System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing data; means for selecting a generative artificial intelligence; means for generating a hypothesis useful for a business; and means for presenting the generated hypothesis.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] Traditional methods have been challenging in that they require a lot of time and expertise to find information useful for business from large amounts of data and propose appropriate hypotheses. Furthermore, if the accuracy of data analysis is low, the hypotheses derived may be meaningless for the business or may be misleading. There is a need to solve these problems and enable companies and organizations to make quick and accurate decisions. [Means for solving the problem]

[0005] This invention provides a system that includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for a business, and a means for presenting the generated hypotheses. The system analyzes large amounts of data provided by the user and extracts features to perform the preprocessing required for generating business hypotheses. Furthermore, the user can select a generative AI specialized for the industry they use, and that AI is used to generate optimal hypotheses. The generated hypotheses are presented to the user along with related data, supporting fast and accurate decision-making. This provides a new level of insight into data utilization and strengthens business competitiveness.

[0006] The "data analysis means" is a means for analyzing large amounts of data provided by users and extracting features.

[0007] The "means for selecting a generative AI" is a means for a user to select an AI specialized in a specific industry of their choice.

[0008] The "means for generating hypotheses" refers to a means for generating hypotheses useful for a business based on the results of data analysis using a selected generative artificial intelligence.

[0009] The "means for presenting a generated hypothesis" is a means for presenting the generated hypothesis and related data to a user. [Brief explanation of the drawings]

[0010] [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

[0011] 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.

[0012] First, the terms used in the following description will be explained.

[0013] 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).

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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."

[0018] [First embodiment]

[0019] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0020] 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.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, and a means for presenting the generated hypotheses. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[0032] Program processing

[0033] Uploading data

[0034] Users upload the data they want to analyze into the system, provided in formats such as CSV or Excel files.

[0035] Examples:

[0036] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[0037] Data Preprocessing

[0038] After receiving the uploaded data, the server performs data cleansing, filling in missing or outlier values ​​and standardizing the data format.

[0039] Examples:

[0040] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[0041] Feature extraction

[0042] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[0043] Examples:

[0044] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[0045] Selecting the Generator AI

[0046] Users can select the AI ​​that best suits their business field from among the multiple generative AI models provided by the system, which allows them to utilize AI with industry-specific knowledge.

[0047] Examples:

[0048] Users select a generative AI specialized for the retail industry.

[0049] Hypothesis generation

[0050] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[0051] Examples:

[0052] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[0053] Presenting a hypothesis

[0054] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, allowing the user to intuitively understand them.

[0055] Examples:

[0056] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[0057] decision support

[0058] The user develops a business strategy and action plan based on the presented hypotheses, then evaluates whether the hypotheses are useful and adjusts them as necessary.

[0059] Examples:

[0060] The user plans a promotion campaign in a specific area based on the presented hypothesis and prepares for its execution.

[0061] As described above, the system of the present invention has the function of supporting rapid and accurate decision-making by efficiently analyzing data provided by users and using generative AI to generate and present useful hypotheses.

[0062] The processing flow will be explained below.

[0063] Program processing steps

[0064] The process flow in the system of the present invention will be specifically explained below step by step.

[0065] Step 1: Upload Data (User)

[0066] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[0067] Specific behavior:

[0068] Users access the system through a browser.

[0069] Use the data file specification dialog box to select a local file.

[0070] Click the "Upload" button to send the data to the server.

[0071] Step 2: Data preprocessing (server)

[0072] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[0073] Specific behavior:

[0074] The server detects missing values ​​in the data and performs the appropriate imputation process.

[0075] Anomalous data points are detected and corrected or removed accordingly.

[0076] Consistency of data types (e.g. converting strings to numbers).

[0077] Step 3: Feature extraction (server)

[0078] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[0079] Specific behavior:

[0080] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[0081] Analyze the frequency distribution of categorical data and extract important features.

[0082] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[0083] Step 4: User selection of the generating AI

[0084] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[0085] Specific behavior:

[0086] Users select an industry from a drop-down menu within the system.

[0087] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[0088] Step 5: Hypothesis generation (server)

[0089] The server uses the selected generation AI to generate hypotheses useful for the business based on the extracted features. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[0090] Specific behavior:

[0091] The server provides the features as input data to the generative AI model.

[0092] Generative AI analyzes input data and generates hypotheses.

[0093] Hypotheses are formalized into concrete action items.

[0094] Step 6: Present the hypothesis (terminal)

[0095] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[0096] Specific behavior:

[0097] The terminal displays the hypotheses and data received from the server on a user interface.

[0098] Visualize data using graphs and charts.

[0099] Displays a summary of the hypothesis in text format.

[0100] Step 7: Decision Support (User)

[0101] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[0102] Specific behavior:

[0103] The user checks the details of the hypothesis on the interface.

[0104] Share your hypotheses with team members and gather feedback.

[0105] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[0106] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[0107] Example 1

[0108] 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."

[0109] Making fast and accurate decisions in business requires efficiently analyzing large amounts of data and quickly generating useful hypotheses from that data. However, with conventional systems, the process from uploading data to generating hypotheses is fragmented, and preprocessing such as data cleansing and feature extraction is often complex and time-consuming, making it difficult to support effective decision-making.

[0110] 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.

[0111] In this invention, the server includes a means for uploading data, a means for performing data preprocessing, and a means for extracting features. This enables consistent analysis of data provided by users and rapid and accurate generation of hypotheses. Specifically, the system solves the conventional problems by automating a series of processes from data uploading, preprocessing, feature extraction, selection of generative AI model, hypothesis generation, and presentation of the generated hypotheses and decision-making support.

[0112] "Data analysis means" is a means for analyzing uploaded data and extracting useful information and patterns from the data.

[0113] The "means for selecting a generating AI" is a means for the user to select an AI model specialized for a particular industry of their choice.

[0114] "Means for generating hypotheses useful for business" refers to means for generating hypotheses useful for business from analyzed data and features.

[0115] The "means for presenting the generated hypothesis" is a means for visualizing and presenting data related to the generated hypothesis to the user.

[0116] The "means for uploading data" refers to a means for a user to upload data that the user wishes to analyze to the system.

[0117] The "means for data preprocessing" refers to a means for performing preprocessing on uploaded data, such as filling in missing values ​​and correcting outliers.

[0118] The "means for extracting features" refers to a means for extracting business-important features from data that has undergone preprocessing.

[0119] The "means for supporting decision-making" is a means for supporting a user in making effective decisions based on the generated hypotheses.

[0120] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. This system includes a data analysis means, a means for selecting a generating AI, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, a means for uploading data, a means for data preprocessing, a means for extracting features, and a means for supporting decision-making.

[0121] First, the user uploads the data they want to analyze to the system. The data is provided in formats such as CSV or Excel files. For example, the user can upload "sales_data.csv," which contains sales data from the past year, to the system.

[0122] Next, the server receives the uploaded data and performs data cleansing. During this process, missing values ​​and outliers are filled in and the data format is standardized. For example, the server fills in missing values ​​and corrects outliers, and prepares the data in "sales_data.csv" in an analyzable format.

[0123] The server then performs feature extraction on the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data to extract features useful for business. For example, the server performs trend analysis on sales data to extract monthly sales trends and product sales rankings.

[0124] Next, users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system. This allows AI with industry-specific knowledge to be used. For example, users can select a generative AI specialized for the retail industry.

[0125] Using the selected generative AI model, the server generates hypotheses based on the features extracted from the data. The generated hypotheses are presented as specific business proposals. The server generates the hypothesis that "sales in a specific region increase sharply during the winter, so strengthening marketing in that region would be effective."

[0126] This hypothesis and related data are presented to the user via the device. Data visualization based on the hypothesis is also performed simultaneously, allowing the user to intuitively understand. For example, in addition to the generated hypothesis, the device can display a graph of monthly sales and a map of regional sales to the user.

[0127] Finally, users develop a business strategy and an action plan based on the presented hypotheses. They then evaluate whether the hypotheses are useful and adjust them as necessary. For example, users may plan a promotional campaign in a specific region based on the presented hypotheses and prepare for its implementation.

[0128] Below are some example prompts to input to a generative AI model:

[0129] Example prompt 1:

[0130] "Using sales data from the past year, please analyze monthly sales trends and product sales rankings to generate hypotheses that will be useful for future marketing strategies."

[0131] Example prompt 2:

[0132] "Generate hypotheses that suggest optimal marketing strategies based on seasonal sales fluctuations in a specific region."

[0133] The above is an embodiment of the present invention. This system efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: Upload your data

[0136] Users upload the data they want to analyze to the system, provided in formats such as CSV or Excel files.

[0137] Specific behavior:

[0138] The user selects the "sales_data.csv" file from their PC and clicks the upload button.

[0139] The server receives the uploaded file and stores it in storage.

[0140] input:

[0141] "sales_data.csv" file

[0142] output:

[0143] Data files saved in storage

[0144] Step 2: Data Preprocessing

[0145] After receiving the uploaded data, the server performs data cleansing, i.e., filling in missing or outlier values ​​and standardizing the data format.

[0146] Specific behavior:

[0147] The server reads the uploaded "sales_data.csv" and identifies rows that contain missing values.

[0148] The server imputes missing values ​​with the mean value or based on specified rules.

[0149] The server detects outliers (e.g., negative sales figures) and corrects them.

[0150] The server standardizes data such as date formats.

[0151] input:

[0152] "sales_data.csv" file saved in storage

[0153] output:

[0154] Preprocessed dataset

[0155] Step 3: Feature extraction

[0156] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[0157] Specific behavior:

[0158] The server extracts monthly sales data and performs time series analysis.

[0159] The server calculates the sales frequency by category (e.g., by product category).

[0160] The server adds these analysis results to the data frame as new features.

[0161] input:

[0162] Preprocessed dataset

[0163] output:

[0164] Dataset with added features

[0165] Step 4: Selecting the Generator AI

[0166] Users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system.

[0167] Specific behavior:

[0168] The user selects a generative AI model for the retail industry on the system's generative AI selection screen.

[0169] The user checks the model description and clicks the selection button.

[0170] The server loads the selected generative AI model.

[0171] input:

[0172] User-generated AI model selection information

[0173] output:

[0174] Loaded generative AI model

[0175] Step 5: Hypothesis generation

[0176] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[0177] Specific behavior:

[0178] The server inputs the feature extraction results into the generation AI as prompts.

[0179] The server stores the generated hypotheses in a database.

[0180] input:

[0181] Dataset with added features

[0182] Loaded generative AI model

[0183] output:

[0184] Generated hypotheses

[0185] Step 6: State your hypotheses

[0186] The device presents the generated hypotheses and related data to the user, while also visualizing the data based on the hypotheses.

[0187] Specific behavior:

[0188] The server transmits the hypotheses and associated data to the terminal.

[0189] The terminal generates a report screen containing the hypotheses and displays related graphs and maps.

[0190] The user can view the hypothesis and the supporting data on their device.

[0191] input:

[0192] Generated hypotheses

[0193] Related data

[0194] output:

[0195] Hypotheses presented to the user and related data

[0196] Step 7: Decision support

[0197] The user develops a business strategy and action plan based on the presented hypotheses, evaluates whether the hypotheses are useful, and adjusts the hypotheses as necessary.

[0198] Specific behavior:

[0199] The user creates a proposal for a promotion campaign based on the presented hypothesis.

[0200] To assess the reliability of the hypothesis, the user compares it with past performance data.

[0201] Users can improve the accuracy of hypotheses by running campaigns and feeding back the results to the system.

[0202] input:

[0203] Hypotheses presented to the user and related data

[0204] output:

[0205] Action plan and its evaluation results

[0206] (Application example 1)

[0207] 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."

[0208] In recent years, it has become increasingly difficult for users of content distribution services to efficiently find content that suits them from the wide variety of content available. This has led to problems such as lower user satisfaction and a decrease in frequency of service use. Furthermore, existing recommendation systems rely on limited data and specific algorithms, limiting the accuracy of their analysis and recommendations. In response to this situation, there is a demand for a system that can efficiently analyze large amounts of data and make highly accurate content recommendations based on users' viewing habits.

[0209] 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.

[0210] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, and a means for analyzing viewing habits from user data and recommending content based on the viewing history. This enables highly accurate content recommendations based on the user's viewing history, thereby increasing user satisfaction. Furthermore, by using an industry-specific generative AI, optimal content recommendations can be made according to the needs of a specific industry.

[0211] The "data analysis means" is a means for analyzing data provided by a user and extracting useful information from the data.

[0212] A "means for selecting generative AI" is a means for selecting the AI ​​model that is best suited to a user's specific purpose or industry from among multiple generative AI models.

[0213] A "means for generating hypotheses useful for a business" is a means for generating hypotheses useful for a specific business using analyzed data and a selected generative AI model.

[0214] The "means for presenting the generated hypotheses" is a means for presenting the generated hypotheses to the user in an easy-to-understand manner.

[0215] "Means for analyzing viewing trends from user data and recommending content based on viewing history" refers to means for analyzing a user's viewing history and evaluation data and recommending the most suitable content to the user based on the results.

[0216] An embodiment of the present invention is based on a system configured as follows: This system has the function of allowing a user to provide viewing history and rating data, analyzing the data, generating hypotheses, and recommending optimal content to the user.

[0217] Uploading data

[0218] Users upload their viewing history and rating data to the system in CSV files. For example, a user might upload a file called "user_watch_data.csv." At this time, the device sends the user's data to the server.

