing, normalizing, and imputing missing values, etc. This process prepares the data for input into the generative model.

[1066] Step 6:

[1067] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and the current situation. Additionally, the extracted emotional data is also input into the model, influencing the analysis.

[1068] Step 7:

[1069] The generative model analyzes the data and sends the results back to the server, such as whether pitcher Matsuda is the best for the next game.

[1070] Step 8:

[1071] The server generates a strategy proposal based on the analysis results obtained from the generative model. The generated strategy proposal is expressed in the form of "It is best to use pitcher Matsuda in the next game." In addition, an additional message (e.g., "Please feel free to use pitcher Matsuda") is generated based on the emotion data to give the user a sense of security.

[1072] Step 9:

[1073] The server formats the generated strategy proposal in JSON format and sends it to the terminal. For example, it may have the format "{"recommendation": "It is best to use pitcher Matsuda in the next game", "additionalMessage": "Please feel free to use pitcher Matsuda"}".

[1074] Step 10:

[1075] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and displays strategy suggestions and additional messages on the user interface.

[1076] Step 11:

[1077] The user checks the strategy suggestion displayed on the device screen, "It is best to use pitcher Matsuda in the next game," along with the additional message, "Please feel free to use pitcher Matsuda." Based on this information, the user decides which pitcher to use in the next game.

[1078] Example 2

[1079] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1080] Conventional strategic planning and scouting systems for sports teams are unable to propose strategies that take user emotions into account, making it difficult to improve the user experience or increase the adoption rate of strategies. Furthermore, the lack of an intuitive interface for dialogue using chatbots can sometimes reduce the accuracy and efficiency of user input. To solve these problems, it is important to recognize user emotions and reflect them in strategic planning.

[1081] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1082] In this invention, the server includes: [means for receiving information input by a user and recognizing emotions using an emotion engine]; [means for retrieving relevant data from a database based on the received information and emotions]; and [means for analyzing the retrieved data and emotions using a generative AI model]. This makes it possible [to quickly provide more accurate strategy proposals while taking into account the user's emotions].

[1083] A "user" is an entity that accesses the system, inputs information, and receives strategic proposals.

[1084] "Input information" is text data that the user provides to the system, including questions and instructions such as which players should be used in the next game.

[1085] An "emotion engine" is software or an algorithm that analyzes information input by a user and recognizes the user's emotions (e.g., tension, anxiety, joy, etc.) based on that information.

[1086] The "database" is a system for storing and managing user-input information and related data based on emotions (for example, players' past performances and opponent data).

[1087] "Related data" refers to information necessary for strategy planning (for example, player performance data and information on the opposing team) that is acquired from a database based on user input.

[1088] A "generative AI model" is a model that uses machine learning algorithms to analyze input data and related data and generate optimal strategic proposals.

[1089] "Analysis" is the process of deriving the optimal strategy based on data obtained using a generative AI model and user emotional data.

[1090] A "strategy" is a specific player selection and tactical policy for the next match proposed based on the results of analysis by the generative AI model.

[1091] "Providing" refers to the act of transmitting the generated strategy from the server to the user via the terminal, and allowing the user to confirm and make a decision.

[1092] A "chatbot" is software that automatically interacts between a user and a system, and is an interface that accepts user input and returns appropriate responses.

[1093] The present invention is a data analysis system for supporting strategic planning and scouting in sports teams, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose more effective strategies. Specific embodiments of this system are described below.

[1094] Overall system configuration

[1095] This system is mainly composed of three components: a server, a terminal, and a user. The server is responsible for accessing the database, analyzing data using a generative AI model, and generating strategies. The terminal receives information input from the user and displays the analysis results and proposals. The user mainly operates the terminal to input information and receive strategy proposals from the system.

[1096] Hardware and software used

[1097] The server is equipped with a high-performance processor and large amounts of memory and storage. Specifically, cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used. MySQL and PostgreSQL are commonly used as databases.

[1098] Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Furthermore, advanced generative models such as OpenAI's GPT-3 are adopted for natural language processing. Sentiment analysis APIs from Microsoft's Azure Cognitive Services can be used as emotion engines.

[1099] What the program does

[1100] User input of information

[1101] Users access the system and use the chatbot to input specific questions, such as which pitcher should be used in the next game. The device receives the user's input and uses an emotion engine to recognize the user's emotions.

[1102] Receiving and processing input data

[1103] The device receives the question and emotion data entered by the user and sends it to the server in a standardized format (e.g., JSON). When the server receives this data, it retrieves related data from a database. For example, if the user enters "Which pitcher should we use in the next game?", the server retrieves the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[1104] Data analysis and strategy generation

[1105] The server inputs the acquired information into a generative AI model, which analyzes the optimal player selection and strategy. The generative AI model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation. It also takes into account the results of the emotion engine and reflects this in its strategic analysis. Based on the analysis results, it generates specific strategy suggestions, such as "It is best to use a specific pitcher in the next game."

[1106] Providing strategic proposals

[1107] The server sends the generated strategy proposal to the terminal, which displays it to the user, who then checks the generated strategy on the terminal and decides on a pitcher for the next game based on it.

[1108] Specific examples

[1109] An example of a prompt is:

[1110] In response to the question, "Which pitcher should we use in the next game?", the system analyzes the situation and makes strategic suggestions such as, "It would be best to use a specific pitcher in the next game. You may be nervous, but rest assured considering their track record."

[1111] In this way, the system of the present invention can combine user input with analysis by the emotion engine to quickly and flexibly provide data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[1112] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1113] Step 1:

[1114] Users access the system using a web browser or mobile app. They input a specific question in natural language into the chatbot interface, such as "Which pitcher should be used in the next game?" The emotion engine then analyzes the user's input and identifies emotions such as "I'm nervous."

[1115] Input: User's question (in text format)

[1116] Output: User's question and emotion data (text format and emotion labels)

[1117] Step 2:

[1118] The device receives questions and emotion data entered by the user, converts this data into a standardized format (e.g., JSON format), and sends it to the server.

[1119] Input: User question and emotion data (text format and emotion labels)

[1120] Output: Standardized data (JSON format)

[1121] Step 3:

[1122] The server receives the JSON data sent from the device, parses it, and sends a query to the database. The query contains information related to the user's question (e.g., the past performance of the team's pitcher, the performance of the opposing team's batters).

[1123] Input: Standardized data (JSON format)

[1124] Output: A list of database queries and the associated data retrieved.

[1125] Step 4:

[1126] The server retrieves relevant information from a database, including the past performance of the team's pitchers and the performance of the opposing batters, and stores the retrieved data temporarily for use in the next analysis step.