[0219] Data Preprocessing

[0220] The server receives the uploaded data and performs data cleansing, imputing missing values ​​and outliers, and arranging the data format. Specifically, it uses the Pandas and NumPy libraries to impute missing values ​​and remove outliers.

[0221] Feature extraction

[0222] Next, the server extracts viewing and rating trends from the viewing data, including the number of views and average ratings. Based on this, the server generates data features and uses them for analysis.

[0223] Selecting a generative AI model

[0224] Users can select the generative AI model that best suits their needs and industry from among the multiple generative AI models provided. For example, they can select a specialized generative AI model for recommending entertainment content.

[0225] Hypothesis generation

[0226] Using the selected generative AI model, the server generates recommended content based on viewing habits from user data. This hypothesis generation process uses a generative AI model specialized for the entertainment industry.

[0227] Presenting a hypothesis

[0228] The generated recommended content is presented to the user via the device, and the user can check their viewing history and a list of recommended content in an intuitive manner.

[0229] Examples and prompts

[0230] For example, by providing the following prompt to a generative AI model, it can generate optimal recommendations for the user:

[0231] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[0232] To realize this system, Python programs, data analysis libraries such as Pandas and NumPy, and generative AI models specialized for specific applications are used.Technically, the system is configured to seamlessly upload data, preprocess it, extract features, analyze it using the generative AI model, and present the results.

[0233] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0234] Step 1:

[0235] Users upload their viewing history and rating data in CSV file format to their device. The device then sends this file to the server. The input is a data file such as "user_watch_data.csv," and the output is the raw data received by the server.

[0236] Step 2:

[0237] The server performs a data cleansing process on the received data. For example, it uses Pandas to fill in missing values ​​and remove outliers. The input is raw data, and the output is cleansed, formatted data. Specifically, the process involves using data.fillna(data.mean(), inplace=True).

[0238] Step 3:

[0239] The server extracts features from the cleansed data. For example, it aggregates the number of views and average ratings to generate a new dataset. The input is the cleansed formatted data, and the output is the extracted feature data. Specifically, the following process is performed: features = data.groupby('content_id').agg({'views': 'sum', 'ratings': 'mean'}).reset_index().

[0240] Step 4:

[0241] The user selects an appropriate generative AI model from among several provided models. The selected generative AI model is selected to be specialized in a specific field. The input is the user's selection, and the output is the selected generative AI model itself.

[0242] Step 5:

[0243] The server uses the selected generative AI model to generate a hypothesis based on the extracted feature data. This hypothesis is what is presented as recommended content to the user. The input is the feature data and the selected generative AI model, and the output is the generated recommendation hypothesis. Specifically, the server inputs a prompt to the generative AI model and obtains the result.

[0244] Step 6:

[0245] The device presents the generated hypotheses, i.e., recommended content, to the user. The user selects, watches, and rates content based on these hypotheses. The input is the generated recommendation hypotheses, and the output is a content list presented to the user.

[0246] Examples and prompts

[0247] For example, in the following example, a prompt sentence based on the viewing history of user ID: 12345 is input to the generative AI model:

[0248] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[0249] Based on this prompt, the generative AI model analyzes it, generates recommended content tailored to the user, and presents it to the user via their device.

[0250] 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.

[0251] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the user's emotions. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[0252] Program processing

[0253] Uploading data

[0254] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[0255] Examples:

[0256] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[0257] Data Preprocessing

[0258] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[0259] Examples:

[0260] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[0261] Feature extraction

[0262] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[0263] Examples:

[0264] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[0265] Selecting the Generator AI

[0266] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[0267] Examples:

[0268] Users select a generative AI specialized for the retail industry.

[0269] Hypothesis generation

[0270] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[0271] Examples:

[0272] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[0273] Acquiring and analyzing emotion data

[0274] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[0275] Examples:

[0276] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[0277] Emotional Hypothesis Adjustment

[0278] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[0279] Examples:

[0280] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[0281] Presenting a hypothesis

[0282] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[0283] Examples:

[0284] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[0285] decision support

[0286] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[0287] Examples:

[0288] Based on the above-mentioned hypothesis, the user plans a promotion campaign for a specific region and prepares for its execution.

[0289] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[0290] The processing flow will be explained below.

[0291] Program processing steps

[0292] The process flow in the system of the present invention will be specifically explained below step by step.

[0293] Step 1: Upload Data (User)

[0294] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[0295] Specific behavior:

[0296] Users access the system through a browser.

[0297] Use the data file specification dialog box to select a local file.

[0298] Click the "Upload" button to send the data to the server.

[0299] Step 2: Data preprocessing (server)

[0300] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[0301] Specific behavior:

[0302] The server detects missing values ​​in the data and performs the appropriate imputation process.

[0303] Anomalous data points are detected and corrected or removed accordingly.

[0304] Consistency of data types (e.g. converting strings to numbers).

[0305] Step 3: Feature extraction (server)

[0306] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[0307] Specific behavior:

[0308] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[0309] Analyze the frequency distribution of categorical data and extract important features.

[0310] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[0311] Step 4: User selection of the generating AI

[0312] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[0313] Specific behavior:

[0314] Users select an industry from a drop-down menu within the system.

[0315] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[0316] Step 5: Hypothesis generation (server)

[0317] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[0318] Specific behavior:

[0319] The server provides the features as input data to the generative AI model.

[0320] Generative AI analyzes input data and generates hypotheses.

[0321] Hypotheses are formalized into concrete action items.

[0322] Step 6: Acquiring and analyzing emotion data (server)

[0323] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[0324] Specific behavior:

[0325] The server receives text comments and voice data entered by the user.

[0326] The emotion engine analyzes the received data and recognizes the user's emotional state (happiness, sadness, anger, etc.).

[0327] The recognized emotional state is stored as emotion data.

[0328] Step 7: Emotion-based hypothesis adjustment (server)

[0329] The server adjusts the hypotheses based on the acquired emotional data, and by making specific suggestions that take the user's emotional state into account, the accuracy and usefulness of the hypotheses are improved.

[0330] Specific behavior:

[0331] The server integrates the generated hypotheses with emotional data and makes adjustments according to the user's interests and expectations.

[0332] Regenerate the adjusted hypotheses as a new business proposition.

[0333] Step 8: Present the hypothesis (terminal)

[0334] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, providing information in a format that is easy for the user to understand.

[0335] Specific behavior:

[0336] The terminal displays the hypotheses and data received from the server on a user interface.

[0337] Visualize data using graphs and charts.

[0338] Displays a summary of the hypothesis in text format.

[0339] Step 9: Decision Support (User)

[0340] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[0341] Specific behavior:

[0342] The user checks the details of the hypothesis on the interface.

[0343] Share your hypotheses with team members and gather feedback.

[0344] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[0345] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[0346] Example 2

[0347] 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."

[0348] Conventional data analysis systems do not generate or adjust hypotheses taking user emotions into account, making it difficult to provide business proposals that truly interest users. Furthermore, the accuracy of generated hypotheses can be reduced by not being able to select industry-specific AI. This makes it difficult to support fast and accurate decision-making.

[0349] 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.

[0350] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for a business, a means for activating an emotion engine that recognizes the user's emotions, and a means for adjusting the hypotheses based on the user's emotion data, thereby enabling highly accurate hypothesis generation that takes the user's emotions into consideration.

[0351] "Data analysis means" refers to means for analyzing the provided data, extracting information, preprocessing, and analyzing features.

[0352] The "means for selecting a generative AI" is a means for a user to select an AI specialized for a specific industry.

[0353] The "means for generating hypotheses" is a means for generating hypotheses useful for a business using analyzed data and selected artificial intelligence.

[0354] The "means for presenting hypotheses" is a means for visually displaying the generated hypotheses and providing them to the user in a format that is easy to understand.

[0355] The "emotion engine" is an engine that analyzes emotions from the user's facial expressions, voice, and text, and generates emotional data.

[0356] The "means for adjusting hypotheses based on user emotional data" refers to a means for adjusting existing hypotheses based on user emotional data and placing emphasis on items that interest or are considered important by the user.

[0357] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the emotions of the user. Specific embodiments of the present invention are described in detail below.

[0358] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data format is typically a CSV or Excel file. Specifically, the user opens a web browser, accesses the system's login page, enters their login information, and logs in to the system. After logging in, they click the upload button, select the data file (for example, "sales_data.csv"), and upload it.

[0359] The server then receives the received data and performs an initial data cleansing process. The server loads the data into memory and uses a missing value imputation algorithm to fill in any missing values ​​in the data. The server also uses an outlier detection algorithm to correct any outliers, and standardizes the data format to make it suitable for analysis.

[0360] Next, the server extracts features from the preprocessed data. The server runs data analysis algorithms (e.g., principal component analysis (PCA) or clustering) to extract key features from the data. The server detects trends and patterns in the sales data and classifies it by time axis and product. The extracted features are used as the basis for hypothesis generation in the next step.

[0361] The user then selects the generative AI that is best suited to their business field from the multiple generative AI models provided by the system. The user checks the list of generative AI models displayed on the dashboard and selects the generative AI model that is best suited to their business field. For example, the user can select a generative AI specialized for the retail industry. The user clicks the selection button to notify the system of their selection.

[0362] After selecting a generative AI model, the server uses the selected generative AI to generate hypotheses based on the features extracted from the data. The server initializes the selected generative AI model and prepares it for analysis. The server inputs the feature data into the generative AI and executes the hypothesis generation process. The generated hypotheses are provided as specific business proposals, and the server stores the generated hypotheses in a database and organizes them into a format that can be presented to users.

[0363] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences. The server collects the user's input media (e.g., text comments and speech data) and runs an emotion analysis algorithm to analyze the user's emotional state. The server generates emotion data such as "happiness," "dissatisfaction," and "surprise," which are used in the hypothesis adjustment process.

[0364] Next, the server adjusts the generated hypotheses based on the emotional data. The server analyzes the user's emotional data to identify the user's interests and important items. The server prioritizes the generated hypotheses and makes important suggestions based on the user's emotions. The adjusted hypotheses are saved in the database again and presented to the user via the device.

[0365] Finally, the device presents the generated hypotheses and related data to the user. The device displays the hypotheses and related data (e.g., graphs and maps) using visualization tools. The user then develops a business strategy based on the presented hypotheses. By formulating a specific action plan and evaluating the usefulness of the hypotheses, the user determines the appropriate action. For example, the user may plan a promotional campaign in a specific region based on the previously presented hypotheses and prepare for its implementation.

[0366] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[0367] Example prompt sentence:

[0368] "Analyze seasonal sales trends from the given sales data and propose a hypothesis for the marketing strategy for the next season."

[0369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0370] Step 1:

[0371] The user logs into the system and uploads the data file to be analyzed.

[0372] input:

[0373] The user provides login information (username, password) and the data file to be analyzed (e.g., "sales_data.csv").

[0374] Specific behavior:

[0375] The user opens a web browser and accesses the system's login page.

[0376] The user enters the login information and logs into the system.

[0377] The user clicks the upload button, selects the data file and uploads it.

[0378] output:

[0379] Data files uploaded to the server.

[0380] Step 2:

[0381] The server pre-processes the received data files.

[0382] input:

[0383] The uploaded data file (for example, "sales_data.csv").

[0384] Specific behavior:

[0385] The server reads the data file into memory.

[0386] The server uses a missing value imputation algorithm to impute missing values.

[0387] The server uses an outlier detection algorithm to correct the outliers.

[0388] The server will standardize the data format and prepare it in a state suitable for analysis.

[0389] output:

[0390] Clean data after preprocessing.

[0391] Step 3:

[0392] The server extracts features from the pre-processed data.

[0393] input:

[0394] Clean data after preprocessing.

[0395] Specific behavior:

[0396] The server runs data analysis algorithms (e.g., principal component analysis and clustering).

[0397] The server extracts the key features of the data.

[0398] The server detects trends and patterns in the sales data and categorizes it by timeline and product.

[0399] output:

[0400] Extracted feature data.

[0401] Step 4:

[0402] The user selects the most appropriate model from the generative AI models provided by the system.

[0403] input:

[0404] A list of generative AI models.

[0405] Specific behavior:

[0406] The user sees a list of generative AI models displayed on the dashboard.

[0407] Users select the generative AI model that best suits their business field.

[0408] The user clicks on the selection button to notify the system of the selection.

[0409] output:

[0410] Information about the selected generative AI model.

[0411] Step 5:

[0412] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[0413] input:

[0414] Extracted feature data and information on the selected generative AI model.

[0415] Specific behavior:

[0416] The server initializes the selected generative AI model and prepares it for analysis.

[0417] The server inputs the feature data into the generation AI and executes the hypothesis generation process.

[0418] The server stores the generated hypotheses in a database.

[0419] output:

[0420] Data for generated hypotheses.

[0421] Step 6:

[0422] The server activates an emotion engine to recognize the user's emotions.

[0423] input:

[0424] User input media (text comments, speech data).

[0425] Specific behavior:

[0426] The server collects the user's input media.

[0427] The server runs an emotion analysis algorithm to analyze the emotional state.

[0428] The server generates emotion data such as "happiness," "dissatisfaction," and "surprise."

[0429] output:

[0430] User emotion data.

[0431] Step 7:

[0432] The server adjusts the generated hypotheses based on the user's emotional data.

[0433] input:

[0434] Generated hypothesis data, user emotion data.

[0435] Specific behavior:

[0436] The server analyzes the user's emotional data and identifies the user's interests and important points.

[0437] The server prioritizes and makes key suggestions based on the generated hypotheses based on the user's emotions.

[0438] The server stores the adjusted hypotheses back in the database.

[0439] output:

[0440] Adjusted hypothesis data.

[0441] Step 8:

[0442] The terminal presents the generated hypotheses and associated data to the user.

[0443] input:

[0444] Adjusted hypothesis data.

[0445] Specific behavior:

[0446] The terminal displays the hypotheses and related data (graphs, maps) using visualization tools.

[0447] The terminal provides an interactive user interface that allows users to explore hypotheses in detail.

[0448] output:

[0449] Hypotheses presented to the user and associated data visualized.

[0450] Step 9:

[0451] The user develops a business strategy based on the presented hypotheses.

[0452] input:

[0453] Presented hypotheses and visualized relevant data.

[0454] Specific behavior:

[0455] The user reviews the presented hypotheses and related data.

[0456] Users evaluate the usefulness of the hypotheses and plan to incorporate them into their business strategy.

[0457] The user decides on a specific action plan (e.g., implementing a promotional campaign) and prepares for its implementation.

[0458] output:

[0459] A proposed business strategy and a concrete action plan.

[0460] (Application example 2)

[0461] 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."

[0462] Conventional data analysis systems are limited to analyzing massive amounts of data to generate hypotheses, and the generated hypotheses do not adequately reflect user sentiment or the specific needs of the business, making it difficult to improve the accuracy of decision-making support.In addition, they lack the ability to utilize generative AI models specialized for specific industries, and tend to provide hypotheses with low accuracy.

[0463] 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 a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, an emotion recognition means for acquiring and analyzing emotion data, and a means for adjusting the hypotheses based on the emotion data. This makes it possible to analyze user-provided data, select a generative AI model specialized for a specific industry, and generate highly accurate hypotheses that reflect the emotion data.

[0464] "Data analysis means" refers to a device or software that has the function of analyzing data provided by a user and extracting useful information or patterns.

[0465] A "means for selecting generative artificial intelligence" is a device or software that has the function of selecting an artificial intelligence model suitable for a particular industry or application.

[0466] A "means for generating hypotheses useful for a business" is a device or software that has the function of generating hypotheses useful for business decision-making based on analyzed data.

[0467] The "means for presenting the generated hypotheses" refers to a device or software that has the function of presenting the generated hypotheses to the user visually or as text.

[0468] "Emotion recognition means" refers to a device or software that has the function of analyzing emotions from a user's facial expressions, voice, writing, etc., and generating emotion data.

[0469] The "means for adjusting hypotheses based on emotional data" refers to a device or software that has the function of adjusting or correcting hypotheses generated by taking into account emotional data.

[0470] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a generation artificial intelligence selection means, a generation hypothesis generation means, a presentation means for generating hypotheses useful for business, an emotion recognition means, and a means for adjusting the hypotheses based on the emotion data.

[0471] Hardware and software used

[0472] Hardware: Regular PC or smartphone

[0473] Software: Python, pandas, scikit-learn, sentiment analysis library (e.g., sentiment_analysis)

[0474] System action

[0475] Uploading data

[0476] Users log in to the system, select the data file to be analyzed, and upload it. Data is typically in CSV or Excel format.

[0477] Examples:

[0478] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[0479] Data Preprocessing

[0480] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to make it suitable for analysis.

[0481] Examples:

[0482] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[0483] Feature extraction

[0484] The server then performs feature extraction on the preprocessed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[0485] Examples:

[0486] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[0487] Selecting the Generator AI

[0488] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[0489] Examples:

[0490] Users select a generative AI specialized for the retail industry.

[0491] Hypothesis generation

[0492] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[0493] Examples:

[0494] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[0495] Acquiring and analyzing emotion data

[0496] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[0497] Examples:

[0498] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[0499] Emotional Hypothesis Adjustment

[0500] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[0501] Examples:

[0502] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[0503] Presenting a hypothesis

[0504] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[0505] Examples:

[0506] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[0507] Prompt Sentence Examples

[0508] "I am very excited about the new product launch"

[0509] As a result, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using a generative AI model and emotion engine, thereby supporting fast and accurate decision-making.

[0510] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0511] Step 1:

[0512] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data to be analyzed is typically in CSV or Excel format. As a specific example, the user uploads "sales_data.csv," which contains sales data from the past year, to the system.

[0513] Input: Login information, data file (sales_data.csv)

[0514] Output: Raw data uploaded to the server

[0515] Step 2:

[0516] The server preprocesses the received data, cleansing it, filling in missing and outlier values, and standardizing the data format, thereby preparing the data for analysis.

[0517] Input: raw data (sales_data.csv)

[0518] Output: Cleansed data

[0519] Step 3:

[0520] The server performs feature extraction on the preprocessed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[0521] Input: Cleansed data

[0522] Output: Extracted features (e.g., monthly sales trends, product sales rankings)

[0523] Step 4:

[0524] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By selecting an AI model specialized for a specific industry, more accurate hypotheses can be obtained.

[0525] Input: Generative AI model selection information (e.g., AI specialized for the retail industry)

[0526] Output: The selected generative AI model

[0527] Step 5:

[0528] The server uses the selected generative AI model to generate hypotheses based on the features extracted from the data, and these hypotheses are provided to users as concrete business proposals.

[0529] Input: extracted features, selected generative AI model

[0530] Output: Generated hypotheses (e.g., sales in a particular region spike during the winter, so increased marketing in that region is beneficial)

[0531] Step 6:

[0532] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[0533] Input: User input comments or utterances (e.g., "I am very excited about the new product launch")

[0534] Output: Emotion data (e.g., happiness, surprise)

[0535] Step 7:

[0536] The server adjusts the generated hypotheses based on the emotion data, providing suggestions that focus on items that the user is most interested in.

[0537] Input: Generated hypotheses, emotion data

[0538] Output: Adjusted hypotheses (e.g., a proposal for an aggressive promotion strategy for a new product for which users expressed "surprise")

[0539] Step 8:

[0540] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[0541] Input: Adjusted hypotheses, visualization data (e.g., monthly sales graph, regional sales map)

[0542] Output: Hypotheses and associated data presented to the user

[0543] 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.

[0544] 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.

[0545] 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.

[0546] [Second embodiment]

[0547] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0548] 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.

[0549] 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).

[0550] 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.

[0551] 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.

[0552] 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).

[0553] 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.

[0554] 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.

[0555] 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.

[0556] 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.

[0557] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0558] 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."

[0559] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, and a means for presenting the generated hypotheses. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[0560] Program processing

[0561] Uploading data

[0562] Users upload the data they want to analyze into the system, provided in formats such as CSV or Excel files.

[0563] Examples:

[0564] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[0565] Data Preprocessing

[0566] After receiving the uploaded data, the server performs data cleansing, filling in missing or outlier values ​​and standardizing the data format.

[0567] Examples:

[0568] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[0569] Feature extraction

[0570] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[0571] Examples:

[0572] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[0573] Selecting the Generator AI

[0574] Users can select the AI ​​that best suits their business field from among the multiple generative AI models provided by the system, which allows them to utilize AI with industry-specific knowledge.

[0575] Examples:

[0576] Users select a generative AI specialized for the retail industry.

[0577] Hypothesis generation

[0578] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[0579] Examples:

[0580] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[0581] Presenting a hypothesis

[0582] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, allowing the user to intuitively understand them.

[0583] Examples:

[0584] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[0585] decision support

[0586] The user develops a business strategy and action plan based on the presented hypotheses, then evaluates whether the hypotheses are useful and adjusts them as necessary.

[0587] Examples:

[0588] The user plans a promotion campaign in a specific area based on the presented hypothesis and prepares for its execution.

[0589] As described above, the system of the present invention has the function of supporting rapid and accurate decision-making by efficiently analyzing data provided by users and using generative AI to generate and present useful hypotheses.

[0590] The processing flow will be explained below.

[0591] Program processing steps

[0592] The process flow in the system of the present invention will be specifically explained below step by step.

[0593] Step 1: Upload Data (User)

[0594] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[0595] Specific behavior:

[0596] Users access the system through a browser.

[0597] Use the data file specification dialog box to select a local file.

[0598] Click the "Upload" button to send the data to the server.

[0599] Step 2: Data preprocessing (server)

[0600] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[0601] Specific behavior:

[0602] The server detects missing values ​​in the data and performs the appropriate imputation process.

[0603] Anomalous data points are detected and corrected or removed accordingly.

[0604] Consistency of data types (e.g. converting strings to numbers).

[0605] Step 3: Feature extraction (server)

[0606] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[0607] Specific behavior:

[0608] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[0609] Analyze the frequency distribution of categorical data and extract important features.

[0610] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[0611] Step 4: User selection of the generating AI

[0612] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[0613] Specific behavior:

[0614] Users select an industry from a drop-down menu within the system.

[0615] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[0616] Step 5: Hypothesis generation (server)

[0617] The server uses the selected generation AI to generate hypotheses useful for the business based on the extracted features. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[0618] Specific behavior:

[0619] The server provides the features as input data to the generative AI model.

[0620] Generative AI analyzes input data and generates hypotheses.

[0621] Hypotheses are formalized into concrete action items.

[0622] Step 6: Present the hypothesis (terminal)

[0623] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[0624] Specific behavior:

[0625] The terminal displays the hypotheses and data received from the server on a user interface.

[0626] Visualize data using graphs and charts.

[0627] Displays a summary of the hypothesis in text format.

[0628] Step 7: Decision Support (User)

[0629] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[0630] Specific behavior:

[0631] The user checks the details of the hypothesis on the interface.

[0632] Share your hypotheses with team members and gather feedback.

[0633] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[0634] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[0635] Example 1

[0636] 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."

[0637] Making fast and accurate decisions in business requires efficiently analyzing large amounts of data and quickly generating useful hypotheses from that data. However, with conventional systems, the process from uploading data to generating hypotheses is fragmented, and preprocessing such as data cleansing and feature extraction is often complex and time-consuming, making it difficult to support effective decision-making.

[0638] 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.

[0639] In this invention, the server includes a means for uploading data, a means for performing data preprocessing, and a means for extracting features. This enables consistent analysis of data provided by users and rapid and accurate generation of hypotheses. Specifically, the system solves the conventional problems by automating a series of processes from data uploading, preprocessing, feature extraction, selection of generative AI model, hypothesis generation, and presentation of the generated hypotheses and decision-making support.

[0640] "Data analysis means" is a means for analyzing uploaded data and extracting useful information and patterns from the data.

[0641] The "means for selecting a generating AI" is a means for the user to select an AI model specialized for a particular industry of their choice.

[0642] "Means for generating hypotheses useful for business" refers to means for generating hypotheses useful for business from analyzed data and features.

[0643] The "means for presenting the generated hypothesis" is a means for visualizing and presenting data related to the generated hypothesis to the user.

[0644] The "means for uploading data" refers to a means for a user to upload data that the user wishes to analyze to the system.

[0645] The "means for data preprocessing" refers to a means for performing preprocessing on uploaded data, such as filling in missing values ​​and correcting outliers.

[0646] The "means for extracting features" refers to a means for extracting business-important features from data that has undergone preprocessing.

[0647] The "means for supporting decision-making" is a means for supporting a user in making effective decisions based on the generated hypotheses.

[0648] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. This system includes a data analysis means, a means for selecting a generating AI, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, a means for uploading data, a means for data preprocessing, a means for extracting features, and a means for supporting decision-making.

[0649] First, the user uploads the data they want to analyze to the system. The data is provided in formats such as CSV or Excel files. For example, the user can upload "sales_data.csv," which contains sales data from the past year, to the system.

[0650] Next, the server receives the uploaded data and performs data cleansing. During this process, missing values ​​and outliers are filled in and the data format is standardized. For example, the server fills in missing values ​​and corrects outliers, and prepares the data in "sales_data.csv" in an analyzable format.

[0651] The server then performs feature extraction on the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data to extract features useful for business. For example, the server performs trend analysis on sales data to extract monthly sales trends and product sales rankings.

[0652] Next, users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system. This allows AI with industry-specific knowledge to be used. For example, users can select a generative AI specialized for the retail industry.

[0653] Using the selected generative AI model, the server generates hypotheses based on the features extracted from the data. The generated hypotheses are presented as specific business proposals. The server generates the hypothesis that "sales in a specific region increase sharply during the winter, so strengthening marketing in that region would be effective."

[0654] This hypothesis and related data are presented to the user via the device. Data visualization based on the hypothesis is also performed simultaneously, allowing the user to intuitively understand. For example, in addition to the generated hypothesis, the device can display a graph of monthly sales and a map of regional sales to the user.

[0655] Finally, users develop a business strategy and an action plan based on the presented hypotheses. They then evaluate whether the hypotheses are useful and adjust them as necessary. For example, users may plan a promotional campaign in a specific region based on the presented hypotheses and prepare for its implementation.

[0656] Below are some example prompts to input to a generative AI model:

[0657] Example prompt 1:

[0658] "Using sales data from the past year, please analyze monthly sales trends and product sales rankings to generate hypotheses that will be useful for future marketing strategies."

[0659] Example prompt 2:

[0660] "Generate hypotheses that suggest optimal marketing strategies based on seasonal sales fluctuations in a specific region."

[0661] The above is an embodiment of the present invention. This system efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[0662] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0663] Step 1: Upload your data

[0664] Users upload the data they want to analyze to the system, provided in formats such as CSV or Excel files.