[1127] Input: Database query

[1128] Output: Related data (e.g., pitcher's past performance, batter's performance)

[1129] Step 5:

[1130] The server inputs the acquired relevant data into the generative AI model and begins analysis. The generative AI model analyzes the data using machine learning algorithms (e.g., TensorFlow or PyTorch) and proposes optimal player selection. It also incorporates the results of the emotion engine into the analysis and makes adjustments based on emotions.

[1131] Input: Related data (e.g., pitcher's past performance, batter's performance) and emotion data

[1132] Output: Analysis results (e.g., optimal pitcher suggestions)

[1133] Step 6:

[1134] The server generates specific strategy suggestions based on the analysis results obtained from the generative AI model. For example, it generates a strategy statement such as, "It is best to use a specific pitcher in the next game." The message is also adjusted to reflect the user's emotions.

[1135] Input: Analysis results (e.g., optimal pitcher suggestions)

[1136] Output: Strategy proposal (strategy statement in text format)

[1137] Step 7:

[1138] The server sends the generated strategy proposal to the terminal, which displays the proposal to the user. The user checks the proposed strategy on the terminal and decides on a pitcher for the next game based on the information.

[1139] Input: Strategy proposal (strategy statement in text format)

[1140] Output: Providing strategies to the user (strategy suggestions displayed on the device screen)

[1141] (Application example 2)

[1142] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1143] In today's market, users' shopping experiences are becoming increasingly diverse, and they are seeking personalized recommendations tailored to their individual needs. However, systems that adequately meet these demands are still limited. Furthermore, technology for generating appropriate product recommendations and messages based on users' emotions has not been fully established. Therefore, there is a need to reduce the stress and difficulties users experience when shopping and provide a more comfortable and satisfying shopping experience.

[1144] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring related data from a database based on information input by a user and emotional data of the user, means for analyzing the acquired data and emotional data using a generative model, and means for generating strategies or product proposals based on the analysis results. This enables personalized product proposals that reflect the user's emotions.

[1145] The "means for receiving information input by a user" is a function that allows the system to receive information such as text or voice input by a user via a terminal.

[1146] The "means for retrieving related data from a database based on received information and user emotion data" is a function for searching and retrieving related information from a database using information received from a user and the user emotion data analyzed by the emotion engine.

[1147] "Means for analyzing acquired data and emotion data using a generative model" refers to a function for inputting information and emotion data acquired from a database into a generative model based on a machine learning algorithm and performing analysis.

[1148] The "means for generating a strategy or product proposal based on the analysis results" is a function for generating a strategy or product proposal in a concrete form based on the analysis results obtained by the generative model.

[1149] The "means for providing the generated strategy or product proposal to the user" is a function for presenting the generated strategy or product proposal to the user via the terminal.

[1150] This invention is a data analysis system for mail-order sites that recognizes user emotions and makes appropriate product suggestions based on those emotions. A specific embodiment of this system is described below.

[1151] System configuration

[1152] This system encompasses a series of processes: inputting information from the user, retrieving related data from a database, analyzing the data using a generative model, generating suggestions, and delivering the generated suggestions. It also uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions based on the results. The system has three main components: a server, a terminal, and a user.

[1153] Hardware and software used

[1154] Hardware:

[1155] Smartphone (device)

[1156] server

[1157] software:

[1158] Emotion Engine API (Emotion Analysis)

[1159] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1160] Database System

[1161] Natural Language Generation (NLG) models

[1162] UI engine (e.g. React Native)

[1163] Network Communication Interface

[1164] Detailed explanation of the process

[1165] Data Entry and Receipt

[1166] A user enters product-related keywords and review content into a shopping app. The emotion engine reads emotions from the user's input and facial expressions (using the smartphone camera). The input data and emotion data are sent from the smartphone to the server in JSON format.

[1167] Data Acquisition

[1168] The server retrieves related product information, reviews, and recommended product data from a database based on the received user input data and emotion data. The connected database includes a database that stores detailed product information and user reviews.

[1169] Data analysis

[1170] The server inputs this acquired information into a generative model and makes product recommendations that take the user's emotional state into account. Machine learning libraries such as TensorFlow and PyTorch are used to analyze the generative model.

[1171] Proposal generation and delivery

[1172] The server generates product suggestions based on the analysis results obtained from the generative model, corresponding to the user's emotions. The generated product suggestions are presented with a message, such as "These earphones have sound quality that will relax you." The suggested products and messages are sent to a smartphone app and displayed to the user.

[1173] Specific examples

[1174] scenario

[1175] Here is a specific usage scenario where a user enters "I want new earphones" into a shopping app.

[1176] Prompt Sentence Examples

[1177] "I want new earphones."

[1178] This system allows users to receive product suggestions that match their emotions, resulting in a more comfortable and satisfying shopping experience.

[1179] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1180] Step 1:

[1181] Users enter product-related keywords and review content into the shopping app. At this time, the smartphone camera captures the user's facial expressions, which are then analyzed by the emotion engine API to generate emotion data. The input here is the user's text input and facial expression data, and emotion data is output based on this.

[1182] Step 2:

[1183] The device receives the user's input data and the emotion data recognized by the emotion engine, and sends them to the server in a standardized format (e.g., JSON). In this process, the text input data and emotion data are transferred together to the server.

[1184] Step 3:

[1185] The server analyzes the received user input data and emotion data and retrieves related information from the database based on the analysis. Specifically, detailed product information, user reviews, and related ratings are retrieved from the database. Here, the input data and emotion data are used to query the relevant database and retrieve the relevant product information.

[1186] Step 4:

[1187] The server inputs the acquired data and emotional data into a generative model to generate optimal product suggestions corresponding to the user's emotional state. At this time, each piece of data is analyzed using a machine learning algorithm (e.g., TensorFlow, PyTorch). The input data is product information and emotional data acquired from a database, and product suggestions are output based on that.

[1188] Step 5:

[1189] The server generates a suggested message based on the analysis results obtained from the generative model. For example, a specific message such as "These earphones have a sound quality that will relax you" is generated. The generated message has appropriate content that reflects the user's emotional state.

[1190] Step 6:

[1191] The server sends the generated product proposal and proposal message to the terminal, which receives them and displays them to the user. The output here is the proposed product and message displayed on the user's terminal.

[1192] Step 7:

[1193] Users can check the suggested products and messages on their device screen and consider purchasing the products based on them. By receiving suggestions that take their emotions into consideration, users can have a more comfortable shopping experience.