[0665] Specific behavior:

[0666] The user selects the "sales_data.csv" file from their PC and clicks the upload button.

[0667] The server receives the uploaded file and stores it in storage.

[0668] input:

[0669] "sales_data.csv" file

[0670] output:

[0671] Data files saved in storage

[0672] Step 2: Data Preprocessing

[0673] After receiving the uploaded data, the server performs data cleansing, i.e., filling in missing or outlier values ​​and standardizing the data format.

[0674] Specific behavior:

[0675] The server reads the uploaded "sales_data.csv" and identifies rows that contain missing values.

[0676] The server imputes missing values ​​with the mean value or based on specified rules.

[0677] The server detects outliers (e.g., negative sales figures) and corrects them.

[0678] The server standardizes data such as date formats.

[0679] input:

[0680] "sales_data.csv" file saved in storage

[0681] output:

[0682] Preprocessed dataset

[0683] Step 3: Feature extraction

[0684] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[0685] Specific behavior:

[0686] The server extracts monthly sales data and performs time series analysis.

[0687] The server calculates the sales frequency by category (e.g., by product category).

[0688] The server adds these analysis results to the data frame as new features.

[0689] input:

[0690] Preprocessed dataset

[0691] output:

[0692] Dataset with added features

[0693] Step 4: Selecting the Generator AI

[0694] Users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system.

[0695] Specific behavior:

[0696] The user selects a generative AI model for the retail industry on the system's generative AI selection screen.

[0697] The user checks the model description and clicks the selection button.

[0698] The server loads the selected generative AI model.

[0699] input:

[0700] User-generated AI model selection information

[0701] output:

[0702] Loaded generative AI model

[0703] Step 5: Hypothesis generation

[0704] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[0705] Specific behavior:

[0706] The server inputs the feature extraction results into the generation AI as prompts.

[0707] The server stores the generated hypotheses in a database.

[0708] input:

[0709] Dataset with added features

[0710] Loaded generative AI model

[0711] output:

[0712] Generated hypotheses

[0713] Step 6: State your hypotheses

[0714] The device presents the generated hypotheses and related data to the user, while also visualizing the data based on the hypotheses.

[0715] Specific behavior:

[0716] The server transmits the hypotheses and associated data to the terminal.

[0717] The terminal generates a report screen containing the hypotheses and displays related graphs and maps.

[0718] The user can view the hypothesis and the supporting data on their device.

[0719] input:

[0720] Generated hypotheses

[0721] Related data

[0722] output:

[0723] Hypotheses presented to the user and related data

[0724] Step 7: Decision support

[0725] The user develops a business strategy and action plan based on the presented hypotheses, evaluates whether the hypotheses are useful, and adjusts the hypotheses as necessary.

[0726] Specific behavior:

[0727] The user creates a proposal for a promotion campaign based on the presented hypothesis.

[0728] To assess the reliability of the hypothesis, the user compares it with past performance data.

[0729] Users can improve the accuracy of hypotheses by running campaigns and feeding back the results to the system.

[0730] input:

[0731] Hypotheses presented to the user and related data

[0732] output:

[0733] Action plan and its evaluation results

[0734] (Application example 1)

[0735] 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."

[0736] In recent years, it has become increasingly difficult for users of content distribution services to efficiently find content that suits them from the wide variety of content available. This has led to problems such as lower user satisfaction and a decrease in frequency of service use. Furthermore, existing recommendation systems rely on limited data and specific algorithms, limiting the accuracy of their analysis and recommendations. In response to this situation, there is a demand for a system that can efficiently analyze large amounts of data and make highly accurate content recommendations based on users' viewing habits.

[0737] 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.

[0738] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, and a means for analyzing viewing habits from user data and recommending content based on the viewing history. This enables highly accurate content recommendations based on the user's viewing history, thereby increasing user satisfaction. Furthermore, by using an industry-specific generative AI, optimal content recommendations can be made according to the needs of a specific industry.

[0739] The "data analysis means" is a means for analyzing data provided by a user and extracting useful information from the data.

[0740] A "means for selecting generative AI" is a means for selecting the AI ​​model that is best suited to a user's specific purpose or industry from among multiple generative AI models.

[0741] A "means for generating hypotheses useful for a business" is a means for generating hypotheses useful for a specific business using analyzed data and a selected generative AI model.

[0742] The "means for presenting the generated hypotheses" is a means for presenting the generated hypotheses to the user in an easy-to-understand manner.

[0743] "Means for analyzing viewing trends from user data and recommending content based on viewing history" refers to means for analyzing a user's viewing history and evaluation data and recommending the most suitable content to the user based on the results.

[0744] An embodiment of the present invention is based on a system configured as follows: This system has the function of allowing a user to provide viewing history and rating data, analyzing the data, generating hypotheses, and recommending optimal content to the user.

[0745] Uploading data

[0746] Users upload their viewing history and rating data to the system in CSV files. For example, a user might upload a file called "user_watch_data.csv." At this time, the device sends the user's data to the server.

[0747] Data Preprocessing

[0748] The server receives the uploaded data and performs data cleansing, imputing missing values ​​and outliers, and arranging the data format. Specifically, it uses the Pandas and NumPy libraries to impute missing values ​​and remove outliers.

[0749] Feature extraction

[0750] Next, the server extracts viewing and rating trends from the viewing data, including the number of views and average ratings. Based on this, the server generates data features and uses them for analysis.

[0751] Selecting a generative AI model

[0752] Users can select the generative AI model that best suits their needs and industry from among the multiple generative AI models provided. For example, they can select a specialized generative AI model for recommending entertainment content.

[0753] Hypothesis generation

[0754] Using the selected generative AI model, the server generates recommended content based on viewing habits from user data. This hypothesis generation process uses a generative AI model specialized for the entertainment industry.

[0755] Presenting a hypothesis

[0756] The generated recommended content is presented to the user via the device, and the user can check their viewing history and a list of recommended content in an intuitive manner.

[0757] Examples and prompts

[0758] For example, by providing the following prompt to a generative AI model, it can generate optimal recommendations for the user:

[0759] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[0760] To realize this system, Python programs, data analysis libraries such as Pandas and NumPy, and generative AI models specialized for specific applications are used.Technically, the system is configured to seamlessly upload data, preprocess it, extract features, analyze it using the generative AI model, and present the results.

[0761] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0762] Step 1:

[0763] Users upload their viewing history and rating data in CSV file format to their device. The device then sends this file to the server. The input is a data file such as "user_watch_data.csv," and the output is the raw data received by the server.

[0764] Step 2:

[0765] The server performs a data cleansing process on the received data. For example, it uses Pandas to fill in missing values ​​and remove outliers. The input is raw data, and the output is cleansed, formatted data. Specifically, the process involves using data.fillna(data.mean(), inplace=True).

[0766] Step 3:

[0767] The server extracts features from the cleansed data. For example, it aggregates the number of views and average ratings to generate a new dataset. The input is the cleansed formatted data, and the output is the extracted feature data. Specifically, the following process is performed: features = data.groupby('content_id').agg({'views': 'sum', 'ratings': 'mean'}).reset_index().

[0768] Step 4:

[0769] The user selects an appropriate generative AI model from among several provided models. The selected generative AI model is selected to be specialized in a specific field. The input is the user's selection, and the output is the selected generative AI model itself.

[0770] Step 5:

[0771] The server uses the selected generative AI model to generate a hypothesis based on the extracted feature data. This hypothesis is what is presented as recommended content to the user. The input is the feature data and the selected generative AI model, and the output is the generated recommendation hypothesis. Specifically, the server inputs a prompt to the generative AI model and obtains the result.

[0772] Step 6:

[0773] The device presents the generated hypotheses, i.e., recommended content, to the user. The user selects, watches, and rates content based on these hypotheses. The input is the generated recommendation hypotheses, and the output is a content list presented to the user.

[0774] Examples and prompts

[0775] For example, in the following example, a prompt sentence based on the viewing history of user ID: 12345 is input to the generative AI model:

[0776] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[0777] Based on this prompt, the generative AI model analyzes it, generates recommended content tailored to the user, and presents it to the user via their device.

[0778] 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.

[0779] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the user's emotions. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[0780] Program processing

[0781] Uploading data

[0782] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[0783] Examples:

[0784] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[0785] Data Preprocessing

[0786] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[0787] Examples:

[0788] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[0789] Feature extraction

[0790] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[0791] Examples:

[0792] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[0793] Selecting the Generator AI

[0794] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[0795] Examples:

[0796] Users select a generative AI specialized for the retail industry.

[0797] Hypothesis generation

[0798] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[0799] Examples:

[0800] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[0801] Acquiring and analyzing emotion data

[0802] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[0803] Examples:

[0804] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[0805] Emotional Hypothesis Adjustment

[0806] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[0807] Examples:

[0808] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[0809] Presenting a hypothesis

[0810] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[0811] Examples:

[0812] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[0813] decision support

[0814] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[0815] Examples:

[0816] Based on the above-mentioned hypothesis, the user plans a promotion campaign for a specific region and prepares for its execution.

[0817] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[0818] The processing flow will be explained below.

[0819] Program processing steps

[0820] The process flow in the system of the present invention will be specifically explained below step by step.

[0821] Step 1: Upload Data (User)

[0822] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[0823] Specific behavior:

[0824] Users access the system through a browser.

[0825] Use the data file specification dialog box to select a local file.

[0826] Click the "Upload" button to send the data to the server.

[0827] Step 2: Data preprocessing (server)

[0828] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[0829] Specific behavior:

[0830] The server detects missing values ​​in the data and performs the appropriate imputation process.

[0831] Anomalous data points are detected and corrected or removed accordingly.

[0832] Consistency of data types (e.g. converting strings to numbers).

[0833] Step 3: Feature extraction (server)

[0834] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[0835] Specific behavior:

[0836] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[0837] Analyze the frequency distribution of categorical data and extract important features.

[0838] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[0839] Step 4: User selection of the generating AI

[0840] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[0841] Specific behavior:

[0842] Users select an industry from a drop-down menu within the system.

[0843] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[0844] Step 5: Hypothesis generation (server)

[0845] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[0846] Specific behavior:

[0847] The server provides the features as input data to the generative AI model.

[0848] Generative AI analyzes input data and generates hypotheses.

[0849] Hypotheses are formalized into concrete action items.

[0850] Step 6: Acquiring and analyzing emotion data (server)

[0851] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[0852] Specific behavior:

[0853] The server receives text comments and voice data entered by the user.

[0854] The emotion engine analyzes the received data and recognizes the user's emotional state (happiness, sadness, anger, etc.).

[0855] The recognized emotional state is stored as emotion data.

[0856] Step 7: Emotion-based hypothesis adjustment (server)

[0857] The server adjusts the hypotheses based on the acquired emotional data, and by making specific suggestions that take the user's emotional state into account, the accuracy and usefulness of the hypotheses are improved.

[0858] Specific behavior:

[0859] The server integrates the generated hypotheses with emotional data and makes adjustments according to the user's interests and expectations.

[0860] Regenerate the adjusted hypotheses as a new business proposition.

[0861] Step 8: Present the hypothesis (terminal)

[0862] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, providing information in a format that is easy for the user to understand.

[0863] Specific behavior:

[0864] The terminal displays the hypotheses and data received from the server on a user interface.

[0865] Visualize data using graphs and charts.

[0866] Displays a summary of the hypothesis in text format.

[0867] Step 9: Decision Support (User)

[0868] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[0869] Specific behavior:

[0870] The user checks the details of the hypothesis on the interface.

[0871] Share your hypotheses with team members and gather feedback.

[0872] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[0873] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[0874] Example 2

[0875] 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."

[0876] Conventional data analysis systems do not generate or adjust hypotheses taking user emotions into account, making it difficult to provide business proposals that truly interest users. Furthermore, the accuracy of generated hypotheses can be reduced by not being able to select industry-specific AI. This makes it difficult to support fast and accurate decision-making.

[0877] 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.

[0878] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for a business, a means for activating an emotion engine that recognizes the user's emotions, and a means for adjusting the hypotheses based on the user's emotion data, thereby enabling highly accurate hypothesis generation that takes the user's emotions into consideration.

[0879] "Data analysis means" refers to means for analyzing the provided data, extracting information, preprocessing, and analyzing features.

[0880] The "means for selecting a generative AI" is a means for a user to select an AI specialized for a specific industry.

[0881] The "means for generating hypotheses" is a means for generating hypotheses useful for a business using analyzed data and selected artificial intelligence.

[0882] The "means for presenting hypotheses" is a means for visually displaying the generated hypotheses and providing them to the user in a format that is easy to understand.

[0883] The "emotion engine" is an engine that analyzes emotions from the user's facial expressions, voice, and text, and generates emotional data.

[0884] The "means for adjusting hypotheses based on user emotional data" refers to a means for adjusting existing hypotheses based on user emotional data and placing emphasis on items that interest or are considered important by the user.

[0885] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the emotions of the user. Specific embodiments of the present invention are described in detail below.

[0886] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data format is typically a CSV or Excel file. Specifically, the user opens a web browser, accesses the system's login page, enters their login information, and logs in to the system. After logging in, they click the upload button, select the data file (for example, "sales_data.csv"), and upload it.

[0887] The server then receives the received data and performs an initial data cleansing process. The server loads the data into memory and uses a missing value imputation algorithm to fill in any missing values ​​in the data. The server also uses an outlier detection algorithm to correct any outliers, and standardizes the data format to make it suitable for analysis.

[0888] Next, the server extracts features from the preprocessed data. The server runs data analysis algorithms (e.g., principal component analysis (PCA) or clustering) to extract key features from the data. The server detects trends and patterns in the sales data and classifies it by time axis and product. The extracted features are used as the basis for hypothesis generation in the next step.

[0889] The user then selects the generative AI that is best suited to their business field from the multiple generative AI models provided by the system. The user checks the list of generative AI models displayed on the dashboard and selects the generative AI model that is best suited to their business field. For example, the user can select a generative AI specialized for the retail industry. The user clicks the selection button to notify the system of their selection.

[0890] After selecting a generative AI model, the server uses the selected generative AI to generate hypotheses based on the features extracted from the data. The server initializes the selected generative AI model and prepares it for analysis. The server inputs the feature data into the generative AI and executes the hypothesis generation process. The generated hypotheses are provided as specific business proposals, and the server stores the generated hypotheses in a database and organizes them into a format that can be presented to users.

[0891] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences. The server collects the user's input media (e.g., text comments and speech data) and runs an emotion analysis algorithm to analyze the user's emotional state. The server generates emotion data such as "happiness," "dissatisfaction," and "surprise," which are used in the hypothesis adjustment process.

[0892] Next, the server adjusts the generated hypotheses based on the emotional data. The server analyzes the user's emotional data to identify the user's interests and important items. The server prioritizes the generated hypotheses and makes important suggestions based on the user's emotions. The adjusted hypotheses are saved in the database again and presented to the user via the device.

[0893] Finally, the device presents the generated hypotheses and related data to the user. The device displays the hypotheses and related data (e.g., graphs and maps) using visualization tools. The user then develops a business strategy based on the presented hypotheses. By formulating a specific action plan and evaluating the usefulness of the hypotheses, the user determines the appropriate action. For example, the user may plan a promotional campaign in a specific region based on the previously presented hypotheses and prepare for its implementation.

[0894] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[0895] Example prompt sentence:

[0896] "Analyze seasonal sales trends from the given sales data and propose a hypothesis for the marketing strategy for the next season."

[0897] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0898] Step 1:

[0899] The user logs into the system and uploads the data file to be analyzed.

[0900] input:

[0901] The user provides login information (username, password) and the data file to be analyzed (e.g., "sales_data.csv").

[0902] Specific behavior:

[0903] The user opens a web browser and accesses the system's login page.

[0904] The user enters the login information and logs into the system.

[0905] The user clicks the upload button, selects the data file and uploads it.

[0906] output:

[0907] Data files uploaded to the server.

[0908] Step 2:

[0909] The server pre-processes the received data files.

[0910] input:

[0911] The uploaded data file (for example, "sales_data.csv").

[0912] Specific behavior:

[0913] The server reads the data file into memory.

[0914] The server uses a missing value imputation algorithm to impute missing values.

[0915] The server uses an outlier detection algorithm to correct the outliers.

[0916] The server will standardize the data format and prepare it in a state suitable for analysis.

[0917] output:

[0918] Clean data after preprocessing.

[0919] Step 3:

[0920] The server extracts features from the pre-processed data.

[0921] input:

[0922] Clean data after preprocessing.

[0923] Specific behavior:

[0924] The server runs data analysis algorithms (e.g., principal component analysis and clustering).

[0925] The server extracts the key features of the data.

[0926] The server detects trends and patterns in the sales data and categorizes it by timeline and product.

[0927] output:

[0928] Extracted feature data.

[0929] Step 4:

[0930] The user selects the most appropriate model from the generative AI models provided by the system.

[0931] input:

[0932] A list of generative AI models.

[0933] Specific behavior:

[0934] The user sees a list of generative AI models displayed on the dashboard.

[0935] Users select the generative AI model that best suits their business field.

[0936] The user clicks on the selection button to notify the system of the selection.

[0937] output:

[0938] Information about the selected generative AI model.

[0939] Step 5:

[0940] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[0941] input:

[0942] Extracted feature data and information on the selected generative AI model.

[0943] Specific behavior:

[0944] The server initializes the selected generative AI model and prepares it for analysis.

[0945] The server inputs the feature data into the generation AI and executes the hypothesis generation process.

[0946] The server stores the generated hypotheses in a database.

[0947] output:

[0948] Data for generated hypotheses.

[0949] Step 6:

[0950] The server activates an emotion engine to recognize the user's emotions.

[0951] input:

[0952] User input media (text comments, speech data).

[0953] Specific behavior:

[0954] The server collects the user's input media.

[0955] The server runs an emotion analysis algorithm to analyze the emotional state.

[0956] The server generates emotion data such as "happiness," "dissatisfaction," and "surprise."

[0957] output:

[0958] User emotion data.

[0959] Step 7:

[0960] The server adjusts the generated hypotheses based on the user's emotional data.

[0961] input:

[0962] Generated hypothesis data, user emotion data.

[0963] Specific behavior:

[0964] The server analyzes the user's emotional data and identifies the user's interests and important points.

[0965] The server prioritizes and makes key suggestions based on the generated hypotheses based on the user's emotions.

[0966] The server stores the adjusted hypotheses back in the database.

[0967] output:

[0968] Adjusted hypothesis data.

[0969] Step 8:

[0970] The terminal presents the generated hypotheses and associated data to the user.

[0971] input:

[0972] Adjusted hypothesis data.

[0973] Specific behavior:

[0974] The terminal displays the hypotheses and related data (graphs, maps) using visualization tools.

[0975] The terminal provides an interactive user interface that allows users to explore hypotheses in detail.

[0976] output:

[0977] Hypotheses presented to the user and associated data visualized.

[0978] Step 9:

[0979] The user develops a business strategy based on the presented hypotheses.

[0980] input:

[0981] Presented hypotheses and visualized relevant data.

[0982] Specific behavior:

[0983] The user reviews the presented hypotheses and related data.

[0984] Users evaluate the usefulness of the hypotheses and plan to incorporate them into their business strategy.

[0985] The user decides on a specific action plan (e.g., implementing a promotional campaign) and prepares for its implementation.

[0986] output:

[0987] A proposed business strategy and a concrete action plan.

[0988] (Application example 2)

[0989] 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."

[0990] Conventional data analysis systems are limited to analyzing massive amounts of data to generate hypotheses, and the generated hypotheses do not adequately reflect user sentiment or the specific needs of the business, making it difficult to improve the accuracy of decision-making support.In addition, they lack the ability to utilize generative AI models specialized for specific industries, and tend to provide hypotheses with low accuracy.

[0991] 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 a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, an emotion recognition means for acquiring and analyzing emotion data, and a means for adjusting the hypotheses based on the emotion data. This makes it possible to analyze user-provided data, select a generative AI model specialized for a specific industry, and generate highly accurate hypotheses that reflect the emotion data.

[0992] "Data analysis means" refers to a device or software that has the function of analyzing data provided by a user and extracting useful information or patterns.

[0993] A "means for selecting generative artificial intelligence" is a device or software that has the function of selecting an artificial intelligence model suitable for a particular industry or application.

[0994] A "means for generating hypotheses useful for a business" is a device or software that has the function of generating hypotheses useful for business decision-making based on analyzed data.

[0995] The "means for presenting the generated hypotheses" refers to a device or software that has the function of presenting the generated hypotheses to the user visually or as text.

[0996] "Emotion recognition means" refers to a device or software that has the function of analyzing emotions from a user's facial expressions, voice, writing, etc., and generating emotion data.

[0997] The "means for adjusting hypotheses based on emotional data" refers to a device or software that has the function of adjusting or correcting hypotheses generated by taking into account emotional data.

[0998] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a generation artificial intelligence selection means, a generation hypothesis generation means, a presentation means for generating hypotheses useful for business, an emotion recognition means, and a means for adjusting the hypotheses based on the emotion data.

[0999] Hardware and software used

[1000] Hardware: Regular PC or smartphone

[1001] Software: Python, pandas, scikit-learn, sentiment analysis library (e.g., sentiment_analysis)

[1002] System action

[1003] Uploading data

[1004] Users log in to the system, select the data file to be analyzed, and upload it. Data is typically in CSV or Excel format.

[1005] Examples:

[1006] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[1007] Data Preprocessing

[1008] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to make it suitable for analysis.

[1009] Examples:

[1010] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[1011] Feature extraction

[1012] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[1013] Examples:

[1014] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[1015] Selecting the Generator AI

[1016] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1017] Examples:

[1018] Users select a generative AI specialized for the retail industry.

[1019] Hypothesis generation

[1020] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[1021] Examples:

[1022] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[1023] Acquiring and analyzing emotion data

[1024] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1025] Examples:

[1026] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[1027] Emotional Hypothesis Adjustment

[1028] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[1029] Examples:

[1030] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[1031] Presenting a hypothesis

[1032] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1033] Examples:

[1034] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[1035] Prompt Sentence Examples

[1036] "I am very excited about the new product launch"

[1037] As a result, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using a generative AI model and emotion engine, thereby supporting fast and accurate decision-making.

[1038] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1039] Step 1:

[1040] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data to be analyzed is typically in CSV or Excel format. As a specific example, the user uploads "sales_data.csv," which contains sales data from the past year, to the system.

[1041] Input: Login information, data file (sales_data.csv)

[1042] Output: Raw data uploaded to the server

[1043] Step 2:

[1044] The server preprocesses the received data, cleansing it, filling in missing and outlier values, and standardizing the data format, thereby preparing the data for analysis.

[1045] Input: raw data (sales_data.csv)

[1046] Output: Cleansed data

[1047] Step 3:

[1048] The server performs feature extraction on the preprocessed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[1049] Input: Cleansed data

[1050] Output: Extracted features (e.g., monthly sales trends, product sales rankings)

[1051] Step 4:

[1052] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By selecting an AI model specialized for a specific industry, more accurate hypotheses can be obtained.

[1053] Input: Generative AI model selection information (e.g., AI specialized for the retail industry)

[1054] Output: The selected generative AI model

[1055] Step 5:

[1056] The server uses the selected generative AI model to generate hypotheses based on the features extracted from the data, and these hypotheses are provided to users as concrete business proposals.

[1057] Input: extracted features, selected generative AI model

[1058] Output: Generated hypotheses (e.g., sales in a particular region spike during the winter, so increased marketing in that region is beneficial)

[1059] Step 6:

[1060] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1061] Input: User input comments or utterances (e.g., "I am very excited about the new product launch")

[1062] Output: Emotion data (e.g., happiness, surprise)

[1063] Step 7:

[1064] The server adjusts the generated hypotheses based on the emotion data, providing suggestions that focus on items that the user is most interested in.

[1065] Input: Generated hypotheses, emotion data

[1066] Output: Adjusted hypotheses (e.g., a proposal for an aggressive promotion strategy for a new product for which users expressed "surprise")

[1067] Step 8:

[1068] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1069] Input: Adjusted hypotheses, visualization data (e.g., monthly sales graph, regional sales map)

[1070] Output: Hypotheses and associated data presented to the user

[1071] 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.

[1072] 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.

[1073] 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.

[1074] [Third embodiment]

[1075] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1076] 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.

[1077] 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).

[1078] 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.

[1079] 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.

[1080] 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).

[1081] 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.

[1082] 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.

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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."

[1087] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, and a means for presenting the generated hypotheses. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[1088] Program processing

[1089] Uploading data

[1090] Users upload the data they want to analyze into the system, provided in formats such as CSV or Excel files.

[1091] Examples:

[1092] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[1093] Data Preprocessing

[1094] After receiving the uploaded data, the server performs data cleansing, filling in missing or outlier values ​​and standardizing the data format.

[1095] Examples:

[1096] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[1097] Feature extraction

[1098] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[1099] Examples:

[1100] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[1101] Selecting the Generator AI

[1102] Users can select the AI ​​that best suits their business field from among the multiple generative AI models provided by the system, which allows them to utilize AI with industry-specific knowledge.

[1103] Examples:

[1104] Users select a generative AI specialized for the retail industry.

[1105] Hypothesis generation

[1106] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[1107] Examples:

[1108] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[1109] Presenting a hypothesis

[1110] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, allowing the user to intuitively understand them.

[1111] Examples:

[1112] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[1113] decision support

[1114] The user develops a business strategy and action plan based on the presented hypotheses, then evaluates whether the hypotheses are useful and adjusts them as necessary.

[1115] Examples:

[1116] The user plans a promotion campaign in a specific area based on the presented hypothesis and prepares for its execution.

[1117] As described above, the system of the present invention has the function of supporting rapid and accurate decision-making by efficiently analyzing data provided by users and using generative AI to generate and present useful hypotheses.

[1118] The processing flow will be explained below.

[1119] Program processing steps

[1120] The process flow in the system of the present invention will be specifically explained below step by step.

[1121] Step 1: Upload Data (User)

[1122] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[1123] Specific behavior:

[1124] Users access the system through a browser.

[1125] Use the data file specification dialog box to select a local file.

[1126] Click the "Upload" button to send the data to the server.

[1127] Step 2: Data preprocessing (server)

[1128] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[1129] Specific behavior:

[1130] The server detects missing values ​​in the data and performs the appropriate imputation process.

[1131] Anomalous data points are detected and corrected or removed accordingly.

[1132] Consistency of data types (e.g. converting strings to numbers).

[1133] Step 3: Feature extraction (server)

[1134] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[1135] Specific behavior:

[1136] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[1137] Analyze the frequency distribution of categorical data and extract important features.