[1194] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1195] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1196] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1197] [Fourth embodiment]

[1198] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1199] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1200] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1201] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1202] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1203] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1204] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1205] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1206] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1207] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1208] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1209] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1210] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1211] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. Specific embodiments of this system will be described below.

[1212] System Overview:

[1213] This system includes a series of processes: input of information from users, acquisition of related data from a database, data analysis using a generative model, strategy generation, and provision of the generated strategy. The system has three main components: a server, a terminal, and a user.

[1214] What the program does:

[1215] Data Entry:

[1216] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot provides an intuitive user interface and enables quick data entry.

[1217] Data reception:

[1218] The terminal receives input from the user and sends it to the server. The input data is sent to the server in a standardized format (e.g., JSON).

[1219] Data Acquisition:

[1220] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[1221] Data Analysis:

[1222] The server inputs the acquired information into a generative model to analyze optimal player selection and strategy. The generative model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation.

[1223] Strategy Generation:

[1224] The server generates specific strategy proposals based on the analysis results obtained from the generative model, for example, by proposing a strategy in the form of "It would be optimal to use pitcher Matsuda in the next game."

[1225] Strategy provided:

[1226] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[1227] Examples:

[1228] scenario:

[1229] Ask the system which pitcher to use in the next game.

[1230] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[1231] 2. The device receives the user's input and sends it to the server in a standardized format (JSON).

[1232] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[1233] 4. The server analyzes this data using a generative model to identify the best pitcher.

[1234] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game."

[1235] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[1236] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[1237] As described above, the system of the present invention can analyze data based on user input and provide instant and flexible strategy proposals, enabling sports teams to quickly and effectively develop tactics and improve their chances of winning a game.

[1238] The processing flow will be explained below.

[1239] Step 1:

[1240] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[1241] Step 2:

[1242] The terminal receives input data from the user. The received data is converted into JSON format and then sent to the server. For example, the converted data will be in the format "{"query": "Which pitcher is best for the next game?"".

[1243] Step 3:

[1244] The server receives the JSON data sent from the device, parses the received data, extracts the necessary information, and then begins preparations to access the database.

[1245] Step 4:

[1246] The server queries the database to retrieve relevant data, specifically the performance data for the team's pitchers over the past 10 games and the most recent performance data for the opposing batters.

[1247] Step 5:

[1248] The server preprocesses the acquired data, including standardizing, normalizing, and imputing missing values, so that the data is ready to be input to the generative model.

[1249] Step 6:

[1250] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and current situation.

[1251] Step 7:

[1252] The generative model analyzes the data and sends the results back to the server, such as "Pitcher Matsuda is the best for the next game."

[1253] Step 8:

[1254] The server receives the results from the generative model and generates a strategy proposal based on the analysis results. The strategy proposal is a specific statement such as, "It would be best to use pitcher Matsuda in the next game."

[1255] Step 9:

[1256] The server formats the generated strategy proposal in JSON format and sends it to the device, for example, "{"recommendation": "It is best to use pitcher Matsuda in the next game"}".

[1257] Step 10:

[1258] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and then displays the strategy proposal on the user interface.

[1259] Step 11:

[1260] The user checks the strategy suggestion displayed on the device screen, saying, "It is best to use pitcher Matsuda in the next game." Based on this information, the user decides which pitcher to use in the next game.

[1261] Example 1

[1262] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1263] There is a growing need for a system that can quickly and effectively analyze data and propose optimal strategies in the strategic planning and scouting of sports teams. Conventional methods require the time-consuming task of collecting and analyzing data individually, making it difficult to plan strategies efficiently. The objective of this invention is to provide a system that can be intuitively used by users and that centrally performs everything from data analysis to strategy proposals.

[1264] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1265] In this invention, the server includes: [terminal means for receiving information input by a user; [means for transmitting the information received by the terminal to the server in a standardized format; [means for acquiring related data from a database based on the information received by the server; [means for performing analysis using a generative model with the acquired data by the server; [means for the server to generate a strategy based on the analysis results; and [means for providing the generated strategy to the user via the terminal.] This enables the user to easily input the necessary information and quickly acquire a strategy based on the analysis results.

[1266] A "user" is an entity that uses the system to input information and receives strategies provided as analysis results.

[1267] A "terminal" is a device that receives information from a user and transmits it to a server. Examples include PCs, smartphones, and tablets.

[1268] The "server" is a computer system that retrieves relevant data from a database based on received information, analyzes the data using a generative model, and generates and provides a strategy.

[1269] A "database" is a system that stores related information and provides data in response to queries from a server.

[1270] A "generative model" is a model that uses machine learning algorithms to analyze data and identify optimal strategies.

[1271] A "chatbot" is an interface for collecting information through dialogue with users and sending it to a system.

[1272] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate analytical results.

[1273] A "prompt sentence" is an input sentence given to a generative AI model, and is the basic information that the model uses for analysis.

[1274] A "standardized format" is a format in which information is structured according to certain rules and is primarily used for exchanging data between systems. Examples include the JSON format.

[1275] A "strategy" is a specific action plan proposed based on the results of analysis by the generative model.

[1276] The "analysis result" is the final output of the analysis performed by the generative model based on the input data.

[1277] The present invention relates to a data analysis system for supporting strategic planning and scouting for sports teams. Specific embodiments of this system will be described below.

[1278] The system's main components are a user, a device, and a server. The user inputs information into the system via a chatbot. The device receives the information and sends it to the server in a standardized format (e.g., JSON). The server then retrieves relevant data from a database based on the information and performs data analysis using a generative AI model. Based on the analysis results, the server generates a strategy and provides it to the user via the device.

[1279] Hardware and software used

[1280] Server: A high-performance server for performing data analysis and strategy generation (e.g., Amazon Web Services, Google Cloud Platform)

[1281] Terminal: The device on which the user enters input and confirms strategic proposals (e.g., PC, smartphone, tablet)

[1282] Chatbot interface: Tools that allow users to input information intuitively (e.g., Dialogflow, Microsoft Bot Framework)

[1283] Generative AI models: Machine learning models for data analysis (e.g., TensorFlow, PyTorch)

[1284] Operation flow

[1285] 1. A user inputs a query such as "Which pitcher should be used in the next game?" in natural language via a chatbot. For example, a user opens the chatbot's user interface from a smartphone or PC browser, inputs a query in the text field, and presses the send button.

[1286] 2. The terminal receives input from the user and converts the data into a standardized format (JSON). The terminal parses the user's input text and converts it into JSON format such as { "query": "Which pitcher should be used in the next game?"}

[1287] 3. The device sends the converted data to the server. The device sends the JSON data via the network as a POST request to a specific API endpoint on the server.

[1288] 4. The server receives the data sent from the device. The server's API receives the request and extracts the JSON data from the request body.

[1289] 5. The server retrieves the necessary relevant information from the database based on the received data. The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[1290] 6. The server inputs the acquired data into a generative AI model for data analysis. The server invokes a machine learning model (e.g., TensorFlow) and passes the performance data as input to the model. The model performs the analysis and identifies the optimal pitcher.

[1291] 7. The server generates a specific strategy proposal based on the analysis results obtained from the generative AI model. The server applies the analysis results (e.g., pitcher's name) to a template for expressing them in natural language, and generates a sentence such as, "It is best to use pitcher Matsuda in the next game."

[1292] 8. The server sends the generated strategy proposal to the terminal. The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[1293] 9. The terminal displays the strategy proposal received from the server to the user. The terminal extracts the strategy proposal from the response body and displays the proposal on the chatbot's UI.

[1294] 10. The user checks the strategy suggestions displayed on the device screen and makes a decision based on them. The user reads the suggestions displayed on the chatbot screen and decides on the pitcher for the next game.

[1295] Examples of prompt statements

[1296] "Which pitcher should we use in the next game?

[1297] Analyze the optimal pitcher based on past performance and the performance of opposing batters, and propose a specific strategy.

[1298] In this way, this system can quickly and effectively analyze data and propose optimal strategies to sports teams, significantly improving the efficiency of strategic planning and scouting for sports teams.

[1299] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1300] Step 1:

[1301] A user accesses the system and inputs the query "Which pitcher should be used in the next game?" in natural language through the chatbot.

[1302] Input: The user enters a query into the chatbot's input field and presses the submit button.

[1303] Output: A query in natural language form is generated.

[1304] Specific operation: The user opens the chatbot screen in a smartphone or PC browser, enters "Which pitcher should be used in the next game?" in the text field, and presses the send button.

[1305] Step 2:

[1306] The terminal receives input from the user and converts the information into a standardized format (JSON).

[1307] Input: The natural language query entered by the user.

[1308] Output: Data in a standardized format (e.g. JSON).

[1309] Specific operation: The device parses the user's input text and converts it into JSON format, such as { "query": "Which pitcher should be used in the next game?"}.

[1310] Step 3:

[1311] The terminal transmits the converted data to the server.

[1312] Input: A query expressed in a standardized format (JSON).

[1313] Output: A POST request to the server.

[1314] Specific operation: The terminal sends JSON data via the network as a POST request to a specific API endpoint on the server.

[1315] Step 4:

[1316] The server receives the data sent from the terminal.

[1317] Input: JSON format data sent from the terminal.

[1318] Output: Internal data structure that parses the received JSON data.

[1319] Specific operation: The server API receives the request and extracts the JSON data from the request body.

[1320] Step 5:

[1321] The server retrieves the necessary relevant information from a database based on the received data.

[1322] Input: User query in JSON format.

[1323] Output: Relevant database entries (e.g. pitcher's past performance, opponent's performance).

[1324] Specific operation: The server executes a database query (e.g. SELECT FROM pitchers WHERE team_id='my team ID';) to retrieve the past performance of the team's pitchers and the performance of the opposing team's batters.

[1325] Step 6:

[1326] The server inputs the acquired data into a generative AI model and performs data analysis.

[1327] Input: Relevant data retrieved from the database.

[1328] Output: Analysis results from the generative model (e.g., optimal pitcher).

[1329] How it works: The server calls a machine learning model (e.g., TensorFlow) and passes the acquired performance data as input to the model. The model then performs analysis and identifies the best pitcher.

[1330] Step 7:

[1331] The server generates specific strategy proposals based on the analysis results obtained from the generative AI model.

[1332] Input: Analysis results from the generative AI model.

[1333] Output: Strategy suggestions in natural language format.

[1334] Specific operation: The server applies the model output (e.g., the pitcher's name) to a template for expressing it in natural language, and generates the sentence, "It would be best to use pitcher Matsuda in the next game."

[1335] Step 8:

[1336] The server transmits the generated strategy proposal to the terminal.

[1337] Input: A strategy proposal expressed in natural language.

[1338] Output: JSON data containing the strategy proposal as a response to the terminal.

[1339] Specific operation: The server creates the generated strategy statement in JSON format and returns a response to the terminal.

[1340] Step 9:

[1341] The terminal displays the strategy proposal received from the server to the user.

[1342] Input: JSON data sent from the server.

[1343] Output: Strategy proposals displayed on the user interface.

[1344] Specific operation: The terminal extracts strategy proposals from the response body and displays them on the chatbot's UI.

[1345] Step 10:

[1346] The user checks the strategy proposals displayed on the terminal screen and makes a decision based on them.

[1347] Input: Strategy proposals displayed on the terminal screen.

[1348] Output: Deciding which pitcher to use in the next game.

[1349] Specific operation: The user confirms the strategy suggestion displayed on the chatbot screen, "It would be best to use pitcher Matsuda in the next game," and decides to pitch Matsuda for the next game.

[1350] (Application example 1)

[1351] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1352] Planning maintenance for industrial equipment and optimizing production lines are important issues for efficient factory operation. However, manually managing the operating status and past maintenance records of each piece of equipment and performing maintenance at the appropriate time is difficult, increasing the risk of equipment failure and production loss. Therefore, there is a need for efficient strategy proposals based on the analysis of real-time data.

[1353] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1354] In this invention, the server includes: [means for receiving information input by a user;] [means for acquiring related data from a database based on the received information;] [means for analyzing the acquired data using a generative model;] [means for generating a strategy based on the analysis results;] [means for providing the generated strategy to the user;] [means for acquiring the operating status and maintenance records of industrial equipment; and [means for making maintenance predictions for industrial equipment using a machine learning algorithm.] This makes it possible to efficiently manage the operating status and past maintenance records of each piece of equipment and predict the appropriate timing for maintenance.

[1355] A "user" is a person or organization that operates the system and provides input information.

[1356] "Information" means data or requests provided by a user to a server.

[1357] A "database" is a collection of data that stores and manages related information in an organized manner.

[1358] A "generative model" is a system that uses machine learning algorithms to analyze input data and generate a specific output.

[1359] "Analysis" is the process of examining data in detail and drawing specific conclusions or strategies.

[1360] A "strategy" is a plan or policy for achieving a specific objective.

[1361] "Providing" is the act of presenting the generated strategies and information to the user.