[1138] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[1139] Step 4: User selection of the generating AI

[1140] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1141] Specific behavior:

[1142] Users select an industry from a drop-down menu within the system.

[1143] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[1144] Step 5: Hypothesis generation (server)

[1145] The server uses the selected generation AI to generate hypotheses useful for the business based on the extracted features. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[1146] Specific behavior:

[1147] The server provides the features as input data to the generative AI model.

[1148] Generative AI analyzes input data and generates hypotheses.

[1149] Hypotheses are formalized into concrete action items.

[1150] Step 6: Present the hypothesis (terminal)

[1151] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1152] Specific behavior:

[1153] The terminal displays the hypotheses and data received from the server on a user interface.

[1154] Visualize data using graphs and charts.

[1155] Displays a summary of the hypothesis in text format.

[1156] Step 7: Decision Support (User)

[1157] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[1158] Specific behavior:

[1159] The user checks the details of the hypothesis on the interface.

[1160] Share your hypotheses with team members and gather feedback.

[1161] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[1162] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[1163] Example 1

[1164] 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."

[1165] Making fast and accurate decisions in business requires efficiently analyzing large amounts of data and quickly generating useful hypotheses from that data. However, with conventional systems, the process from uploading data to generating hypotheses is fragmented, and preprocessing such as data cleansing and feature extraction is often complex and time-consuming, making it difficult to support effective decision-making.

[1166] 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.

[1167] In this invention, the server includes a means for uploading data, a means for performing data preprocessing, and a means for extracting features. This enables consistent analysis of data provided by users and rapid and accurate generation of hypotheses. Specifically, the system solves the conventional problems by automating a series of processes from data uploading, preprocessing, feature extraction, selection of generative AI model, hypothesis generation, and presentation of the generated hypotheses and decision-making support.

[1168] "Data analysis means" is a means for analyzing uploaded data and extracting useful information and patterns from the data.

[1169] The "means for selecting a generating AI" is a means for the user to select an AI model specialized for a particular industry of their choice.

[1170] "Means for generating hypotheses useful for business" refers to means for generating hypotheses useful for business from analyzed data and features.

[1171] The "means for presenting the generated hypothesis" is a means for visualizing and presenting data related to the generated hypothesis to the user.

[1172] The "means for uploading data" refers to a means for a user to upload data that the user wishes to analyze to the system.

[1173] The "means for data preprocessing" refers to a means for performing preprocessing on uploaded data, such as filling in missing values ​​and correcting outliers.

[1174] The "means for extracting features" refers to a means for extracting business-important features from data that has undergone preprocessing.

[1175] The "means for supporting decision-making" is a means for supporting a user in making effective decisions based on the generated hypotheses.

[1176] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. This system includes a data analysis means, a means for selecting a generating AI, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, a means for uploading data, a means for data preprocessing, a means for extracting features, and a means for supporting decision-making.

[1177] First, the user uploads the data they want to analyze to the system. The data is provided in formats such as CSV or Excel files. For example, the user can upload "sales_data.csv," which contains sales data from the past year, to the system.

[1178] Next, the server receives the uploaded data and performs data cleansing. During this process, missing values ​​and outliers are filled in and the data format is standardized. For example, the server fills in missing values ​​and corrects outliers, and prepares the data in "sales_data.csv" in an analyzable format.

[1179] The server then performs feature extraction on the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data to extract features useful for business. For example, the server performs trend analysis on sales data to extract monthly sales trends and product sales rankings.

[1180] Next, users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system. This allows AI with industry-specific knowledge to be used. For example, users can select a generative AI specialized for the retail industry.

[1181] Using the selected generative AI model, the server generates hypotheses based on the features extracted from the data. The generated hypotheses are presented as specific business proposals. The server generates the hypothesis that "sales in a specific region increase sharply during the winter, so strengthening marketing in that region would be effective."

[1182] This hypothesis and related data are presented to the user via the device. Data visualization based on the hypothesis is also performed simultaneously, allowing the user to intuitively understand. For example, in addition to the generated hypothesis, the device can display a graph of monthly sales and a map of regional sales to the user.

[1183] Finally, users develop a business strategy and an action plan based on the presented hypotheses. They then evaluate whether the hypotheses are useful and adjust them as necessary. For example, users may plan a promotional campaign in a specific region based on the presented hypotheses and prepare for its implementation.

[1184] Below are some example prompts to input to a generative AI model:

[1185] Example prompt 1:

[1186] "Using sales data from the past year, please analyze monthly sales trends and product sales rankings to generate hypotheses that will be useful for future marketing strategies."

[1187] Example prompt 2:

[1188] "Generate hypotheses that suggest optimal marketing strategies based on seasonal sales fluctuations in a specific region."

[1189] The above is an embodiment of the present invention. This system efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[1190] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1191] Step 1: Upload your data

[1192] Users upload the data they want to analyze to the system, provided in formats such as CSV or Excel files.

[1193] Specific behavior:

[1194] The user selects the "sales_data.csv" file from their PC and clicks the upload button.

[1195] The server receives the uploaded file and stores it in storage.

[1196] input:

[1197] "sales_data.csv" file

[1198] output:

[1199] Data files saved in storage

[1200] Step 2: Data Preprocessing

[1201] After receiving the uploaded data, the server performs data cleansing, i.e., filling in missing or outlier values ​​and standardizing the data format.

[1202] Specific behavior:

[1203] The server reads the uploaded "sales_data.csv" and identifies rows that contain missing values.

[1204] The server imputes missing values ​​with the mean value or based on specified rules.

[1205] The server detects outliers (e.g., negative sales figures) and corrects them.

[1206] The server standardizes data such as date formats.

[1207] input:

[1208] "sales_data.csv" file saved in storage

[1209] output:

[1210] Preprocessed dataset

[1211] Step 3: Feature extraction

[1212] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[1213] Specific behavior:

[1214] The server extracts monthly sales data and performs time series analysis.

[1215] The server calculates the sales frequency by category (e.g., by product category).

[1216] The server adds these analysis results to the data frame as new features.

[1217] input:

[1218] Preprocessed dataset

[1219] output:

[1220] Dataset with added features

[1221] Step 4: Selecting the Generator AI

[1222] Users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system.

[1223] Specific behavior:

[1224] The user selects a generative AI model for the retail industry on the system's generative AI selection screen.

[1225] The user checks the model description and clicks the selection button.

[1226] The server loads the selected generative AI model.

[1227] input:

[1228] User-generated AI model selection information

[1229] output:

[1230] Loaded generative AI model

[1231] Step 5: Hypothesis generation

[1232] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[1233] Specific behavior:

[1234] The server inputs the feature extraction results into the generation AI as prompts.

[1235] The server stores the generated hypotheses in a database.

[1236] input:

[1237] Dataset with added features

[1238] Loaded generative AI model

[1239] output:

[1240] Generated hypotheses

[1241] Step 6: State your hypotheses

[1242] The device presents the generated hypotheses and related data to the user, while also visualizing the data based on the hypotheses.

[1243] Specific behavior:

[1244] The server transmits the hypotheses and associated data to the terminal.

[1245] The terminal generates a report screen containing the hypotheses and displays related graphs and maps.

[1246] The user can view the hypothesis and the supporting data on their device.

[1247] input:

[1248] Generated hypotheses

[1249] Related data

[1250] output:

[1251] Hypotheses presented to the user and related data

[1252] Step 7: Decision support

[1253] The user develops a business strategy and action plan based on the presented hypotheses, evaluates whether the hypotheses are useful, and adjusts the hypotheses as necessary.

[1254] Specific behavior:

[1255] The user creates a proposal for a promotion campaign based on the presented hypothesis.

[1256] To assess the reliability of the hypothesis, the user compares it with past performance data.

[1257] Users can improve the accuracy of hypotheses by running campaigns and feeding back the results to the system.

[1258] input:

[1259] Hypotheses presented to the user and related data

[1260] output:

[1261] Action plan and its evaluation results

[1262] (Application example 1)

[1263] 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."

[1264] In recent years, it has become increasingly difficult for users of content distribution services to efficiently find content that suits them from the wide variety of content available. This has led to problems such as lower user satisfaction and a decrease in frequency of service use. Furthermore, existing recommendation systems rely on limited data and specific algorithms, limiting the accuracy of their analysis and recommendations. In response to this situation, there is a demand for a system that can efficiently analyze large amounts of data and make highly accurate content recommendations based on users' viewing habits.

[1265] 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.

[1266] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, and a means for analyzing viewing habits from user data and recommending content based on the viewing history. This enables highly accurate content recommendations based on the user's viewing history, thereby increasing user satisfaction. Furthermore, by using an industry-specific generative AI, optimal content recommendations can be made according to the needs of a specific industry.

[1267] The "data analysis means" is a means for analyzing data provided by a user and extracting useful information from the data.

[1268] A "means for selecting generative AI" is a means for selecting the AI ​​model that is best suited to a user's specific purpose or industry from among multiple generative AI models.

[1269] A "means for generating hypotheses useful for a business" is a means for generating hypotheses useful for a specific business using analyzed data and a selected generative AI model.

[1270] The "means for presenting the generated hypotheses" is a means for presenting the generated hypotheses to the user in an easy-to-understand manner.

[1271] "Means for analyzing viewing trends from user data and recommending content based on viewing history" refers to means for analyzing a user's viewing history and evaluation data and recommending the most suitable content to the user based on the results.

[1272] An embodiment of the present invention is based on a system configured as follows: This system has the function of allowing a user to provide viewing history and rating data, analyzing the data, generating hypotheses, and recommending optimal content to the user.

[1273] Uploading data

[1274] Users upload their viewing history and rating data to the system in CSV files. For example, a user might upload a file called "user_watch_data.csv." At this time, the device sends the user's data to the server.

[1275] Data Preprocessing

[1276] The server receives the uploaded data and performs data cleansing, imputing missing values ​​and outliers, and arranging the data format. Specifically, it uses the Pandas and NumPy libraries to impute missing values ​​and remove outliers.

[1277] Feature extraction

[1278] Next, the server extracts viewing and rating trends from the viewing data, including the number of views and average ratings. Based on this, the server generates data features and uses them for analysis.

[1279] Selecting a generative AI model

[1280] Users can select the generative AI model that best suits their needs and industry from among the multiple generative AI models provided. For example, they can select a specialized generative AI model for recommending entertainment content.

[1281] Hypothesis generation

[1282] Using the selected generative AI model, the server generates recommended content based on viewing habits from user data. This hypothesis generation process uses a generative AI model specialized for the entertainment industry.

[1283] Presenting a hypothesis

[1284] The generated recommended content is presented to the user via the device, and the user can check their viewing history and a list of recommended content in an intuitive manner.

[1285] Examples and prompts

[1286] For example, by providing the following prompt to a generative AI model, it can generate optimal recommendations for the user:

[1287] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[1288] To realize this system, Python programs, data analysis libraries such as Pandas and NumPy, and generative AI models specialized for specific applications are used.Technically, the system is configured to seamlessly upload data, preprocess it, extract features, analyze it using the generative AI model, and present the results.

[1289] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1290] Step 1:

[1291] Users upload their viewing history and rating data in CSV file format to their device. The device then sends this file to the server. The input is a data file such as "user_watch_data.csv," and the output is the raw data received by the server.

[1292] Step 2:

[1293] The server performs a data cleansing process on the received data. For example, it uses Pandas to fill in missing values ​​and remove outliers. The input is raw data, and the output is cleansed, formatted data. Specifically, the process involves using data.fillna(data.mean(), inplace=True).

[1294] Step 3:

[1295] The server extracts features from the cleansed data. For example, it aggregates the number of views and average ratings to generate a new dataset. The input is the cleansed formatted data, and the output is the extracted feature data. Specifically, the following process is performed: features = data.groupby('content_id').agg({'views': 'sum', 'ratings': 'mean'}).reset_index().

[1296] Step 4:

[1297] The user selects an appropriate generative AI model from among several provided models. The selected generative AI model is selected to be specialized in a specific field. The input is the user's selection, and the output is the selected generative AI model itself.

[1298] Step 5:

[1299] The server uses the selected generative AI model to generate a hypothesis based on the extracted feature data. This hypothesis is what is presented as recommended content to the user. The input is the feature data and the selected generative AI model, and the output is the generated recommendation hypothesis. Specifically, the server inputs a prompt to the generative AI model and obtains the result.

[1300] Step 6:

[1301] The device presents the generated hypotheses, i.e., recommended content, to the user. The user selects, watches, and rates content based on these hypotheses. The input is the generated recommendation hypotheses, and the output is a content list presented to the user.

[1302] Examples and prompts

[1303] For example, in the following example, a prompt sentence based on the viewing history of user ID: 12345 is input to the generative AI model:

[1304] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[1305] Based on this prompt, the generative AI model analyzes it, generates recommended content tailored to the user, and presents it to the user via their device.

[1306] 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.

[1307] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the user's emotions. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[1308] Program processing

[1309] Uploading data

[1310] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[1311] Examples:

[1312] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[1313] Data Preprocessing

[1314] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[1315] Examples:

[1316] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[1317] Feature extraction

[1318] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[1319] Examples:

[1320] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[1321] Selecting the Generator AI

[1322] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1323] Examples:

[1324] Users select a generative AI specialized for the retail industry.