[1362] "Industrial equipment" refers to machinery and equipment used within a factory.

[1363] "Operation status" refers to information that indicates the operating state and efficiency of industrial equipment.

[1364] "Maintenance records" refer to the past maintenance history of industrial equipment.

[1365] A "machine learning algorithm" is a computer algorithm that learns patterns and trends from large amounts of data and makes predictions and classifications.

[1366] "Maintenance prediction" is the process of using machine learning algorithms to predict when future maintenance will be required.

[1367] The present invention relates to a data analysis system for supporting maintenance planning and optimization of production lines in industrial facilities. Specific embodiments of this system will be described below.

[1368] System Overview:

[1369] This system has three main components: the user, the server, and the terminal, and includes a series of processes that cover everything from data input to maintenance prediction, strategy generation, and strategy provision. The main processes are information input from the user, data analysis on the server, and provision of the analysis results.

[1370] Hardware and software:

[1371] Server: A server for database management and running machine learning model analysis (e.g., AWS EC2 instance).

[1372] Device: A smartphone or tablet where users can enter information and check strategic proposals.

[1373] Industrial robots: Robots used in factories for data collection and interfacing (e.g., Pepper).

[1374] What the program does:

[1375] Data Entry:

[1376] Users access the system via a chatbot and input the necessary information, for example, to inquire about the next machine that needs maintenance. An intuitive user interface is provided, allowing for quick data entry.

[1377] Data reception:

[1378] The terminal receives input from the user and sends it to the server in a standardized format (e.g., JSON).

[1379] Data Acquisition:

[1380] When the server receives the data sent by the user, it retrieves related information from the database based on that information, such as the operating status of industrial equipment and past maintenance records.

[1381] Data Analysis:

[1382] The server inputs the acquired information into a generative model and analyzes the optimal maintenance targets and production line optimization. The generative model uses a machine learning algorithm (e.g., Random Forest Classifier) ​​to perform highly accurate analysis based on past data and the current situation.

[1383] Strategy Generation:

[1384] The server generates specific strategy proposals based on the analysis results obtained from the generative model. For example, it generates a strategy in the form of "Unit A is the next unit to undergo maintenance."

[1385] Strategy provided:

[1386] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[1387] Examples:

[1388] For example, consider a case where a user types into a chatbot, "Please tell me which machine should be maintained next." The system analyzes past maintenance records and operation data and responds, "The next machine that needs maintenance is Unit A."

[1389] Example prompt sentence:

[1390] "Please tell me which machines will undergo the next maintenance. Machine A has 5,000 operating hours, 30 days before its last maintenance, and an error rate of 5%. Machine B has 3,000 operating hours, 15 days before its last maintenance, and an error rate of 3%. Machine C has 6,000 operating hours, 60 days before its last maintenance, and an error rate of 10%."

[1391] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1392] Step 1:

[1393] The user accesses the chatbot using a terminal and inputs a question such as, "Please tell me which machine should be maintained next." The input data is in text format, and this question is registered in the system.

[1394] Input: User inquiry about the machine to be maintained

[1395] Output: Send a query to the chatbot

[1396] Step 2:

[1397] The terminal receives user input, converts it into a standardized format (JSON), and sends it to the server.

[1398] Input: User text input

[1399] Output: Standardized query data (JSON)

[1400] Step 3:

[1401] The server analyzes the received query data and retrieves the operating status and past maintenance records of the industrial equipment from the relevant database.

[1402] Input: Standardized query data (JSON)

[1403] Output: Operation status and maintenance records of industrial equipment

[1404] Step 4:

[1405] The server inputs the acquired data into a machine learning algorithm (generative model) to make maintenance predictions. Specifically, it identifies the equipment that next requires maintenance using information such as the operating hours, last maintenance date, and error rate for each piece of equipment.

[1406] Input: Operation status and maintenance record data

[1407] Output: Prediction of optimal machine maintenance targets

[1408] Step 5:

[1409] The server generates specific maintenance strategy proposals based on the analysis results obtained from the generative model, and expresses the conclusion in text form, such as "Unit A should be the next to undergo maintenance."

[1410] Input: Maintenance forecast results

[1411] Output: Strategy proposal (text format)

[1412] Step 6:

[1413] The server converts the generated strategy proposal into a standardized format (JSON) and sends it to the terminal.

[1414] Input: Strategy proposal (text format)

[1415] Output: Standardized strategy data (JSON)

[1416] Step 7:

[1417] The terminal analyzes the strategy data received from the server and displays strategy proposals to the user, who then checks the maintenance strategy on the terminal screen and makes decisions based on it.

[1418] Input: Standardized strategy data (JSON)

[1419] Output: Strategy proposals displayed to the user

[1420] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1421] The present invention relates to a data analysis system for supporting strategic planning and scouting in sports teams. In particular, by combining it with an emotion engine that recognizes the user's emotions, more effective strategy proposals can be realized. Specific embodiments of this system are described below.

[1422] System Overview:

[1423] This system encompasses a series of processes: inputting information from the user, retrieving relevant data from a database, analyzing the data using a generative model, generating a strategy, and providing the generated strategy. Furthermore, it uses an emotion engine to recognize the user's emotions and adjusts the strategy analysis based on the results. The system has three main components: a server, a terminal, and a user.

[1424] What the program does:

[1425] Data Entry:

[1426] Users access the system through a chatbot and input the necessary information (e.g., which pitcher should be used in the next game). The chatbot responds intuitively to the user's input, and the emotion engine reads emotions from the input.

[1427] Data reception:

[1428] The device receives input data from the user and sends it to the server in a standardized format (e.g., JSON), including the user's emotional data recognized by the emotion engine.

[1429] Data Acquisition:

[1430] When the server receives the data sent by the user, it retrieves relevant information from the database based on that information. For example, if the user inputs "Which pitcher should we use in the next game?", the server will retrieve the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[1431] Data Analysis:

[1432] The server inputs the acquired information into a generative model and analyzes the optimal player selection and strategy. The generative model uses a machine learning algorithm to perform highly accurate analysis based on past data and the current situation. It also adjusts the strategic analysis so that the analysis results from the emotion engine have an impact.

[1433] Strategy Generation:

[1434] The server generates specific strategy proposals based on the analysis results obtained from the generative model. The generated strategy proposals are written in the form of "It would be best to use pitcher Matsuda in the next game." The server also makes proposals that take the user's emotions into consideration.

[1435] Strategy provided:

[1436] The strategy proposals sent from the server are provided to the user via the terminal, where the user can check the generated strategies on the terminal screen and make decisions based on them.

[1437] Examples:

[1438] scenario:

[1439] Ask the system which pitcher to use in the next game.

[1440] 1. User: Type into the chatbot, "Which pitcher should we use in the next game?"

[1441] 2. The device receives the user's input and sends it to the server in a standardized format (JSON), including the user's emotion as recognized by the emotion engine.

[1442] 3. The server receives the user's input and retrieves the past performance of the team's pitcher and the performance of the opposing team's batters from the database.

[1443] 4. The server analyzes this data using a generative model and identifies the best pitcher based on the results of the emotion engine.

[1444] 5. The server generates a strategy that says, "It is best to use pitcher Matsuda in the next game." If the user is feeling nervous, the server adds a message that gives the user a sense of relief, such as, "Don't worry, use pitcher Matsuda."

[1445] 6. The server sends the generated strategy to the terminal, which displays it to the user.

[1446] 7. The user checks the strategy on the device screen and decides on the pitcher for the next game based on it.

[1447] As described above, the system of the present invention combines user input with analysis by the emotion engine to provide fast, flexible, and data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[1448] The processing flow will be explained below.

[1449] Step 1:

[1450] The user inputs a question to the chatbot, such as "Which pitcher should be used in the next game?", and clicks the submit button. The input data is sent to the system through the user interface.

[1451] Step 2:

[1452] The device receives input data from the user and converts it into JSON format. For example, the converted data will be in the format of "{"query": "Which pitcher is best for the next game?"". The emotion engine also identifies the user's emotion from the user's facial expression and input text, and sends the emotion data to the server.

[1453] Step 3:

[1454] The server receives the JSON data and emotion data sent from the device, analyzes the received data, extracts the necessary information, and then prepares to access the database.

[1455] Step 4:

[1456] The server queries the database based on the received information to retrieve relevant data, specifically the performance data of the team's pitcher from the past 10 games and the most recent performance data of the opposing team's batters.

[1457] Step 5:

[1458] The server preprocesses the acquired data, which includes standardizing, normalizing, and imputing missing values, etc. This process prepares the data for input into the generative model.

[1459] Step 6:

[1460] The server inputs the preprocessed data into a generative model, which uses machine learning algorithms to analyze the optimal pitcher based on past performance and the current situation. Additionally, the extracted emotional data is also input into the model, influencing the analysis.

[1461] Step 7:

[1462] The generative model analyzes the data and sends the results back to the server, such as whether pitcher Matsuda is the best for the next game.

[1463] Step 8:

[1464] The server generates a strategy proposal based on the analysis results obtained from the generative model. The generated strategy proposal is expressed in the form of "It is best to use pitcher Matsuda in the next game." In addition, an additional message (e.g., "Please feel free to use pitcher Matsuda") is generated based on the emotion data to give the user a sense of security.

[1465] Step 9:

[1466] The server formats the generated strategy proposal in JSON format and sends it to the terminal. For example, it may have the format "{"recommendation": "It is best to use pitcher Matsuda in the next game", "additionalMessage": "Please feel free to use pitcher Matsuda"}".

[1467] Step 10:

[1468] The terminal parses the JSON data received from the server, converts it into a format suitable for the user interface, and displays strategy suggestions and additional messages on the user interface.

[1469] Step 11:

[1470] The user checks the strategy suggestion displayed on the device screen, "It is best to use pitcher Matsuda in the next game," along with the additional message, "Please feel free to use pitcher Matsuda." Based on this information, the user decides which pitcher to use in the next game.

[1471] Example 2

[1472] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1473] Conventional strategic planning and scouting systems for sports teams are unable to propose strategies that take user emotions into account, making it difficult to improve the user experience or increase the adoption rate of strategies. Furthermore, the lack of an intuitive interface for dialogue using chatbots can sometimes reduce the accuracy and efficiency of user input. To solve these problems, it is important to recognize user emotions and reflect them in strategic planning.

[1474] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1475] In this invention, the server includes: [means for receiving information input by a user and recognizing emotions using an emotion engine]; [means for retrieving relevant data from a database based on the received information and emotions]; and [means for analyzing the retrieved data and emotions using a generative AI model]. This makes it possible [to quickly provide more accurate strategy proposals while taking into account the user's emotions].

[1476] A "user" is an entity that accesses the system, inputs information, and receives strategic proposals.

[1477] "Input information" is text data that the user provides to the system, including questions and instructions such as which players should be used in the next game.

[1478] An "emotion engine" is software or an algorithm that analyzes information input by a user and recognizes the user's emotions (e.g., tension, anxiety, joy, etc.) based on that information.

[1479] The "database" is a system for storing and managing user-input information and related data based on emotions (for example, players' past performances and opponent data).

[1480] "Related data" refers to information necessary for strategy planning (for example, player performance data and information on the opposing team) that is acquired from a database based on user input.

[1481] A "generative AI model" is a model that uses machine learning algorithms to analyze input data and related data and generate optimal strategic proposals.

[1482] "Analysis" is the process of deriving the optimal strategy based on data obtained using a generative AI model and user emotional data.

[1483] A "strategy" is a specific player selection and tactical policy for the next match proposed based on the results of analysis by the generative AI model.

[1484] "Providing" refers to the act of transmitting the generated strategy from the server to the user via the terminal, and allowing the user to confirm and make a decision.

[1485] A "chatbot" is software that automatically interacts between a user and a system, and is an interface that accepts user input and returns appropriate responses.

[1486] The present invention is a data analysis system for supporting strategic planning and scouting in sports teams, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose more effective strategies. Specific embodiments of this system are described below.

[1487] Overall system configuration

[1488] This system is mainly composed of three components: a server, a terminal, and a user. The server is responsible for accessing the database, analyzing data using a generative AI model, and generating strategies. The terminal receives information input from the user and displays the analysis results and proposals. The user mainly operates the terminal to input information and receive strategy proposals from the system.

[1489] Hardware and software used

[1490] The server is equipped with a high-performance processor and large amounts of memory and storage. Specifically, cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used. MySQL and PostgreSQL are commonly used as databases.

[1491] Machine learning libraries such as TensorFlow and PyTorch are used for generative AI models. Furthermore, advanced generative models such as OpenAI's GPT-3 are adopted for natural language processing. Sentiment analysis APIs from Microsoft's Azure Cognitive Services can be used as emotion engines.

[1492] What the program does

[1493] User input of information

[1494] Users access the system and use the chatbot to input specific questions, such as which pitcher should be used in the next game. The device receives the user's input and uses an emotion engine to recognize the user's emotions.