[1325] Hypothesis generation

[1326] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[1327] Examples:

[1328] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[1329] Acquiring and analyzing emotion data

[1330] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1331] Examples:

[1332] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[1333] Emotional Hypothesis Adjustment

[1334] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[1335] Examples:

[1336] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[1337] Presenting a hypothesis

[1338] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1339] Examples:

[1340] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[1341] decision support

[1342] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[1343] Examples:

[1344] Based on the above-mentioned hypothesis, the user plans a promotion campaign for a specific region and prepares for its execution.

[1345] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[1346] The processing flow will be explained below.

[1347] Program processing steps

[1348] The process flow in the system of the present invention will be specifically explained below step by step.

[1349] Step 1: Upload Data (User)

[1350] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[1351] Specific behavior:

[1352] Users access the system through a browser.

[1353] Use the data file specification dialog box to select a local file.

[1354] Click the "Upload" button to send the data to the server.

[1355] Step 2: Data preprocessing (server)

[1356] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[1357] Specific behavior:

[1358] The server detects missing values ​​in the data and performs the appropriate imputation process.

[1359] Anomalous data points are detected and corrected or removed accordingly.

[1360] Consistency of data types (e.g. converting strings to numbers).

[1361] Step 3: Feature extraction (server)

[1362] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[1363] Specific behavior:

[1364] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[1365] Analyze the frequency distribution of categorical data and extract important features.

[1366] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[1367] Step 4: User selection of the generating AI

[1368] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1369] Specific behavior:

[1370] Users select an industry from a drop-down menu within the system.

[1371] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[1372] Step 5: Hypothesis generation (server)

[1373] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[1374] Specific behavior:

[1375] The server provides the features as input data to the generative AI model.

[1376] Generative AI analyzes input data and generates hypotheses.

[1377] Hypotheses are formalized into concrete action items.

[1378] Step 6: Acquiring and analyzing emotion data (server)

[1379] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1380] Specific behavior:

[1381] The server receives text comments and voice data entered by the user.

[1382] The emotion engine analyzes the received data and recognizes the user's emotional state (happiness, sadness, anger, etc.).

[1383] The recognized emotional state is stored as emotion data.

[1384] Step 7: Emotion-based hypothesis adjustment (server)

[1385] The server adjusts the hypotheses based on the acquired emotional data, and by making specific suggestions that take the user's emotional state into account, the accuracy and usefulness of the hypotheses are improved.

[1386] Specific behavior:

[1387] The server integrates the generated hypotheses with emotional data and makes adjustments according to the user's interests and expectations.

[1388] Regenerate the adjusted hypotheses as a new business proposition.

[1389] Step 8: Present the hypothesis (terminal)

[1390] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, providing information in a format that is easy for the user to understand.

[1391] Specific behavior:

[1392] The terminal displays the hypotheses and data received from the server on a user interface.

[1393] Visualize data using graphs and charts.

[1394] Displays a summary of the hypothesis in text format.

[1395] Step 9: Decision Support (User)

[1396] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[1397] Specific behavior:

[1398] The user checks the details of the hypothesis on the interface.

[1399] Share your hypotheses with team members and gather feedback.

[1400] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[1401] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[1402] Example 2

[1403] 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."

[1404] Conventional data analysis systems do not generate or adjust hypotheses taking user emotions into account, making it difficult to provide business proposals that truly interest users. Furthermore, the accuracy of generated hypotheses can be reduced by not being able to select industry-specific AI. This makes it difficult to support fast and accurate decision-making.

[1405] 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.

[1406] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for a business, a means for activating an emotion engine that recognizes the user's emotions, and a means for adjusting the hypotheses based on the user's emotion data, thereby enabling highly accurate hypothesis generation that takes the user's emotions into consideration.

[1407] "Data analysis means" refers to means for analyzing the provided data, extracting information, preprocessing, and analyzing features.

[1408] The "means for selecting a generative AI" is a means for a user to select an AI specialized for a specific industry.

[1409] The "means for generating hypotheses" is a means for generating hypotheses useful for a business using analyzed data and selected artificial intelligence.

[1410] The "means for presenting hypotheses" is a means for visually displaying the generated hypotheses and providing them to the user in a format that is easy to understand.

[1411] The "emotion engine" is an engine that analyzes emotions from the user's facial expressions, voice, and text, and generates emotional data.

[1412] The "means for adjusting hypotheses based on user emotional data" refers to a means for adjusting existing hypotheses based on user emotional data and placing emphasis on items that interest or are considered important by the user.

[1413] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the emotions of the user. Specific embodiments of the present invention are described in detail below.

[1414] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data format is typically a CSV or Excel file. Specifically, the user opens a web browser, accesses the system's login page, enters their login information, and logs in to the system. After logging in, they click the upload button, select the data file (for example, "sales_data.csv"), and upload it.

[1415] The server then receives the received data and performs an initial data cleansing process. The server loads the data into memory and uses a missing value imputation algorithm to fill in any missing values ​​in the data. The server also uses an outlier detection algorithm to correct any outliers, and standardizes the data format to make it suitable for analysis.

[1416] Next, the server extracts features from the preprocessed data. The server runs data analysis algorithms (e.g., principal component analysis (PCA) or clustering) to extract key features from the data. The server detects trends and patterns in the sales data and classifies it by time axis and product. The extracted features are used as the basis for hypothesis generation in the next step.

[1417] The user then selects the generative AI that is best suited to their business field from the multiple generative AI models provided by the system. The user checks the list of generative AI models displayed on the dashboard and selects the generative AI model that is best suited to their business field. For example, the user can select a generative AI specialized for the retail industry. The user clicks the selection button to notify the system of their selection.

[1418] After selecting a generative AI model, the server uses the selected generative AI to generate hypotheses based on the features extracted from the data. The server initializes the selected generative AI model and prepares it for analysis. The server inputs the feature data into the generative AI and executes the hypothesis generation process. The generated hypotheses are provided as specific business proposals, and the server stores the generated hypotheses in a database and organizes them into a format that can be presented to users.

[1419] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences. The server collects the user's input media (e.g., text comments and speech data) and runs an emotion analysis algorithm to analyze the user's emotional state. The server generates emotion data such as "happiness," "dissatisfaction," and "surprise," which are used in the hypothesis adjustment process.

[1420] Next, the server adjusts the generated hypotheses based on the emotional data. The server analyzes the user's emotional data to identify the user's interests and important items. The server prioritizes the generated hypotheses and makes important suggestions based on the user's emotions. The adjusted hypotheses are saved in the database again and presented to the user via the device.

[1421] Finally, the device presents the generated hypotheses and related data to the user. The device displays the hypotheses and related data (e.g., graphs and maps) using visualization tools. The user then develops a business strategy based on the presented hypotheses. By formulating a specific action plan and evaluating the usefulness of the hypotheses, the user determines the appropriate action. For example, the user may plan a promotional campaign in a specific region based on the previously presented hypotheses and prepare for its implementation.

[1422] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[1423] Example prompt sentence:

[1424] "Analyze seasonal sales trends from the given sales data and propose a hypothesis for the marketing strategy for the next season."

[1425] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] The user logs into the system and uploads the data file to be analyzed.

[1428] input:

[1429] The user provides login information (username, password) and the data file to be analyzed (e.g., "sales_data.csv").

[1430] Specific behavior:

[1431] The user opens a web browser and accesses the system's login page.

[1432] The user enters the login information and logs into the system.

[1433] The user clicks the upload button, selects the data file and uploads it.

[1434] output:

[1435] Data files uploaded to the server.

[1436] Step 2:

[1437] The server pre-processes the received data files.

[1438] input:

[1439] The uploaded data file (for example, "sales_data.csv").

[1440] Specific behavior:

[1441] The server reads the data file into memory.

[1442] The server uses a missing value imputation algorithm to impute missing values.

[1443] The server uses an outlier detection algorithm to correct the outliers.

[1444] The server will standardize the data format and prepare it in a state suitable for analysis.

[1445] output:

[1446] Clean data after preprocessing.

[1447] Step 3:

[1448] The server extracts features from the pre-processed data.

[1449] input:

[1450] Clean data after preprocessing.

[1451] Specific behavior:

[1452] The server runs data analysis algorithms (e.g., principal component analysis and clustering).

[1453] The server extracts the key features of the data.

[1454] The server detects trends and patterns in the sales data and categorizes it by timeline and product.

[1455] output:

[1456] Extracted feature data.

[1457] Step 4:

[1458] The user selects the most appropriate model from the generative AI models provided by the system.

[1459] input:

[1460] A list of generative AI models.

[1461] Specific behavior:

[1462] The user sees a list of generative AI models displayed on the dashboard.

[1463] Users select the generative AI model that best suits their business field.

[1464] The user clicks on the selection button to notify the system of the selection.

[1465] output:

[1466] Information about the selected generative AI model.

[1467] Step 5:

[1468] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[1469] input:

[1470] Extracted feature data and information on the selected generative AI model.

[1471] Specific behavior:

[1472] The server initializes the selected generative AI model and prepares it for analysis.

[1473] The server inputs the feature data into the generation AI and executes the hypothesis generation process.

[1474] The server stores the generated hypotheses in a database.

[1475] output:

[1476] Data for generated hypotheses.

[1477] Step 6:

[1478] The server activates an emotion engine to recognize the user's emotions.

[1479] input:

[1480] User input media (text comments, speech data).

[1481] Specific behavior:

[1482] The server collects the user's input media.

[1483] The server runs an emotion analysis algorithm to analyze the emotional state.

[1484] The server generates emotion data such as "happiness," "dissatisfaction," and "surprise."

[1485] output:

[1486] User emotion data.

[1487] Step 7:

[1488] The server adjusts the generated hypotheses based on the user's emotional data.

[1489] input:

[1490] Generated hypothesis data, user emotion data.

[1491] Specific behavior:

[1492] The server analyzes the user's emotional data and identifies the user's interests and important points.

[1493] The server prioritizes and makes key suggestions based on the generated hypotheses based on the user's emotions.

[1494] The server stores the adjusted hypotheses back in the database.

[1495] output:

[1496] Adjusted hypothesis data.

[1497] Step 8:

[1498] The terminal presents the generated hypotheses and associated data to the user.

[1499] input:

[1500] Adjusted hypothesis data.

[1501] Specific behavior:

[1502] The terminal displays the hypotheses and related data (graphs, maps) using visualization tools.

[1503] The terminal provides an interactive user interface that allows users to explore hypotheses in detail.

[1504] output:

[1505] Hypotheses presented to the user and associated data visualized.

[1506] Step 9:

[1507] The user develops a business strategy based on the presented hypotheses.

[1508] input:

[1509] Presented hypotheses and visualized relevant data.

[1510] Specific behavior:

[1511] The user reviews the presented hypotheses and related data.

[1512] Users evaluate the usefulness of the hypotheses and plan to incorporate them into their business strategy.

[1513] The user decides on a specific action plan (e.g., implementing a promotional campaign) and prepares for its implementation.

[1514] output:

[1515] A proposed business strategy and a concrete action plan.

[1516] (Application example 2)

[1517] 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."

[1518] Conventional data analysis systems are limited to analyzing massive amounts of data to generate hypotheses, and the generated hypotheses do not adequately reflect user sentiment or the specific needs of the business, making it difficult to improve the accuracy of decision-making support.In addition, they lack the ability to utilize generative AI models specialized for specific industries, and tend to provide hypotheses with low accuracy.

[1519] 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 a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, an emotion recognition means for acquiring and analyzing emotion data, and a means for adjusting the hypotheses based on the emotion data. This makes it possible to analyze user-provided data, select a generative AI model specialized for a specific industry, and generate highly accurate hypotheses that reflect the emotion data.

[1520] "Data analysis means" refers to a device or software that has the function of analyzing data provided by a user and extracting useful information or patterns.

[1521] A "means for selecting generative artificial intelligence" is a device or software that has the function of selecting an artificial intelligence model suitable for a particular industry or application.

[1522] A "means for generating hypotheses useful for a business" is a device or software that has the function of generating hypotheses useful for business decision-making based on analyzed data.

[1523] The "means for presenting the generated hypotheses" refers to a device or software that has the function of presenting the generated hypotheses to the user visually or as text.

[1524] "Emotion recognition means" refers to a device or software that has the function of analyzing emotions from a user's facial expressions, voice, writing, etc., and generating emotion data.

[1525] The "means for adjusting hypotheses based on emotional data" refers to a device or software that has the function of adjusting or correcting hypotheses generated by taking into account emotional data.

[1526] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a generation artificial intelligence selection means, a generation hypothesis generation means, a presentation means for generating hypotheses useful for business, an emotion recognition means, and a means for adjusting the hypotheses based on the emotion data.

[1527] Hardware and software used

[1528] Hardware: Regular PC or smartphone

[1529] Software: Python, pandas, scikit-learn, sentiment analysis library (e.g., sentiment_analysis)

[1530] System action

[1531] Uploading data

[1532] Users log in to the system, select the data file to be analyzed, and upload it. Data is typically in CSV or Excel format.

[1533] Examples:

[1534] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[1535] Data Preprocessing

[1536] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to make it suitable for analysis.

[1537] Examples:

[1538] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[1539] Feature extraction

[1540] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[1541] Examples:

[1542] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[1543] Selecting the Generator AI

[1544] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1545] Examples:

[1546] Users select a generative AI specialized for the retail industry.