[1495] Receiving and processing input data

[1496] The device receives the question and emotion data entered by the user and sends it to the server in a standardized format (e.g., JSON). When the server receives this data, it retrieves related data from a database. For example, if the user enters "Which pitcher should we use in the next game?", the server retrieves the past performances of the team's pitchers and the performances of the opposing team's batters from the database.

[1497] Data analysis and strategy generation

[1498] The server inputs the acquired information into a generative AI model, which analyzes the optimal player selection and strategy. The generative AI model uses machine learning algorithms to perform highly accurate analysis based on past data and the current situation. It also takes into account the results of the emotion engine and reflects this in its strategic analysis. Based on the analysis results, it generates specific strategy suggestions, such as "It is best to use a specific pitcher in the next game."

[1499] Providing strategic proposals

[1500] The server sends the generated strategy proposal to the terminal, which displays it to the user, who then checks the generated strategy on the terminal and decides on a pitcher for the next game based on it.

[1501] Specific examples

[1502] An example of a prompt is:

[1503] In response to the question, "Which pitcher should we use in the next game?", the system analyzes the situation and makes strategic suggestions such as, "It would be best to use a specific pitcher in the next game. You may be nervous, but rest assured considering their track record."

[1504] In this way, the system of the present invention can combine user input with analysis by the emotion engine to quickly and flexibly provide data-based strategy proposals, enabling sports teams to quickly and effectively plan tactics and improve their chances of winning a game.

[1505] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1506] Step 1:

[1507] Users access the system using a web browser or mobile app. They input a specific question in natural language into the chatbot interface, such as "Which pitcher should be used in the next game?" The emotion engine then analyzes the user's input and identifies emotions such as "I'm nervous."

[1508] Input: User's question (in text format)

[1509] Output: User's question and emotion data (text format and emotion labels)

[1510] Step 2:

[1511] The device receives questions and emotion data entered by the user, converts this data into a standardized format (e.g., JSON format), and sends it to the server.

[1512] Input: User question and emotion data (text format and emotion labels)

[1513] Output: Standardized data (JSON format)

[1514] Step 3:

[1515] The server receives the JSON data sent from the device, parses it, and sends a query to the database. The query contains information related to the user's question (e.g., the past performance of the team's pitcher, the performance of the opposing team's batters).

[1516] Input: Standardized data (JSON format)

[1517] Output: A list of database queries and the associated data retrieved.

[1518] Step 4:

[1519] The server retrieves relevant information from a database, including the past performance of the team's pitchers and the performance of the opposing batters, and stores the retrieved data temporarily for use in the next analysis step.

[1520] Input: Database query

[1521] Output: Related data (e.g., pitcher's past performance, batter's performance)

[1522] Step 5:

[1523] The server inputs the acquired relevant data into the generative AI model and begins analysis. The generative AI model analyzes the data using machine learning algorithms (e.g., TensorFlow or PyTorch) and proposes optimal player selection. It also incorporates the results of the emotion engine into the analysis and makes adjustments based on emotions.

[1524] Input: Related data (e.g., pitcher's past performance, batter's performance) and emotion data

[1525] Output: Analysis results (e.g., optimal pitcher suggestions)

[1526] Step 6:

[1527] The server generates specific strategy suggestions based on the analysis results obtained from the generative AI model. For example, it generates a strategy statement such as, "It is best to use a specific pitcher in the next game." The message is also adjusted to reflect the user's emotions.

[1528] Input: Analysis results (e.g., optimal pitcher suggestions)

[1529] Output: Strategy proposal (strategy statement in text format)

[1530] Step 7:

[1531] The server sends the generated strategy proposal to the terminal, which displays the proposal to the user. The user checks the proposed strategy on the terminal and decides on a pitcher for the next game based on the information.

[1532] Input: Strategy proposal (strategy statement in text format)

[1533] Output: Providing strategies to the user (strategy suggestions displayed on the device screen)

[1534] (Application example 2)

[1535] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1536] In today's market, users' shopping experiences are becoming increasingly diverse, and they are seeking personalized recommendations tailored to their individual needs. However, systems that adequately meet these demands are still limited. Furthermore, technology for generating appropriate product recommendations and messages based on users' emotions has not been fully established. Therefore, there is a need to reduce the stress and difficulties users experience when shopping and provide a more comfortable and satisfying shopping experience.

[1537] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring related data from a database based on information input by a user and emotional data of the user, means for analyzing the acquired data and emotional data using a generative model, and means for generating strategies or product proposals based on the analysis results. This enables personalized product proposals that reflect the user's emotions.

[1538] The "means for receiving information input by a user" is a function that allows the system to receive information such as text or voice input by a user via a terminal.

[1539] The "means for retrieving related data from a database based on received information and user emotion data" is a function for searching and retrieving related information from a database using information received from a user and the user emotion data analyzed by the emotion engine.

[1540] "Means for analyzing acquired data and emotion data using a generative model" refers to a function for inputting information and emotion data acquired from a database into a generative model based on a machine learning algorithm and performing analysis.

[1541] The "means for generating a strategy or product proposal based on the analysis results" is a function for generating a strategy or product proposal in a concrete form based on the analysis results obtained by the generative model.

[1542] The "means for providing the generated strategy or product proposal to the user" is a function for presenting the generated strategy or product proposal to the user via the terminal.

[1543] This invention is a data analysis system for mail-order sites that recognizes user emotions and makes appropriate product suggestions based on those emotions. A specific embodiment of this system is described below.

[1544] System configuration

[1545] This system encompasses a series of processes: inputting information from the user, retrieving related data from a database, analyzing the data using a generative model, generating suggestions, and delivering the generated suggestions. It also uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions based on the results. The system has three main components: a server, a terminal, and a user.

[1546] Hardware and software used

[1547] Hardware:

[1548] Smartphone (device)

[1549] server

[1550] software:

[1551] Emotion Engine API (Emotion Analysis)

[1552] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1553] Database System

[1554] Natural Language Generation (NLG) models

[1555] UI engine (e.g. React Native)

[1556] Network Communication Interface

[1557] Detailed explanation of the process

[1558] Data Entry and Receipt

[1559] A user enters product-related keywords and review content into a shopping app. The emotion engine reads emotions from the user's input and facial expressions (using the smartphone camera). The input data and emotion data are sent from the smartphone to the server in JSON format.

[1560] Data Acquisition

[1561] The server retrieves related product information, reviews, and recommended product data from a database based on the received user input data and emotion data. The connected database includes a database that stores detailed product information and user reviews.

[1562] Data analysis

[1563] The server inputs this acquired information into a generative model and makes product recommendations that take the user's emotional state into account. Machine learning libraries such as TensorFlow and PyTorch are used to analyze the generative model.

[1564] Proposal generation and delivery

[1565] The server generates product suggestions based on the analysis results obtained from the generative model, corresponding to the user's emotions. The generated product suggestions are presented with a message, such as "These earphones have sound quality that will relax you." The suggested products and messages are sent to a smartphone app and displayed to the user.

[1566] Specific examples

[1567] scenario

[1568] Here is a specific usage scenario where a user enters "I want new earphones" into a shopping app.

[1569] Prompt Sentence Examples

[1570] "I want new earphones."

[1571] This system allows users to receive product suggestions that match their emotions, resulting in a more comfortable and satisfying shopping experience.

[1572] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1573] Step 1:

[1574] Users enter product-related keywords and review content into the shopping app. At this time, the smartphone camera captures the user's facial expressions, which are then analyzed by the emotion engine API to generate emotion data. The input here is the user's text input and facial expression data, and emotion data is output based on this.

[1575] Step 2:

[1576] The device receives the user's input data and the emotion data recognized by the emotion engine, and sends them to the server in a standardized format (e.g., JSON). In this process, the text input data and emotion data are transferred together to the server.

[1577] Step 3:

[1578] The server analyzes the received user input data and emotion data and retrieves related information from the database based on the analysis. Specifically, detailed product information, user reviews, and related ratings are retrieved from the database. Here, the input data and emotion data are used to query the relevant database and retrieve the relevant product information.

[1579] Step 4:

[1580] The server inputs the acquired data and emotional data into a generative model to generate optimal product suggestions corresponding to the user's emotional state. At this time, each piece of data is analyzed using a machine learning algorithm (e.g., TensorFlow, PyTorch). The input data is product information and emotional data acquired from a database, and product suggestions are output based on that.

[1581] Step 5:

[1582] The server generates a suggested message based on the analysis results obtained from the generative model. For example, a specific message such as "These earphones have a sound quality that will relax you" is generated. The generated message has appropriate content that reflects the user's emotional state.

[1583] Step 6:

[1584] The server sends the generated product proposal and proposal message to the terminal, which receives them and displays them to the user. The output here is the proposed product and message displayed on the user's terminal.

[1585] Step 7:

[1586] Users can check the suggested products and messages on their device screen and consider purchasing the products based on them. By receiving suggestions that take their emotions into consideration, users can have a more comfortable shopping experience.

[1587] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1588] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1589] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1590] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1591] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1592] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1593] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1594] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1595] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1596] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1597] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1598] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1599] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1600] 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.

[1601] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1602] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1603] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1604] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1605] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1606] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1607] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1608] The following is further disclosed regarding the above embodiment.

[1609] (Claim 1)

[1610] [Means for receiving information input from a user;

[1611] [means for retrieving relevant data from a database based on the received information; and

[1612] [Means for analyzing the acquired data using a generative model;

[1613] [Means for generating strategies based on the analysis results;

[1614] [means for providing the generated strategy to a user;

[1615] A system including:

[1616] (Claim 2)

[1617] [The system of claim 1, wherein the generative model uses a machine learning algorithm.

[1618] (Claim 3)

[1619] [The system according to claim 1, which uses a chatbot to interact with the user.

[1620] "Example 1"

[1621] (Claim 1)

[1622] [A terminal means for receiving information input by a user;

[1623] [Means for transmitting the information received by the terminal to the server in a standardized format;

[1624] [Means for retrieving relevant data from a database based on the information received by the server;

[1625] [Means for analyzing the data acquired by the server using a generative model;

[1626] [Means for the server to generate a strategy based on the analysis results;

[1627] [Means for providing the generated strategy to a user through a terminal;

[1628] A system including:

[1629] (Claim 2)

[1630] [The system of claim 1, wherein the generative model uses a machine learning algorithm.

[1631] (Claim 3)

[1632] [The system according to claim 1, which uses a chatbot to interact with the user.

[1633] "Application Example 1"

[1634] (Claim 1)

[1635] [Means for receiving information input from a user;

[1636] [means for retrieving relevant data from a database based on the received information; and

[1637] [Means for analyzing the acquired data using a generative model;

[1638] [Means for generating strategies based on the analysis results;

[1639] [means for providing the generated strategy to a user;

[1640] [Means for obtaining operating status and maintenance records of industrial equipment;

[1641] [Means for predicting maintenance of industrial equipment using machine learning algorithms;

[1642] A system including:

[1643] (Claim 2)

[1644] [The system of claim 1, wherein the generative model uses a machine learning algorithm.

[1645] (Claim 3)

[1646] [The system according to claim 1, which uses a chatbot to interact with the user.

[1647] "Example 2: Combining Emotion Engines"

[1648] (Claim 1)

[1649] [Means for receiving information input from a user and recognizing emotions using an emotion engine;

[1650] [means for retrieving relevant data from a database based on the received information and emotions;

[1651] [Means for analyzing the acquired data and emotions using a generative AI model;

[1652] [Means for generating strategies based on the analysis results and emotions;

[1653] [means for providing the generated strategy to a user;

[1654] A system including:

[1655] (Claim 2)

[1656] [The system of claim 1, wherein the generative AI model uses a machine learning algorithm.

[1657] (Claim 3)

[1658] [The system according to claim 1, which uses a chatbot to interact with the user and recognizes emotions using an emotion engine.

[1659] "Application example 2 when combining emotion engines"

[1660] (Claim 1)

[1661] [Means for receiving information input from a user;

[1662] [Means for retrieving relevant data from a database based on the received information and the user's emotion data;

[1663] [Means for analyzing the acquired data and emotion data using a generative model;

[1664] [means for generating strategies or product proposals based on the analysis results;

[1665] [means for providing the generated strategy or product proposal to a user;

[1666] A system including:

[1667] (Claim 2)

[1668] [The system of claim 1, wherein the generative model uses a machine learning algorithm.

[1669] (Claim 3)

[1670] [The system according to claim 1, which uses a chatbot to interact with the user. [Explanation of symbols]

[1671] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving information input from a user; means for retrieving relevant data from a database based on the received information; A means for analyzing the acquired data using a generative model; means for generating a strategy based on the analysis results; a means for providing the generated strategy to a user; A system including:

2. The system of claim 1 , wherein the generative model uses a machine learning algorithm.

3. The system according to claim 1, wherein the system uses a chatbot to interact with the user.

Images