[1547] Hypothesis generation

[1548] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[1549] Examples:

[1550] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[1551] Acquiring and analyzing emotion data

[1552] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1553] Examples:

[1554] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[1555] Emotional Hypothesis Adjustment

[1556] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[1557] Examples:

[1558] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[1559] Presenting a hypothesis

[1560] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1561] Examples:

[1562] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[1563] Prompt Sentence Examples

[1564] "I am very excited about the new product launch"

[1565] As a result, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using a generative AI model and emotion engine, thereby supporting fast and accurate decision-making.

[1566] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1567] Step 1:

[1568] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data to be analyzed is typically in CSV or Excel format. As a specific example, the user uploads "sales_data.csv," which contains sales data from the past year, to the system.

[1569] Input: Login information, data file (sales_data.csv)

[1570] Output: Raw data uploaded to the server

[1571] Step 2:

[1572] The server preprocesses the received data, cleansing it, filling in missing and outlier values, and standardizing the data format, thereby preparing the data for analysis.

[1573] Input: raw data (sales_data.csv)

[1574] Output: Cleansed data

[1575] Step 3:

[1576] The server performs feature extraction on the preprocessed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[1577] Input: Cleansed data

[1578] Output: Extracted features (e.g., monthly sales trends, product sales rankings)

[1579] Step 4:

[1580] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By selecting an AI model specialized for a specific industry, more accurate hypotheses can be obtained.

[1581] Input: Generative AI model selection information (e.g., AI specialized for the retail industry)

[1582] Output: The selected generative AI model

[1583] Step 5:

[1584] The server uses the selected generative AI model to generate hypotheses based on the features extracted from the data, and these hypotheses are provided to users as concrete business proposals.

[1585] Input: extracted features, selected generative AI model

[1586] Output: Generated hypotheses (e.g., sales in a particular region spike during the winter, so increased marketing in that region is beneficial)

[1587] Step 6:

[1588] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1589] Input: User input comments or utterances (e.g., "I am very excited about the new product launch")

[1590] Output: Emotion data (e.g., happiness, surprise)

[1591] Step 7:

[1592] The server adjusts the generated hypotheses based on the emotion data, providing suggestions that focus on items that the user is most interested in.

[1593] Input: Generated hypotheses, emotion data

[1594] Output: Adjusted hypotheses (e.g., a proposal for an aggressive promotion strategy for a new product for which users expressed "surprise")

[1595] Step 8:

[1596] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1597] Input: Adjusted hypotheses, visualization data (e.g., monthly sales graph, regional sales map)

[1598] Output: Hypotheses and associated data presented to the user

[1599] 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.

[1600] 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.

[1601] 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.

[1602] [Fourth embodiment]

[1603] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1604] 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.

[1605] 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).

[1606] 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.

[1607] 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.

[1608] 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).

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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."

[1616] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, and a means for presenting the generated hypotheses. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[1617] Program processing

[1618] Uploading data

[1619] Users upload the data they want to analyze into the system, provided in formats such as CSV or Excel files.

[1620] Examples:

[1621] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[1622] Data Preprocessing

[1623] After receiving the uploaded data, the server performs data cleansing, filling in missing or outlier values ​​and standardizing the data format.

[1624] Examples:

[1625] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[1626] Feature extraction

[1627] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[1628] Examples:

[1629] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[1630] Selecting the Generator AI

[1631] Users can select the AI ​​that best suits their business field from among the multiple generative AI models provided by the system, which allows them to utilize AI with industry-specific knowledge.

[1632] Examples:

[1633] Users select a generative AI specialized for the retail industry.

[1634] Hypothesis generation

[1635] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[1636] Examples:

[1637] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[1638] Presenting a hypothesis

[1639] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, allowing the user to intuitively understand them.

[1640] Examples:

[1641] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[1642] decision support

[1643] The user develops a business strategy and action plan based on the presented hypotheses, then evaluates whether the hypotheses are useful and adjusts them as necessary.

[1644] Examples:

[1645] The user plans a promotion campaign in a specific area based on the presented hypothesis and prepares for its execution.

[1646] As described above, the system of the present invention has the function of supporting rapid and accurate decision-making by efficiently analyzing data provided by users and using generative AI to generate and present useful hypotheses.

[1647] The processing flow will be explained below.

[1648] Program processing steps

[1649] The process flow in the system of the present invention will be specifically explained below step by step.

[1650] Step 1: Upload Data (User)

[1651] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[1652] Specific behavior:

[1653] Users access the system through a browser.

[1654] Use the data file specification dialog box to select a local file.

[1655] Click the "Upload" button to send the data to the server.

[1656] Step 2: Data preprocessing (server)

[1657] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[1658] Specific behavior:

[1659] The server detects missing values ​​in the data and performs the appropriate imputation process.

[1660] Anomalous data points are detected and corrected or removed accordingly.

[1661] Consistency of data types (e.g. converting strings to numbers).

[1662] Step 3: Feature extraction (server)

[1663] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[1664] Specific behavior:

[1665] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[1666] Analyze the frequency distribution of categorical data and extract important features.

[1667] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[1668] Step 4: User selection of the generating AI

[1669] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1670] Specific behavior:

[1671] Users select an industry from a drop-down menu within the system.

[1672] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[1673] Step 5: Hypothesis generation (server)

[1674] The server uses the selected generation AI to generate hypotheses useful for the business based on the extracted features. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[1675] Specific behavior:

[1676] The server provides the features as input data to the generative AI model.

[1677] Generative AI analyzes input data and generates hypotheses.

[1678] Hypotheses are formalized into concrete action items.

[1679] Step 6: Present the hypothesis (terminal)

[1680] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1681] Specific behavior:

[1682] The terminal displays the hypotheses and data received from the server on a user interface.

[1683] Visualize data using graphs and charts.

[1684] Displays a summary of the hypothesis in text format.

[1685] Step 7: Decision Support (User)

[1686] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[1687] Specific behavior:

[1688] The user checks the details of the hypothesis on the interface.

[1689] Share your hypotheses with team members and gather feedback.

[1690] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[1691] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[1692] Example 1

[1693] 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."

[1694] Making fast and accurate decisions in business requires efficiently analyzing large amounts of data and quickly generating useful hypotheses from that data. However, with conventional systems, the process from uploading data to generating hypotheses is fragmented, and preprocessing such as data cleansing and feature extraction is often complex and time-consuming, making it difficult to support effective decision-making.

[1695] 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.

[1696] In this invention, the server includes a means for uploading data, a means for performing data preprocessing, and a means for extracting features. This enables consistent analysis of data provided by users and rapid and accurate generation of hypotheses. Specifically, the system solves the conventional problems by automating a series of processes from data uploading, preprocessing, feature extraction, selection of generative AI model, hypothesis generation, and presentation of the generated hypotheses and decision-making support.

[1697] "Data analysis means" is a means for analyzing uploaded data and extracting useful information and patterns from the data.

[1698] The "means for selecting a generating AI" is a means for the user to select an AI model specialized for a particular industry of their choice.

[1699] "Means for generating hypotheses useful for business" refers to means for generating hypotheses useful for business from analyzed data and features.

[1700] The "means for presenting the generated hypothesis" is a means for visualizing and presenting data related to the generated hypothesis to the user.

[1701] The "means for uploading data" refers to a means for a user to upload data that the user wishes to analyze to the system.

[1702] The "means for data preprocessing" refers to a means for performing preprocessing on uploaded data, such as filling in missing values ​​and correcting outliers.

[1703] The "means for extracting features" refers to a means for extracting business-important features from data that has undergone preprocessing.

[1704] The "means for supporting decision-making" is a means for supporting a user in making effective decisions based on the generated hypotheses.

[1705] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. This system includes a data analysis means, a means for selecting a generating AI, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, a means for uploading data, a means for data preprocessing, a means for extracting features, and a means for supporting decision-making.

[1706] First, the user uploads the data they want to analyze to the system. The data is provided in formats such as CSV or Excel files. For example, the user can upload "sales_data.csv," which contains sales data from the past year, to the system.

[1707] Next, the server receives the uploaded data and performs data cleansing. During this process, missing values ​​and outliers are filled in and the data format is standardized. For example, the server fills in missing values ​​and corrects outliers, and prepares the data in "sales_data.csv" in an analyzable format.

[1708] The server then performs feature extraction on the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data to extract features useful for business. For example, the server performs trend analysis on sales data to extract monthly sales trends and product sales rankings.

[1709] Next, users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system. This allows AI with industry-specific knowledge to be used. For example, users can select a generative AI specialized for the retail industry.

[1710] Using the selected generative AI model, the server generates hypotheses based on the features extracted from the data. The generated hypotheses are presented as specific business proposals. The server generates the hypothesis that "sales in a specific region increase sharply during the winter, so strengthening marketing in that region would be effective."

[1711] This hypothesis and related data are presented to the user via the device. Data visualization based on the hypothesis is also performed simultaneously, allowing the user to intuitively understand. For example, in addition to the generated hypothesis, the device can display a graph of monthly sales and a map of regional sales to the user.

[1712] Finally, users develop a business strategy and an action plan based on the presented hypotheses. They then evaluate whether the hypotheses are useful and adjust them as necessary. For example, users may plan a promotional campaign in a specific region based on the presented hypotheses and prepare for its implementation.

[1713] Below are some example prompts to input to a generative AI model:

[1714] Example prompt 1:

[1715] "Using sales data from the past year, please analyze monthly sales trends and product sales rankings to generate hypotheses that will be useful for future marketing strategies."

[1716] Example prompt 2:

[1717] "Generate hypotheses that suggest optimal marketing strategies based on seasonal sales fluctuations in a specific region."

[1718] The above is an embodiment of the present invention. This system efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI, thereby supporting fast and accurate decision-making.

[1719] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1720] Step 1: Upload your data

[1721] Users upload the data they want to analyze to the system, provided in formats such as CSV or Excel files.

[1722] Specific behavior:

[1723] The user selects the "sales_data.csv" file from their PC and clicks the upload button.

[1724] The server receives the uploaded file and stores it in storage.

[1725] input:

[1726] "sales_data.csv" file

[1727] output:

[1728] Data files saved in storage

[1729] Step 2: Data Preprocessing

[1730] After receiving the uploaded data, the server performs data cleansing, i.e., filling in missing or outlier values ​​and standardizing the data format.

[1731] Specific behavior:

[1732] The server reads the uploaded "sales_data.csv" and identifies rows that contain missing values.

[1733] The server imputes missing values ​​with the mean value or based on specified rules.

[1734] The server detects outliers (e.g., negative sales figures) and corrects them.

[1735] The server standardizes data such as date formats.

[1736] input:

[1737] "sales_data.csv" file saved in storage

[1738] output:

[1739] Preprocessed dataset

[1740] Step 3: Feature extraction

[1741] The server extracts features from the cleansed data, performing trend analysis on time-series data and frequency analysis on categorical data.

[1742] Specific behavior:

[1743] The server extracts monthly sales data and performs time series analysis.

[1744] The server calculates the sales frequency by category (e.g., by product category).

[1745] The server adds these analysis results to the data frame as new features.

[1746] input:

[1747] Preprocessed dataset

[1748] output:

[1749] Dataset with added features

[1750] Step 4: Selecting the Generator AI

[1751] Users select the AI ​​that best suits their business field from the multiple generative AI models provided by the system.

[1752] Specific behavior:

[1753] The user selects a generative AI model for the retail industry on the system's generative AI selection screen.

[1754] The user checks the model description and clicks the selection button.

[1755] The server loads the selected generative AI model.

[1756] input:

[1757] User-generated AI model selection information

[1758] output:

[1759] Loaded generative AI model

[1760] Step 5: Hypothesis generation

[1761] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[1762] Specific behavior:

[1763] The server inputs the feature extraction results into the generation AI as prompts.

[1764] The server stores the generated hypotheses in a database.

[1765] input:

[1766] Dataset with added features

[1767] Loaded generative AI model

[1768] output:

[1769] Generated hypotheses

[1770] Step 6: State your hypotheses

[1771] The device presents the generated hypotheses and related data to the user, while also visualizing the data based on the hypotheses.

[1772] Specific behavior:

[1773] The server transmits the hypotheses and associated data to the terminal.

[1774] The terminal generates a report screen containing the hypotheses and displays related graphs and maps.

[1775] The user can view the hypothesis and the supporting data on their device.

[1776] input:

[1777] Generated hypotheses

[1778] Related data

[1779] output:

[1780] Hypotheses presented to the user and related data

[1781] Step 7: Decision support

[1782] The user develops a business strategy and action plan based on the presented hypotheses, evaluates whether the hypotheses are useful, and adjusts the hypotheses as necessary.

[1783] Specific behavior:

[1784] The user creates a proposal for a promotion campaign based on the presented hypothesis.

[1785] To assess the reliability of the hypothesis, the user compares it with past performance data.

[1786] Users can improve the accuracy of hypotheses by running campaigns and feeding back the results to the system.

[1787] input:

[1788] Hypotheses presented to the user and related data

[1789] output:

[1790] Action plan and its evaluation results

[1791] (Application example 1)

[1792] 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."

[1793] In recent years, it has become increasingly difficult for users of content distribution services to efficiently find content that suits them from the wide variety of content available. This has led to problems such as lower user satisfaction and a decrease in frequency of service use. Furthermore, existing recommendation systems rely on limited data and specific algorithms, limiting the accuracy of their analysis and recommendations. In response to this situation, there is a demand for a system that can efficiently analyze large amounts of data and make highly accurate content recommendations based on users' viewing habits.

[1794] 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.

[1795] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, and a means for analyzing viewing habits from user data and recommending content based on the viewing history. This enables highly accurate content recommendations based on the user's viewing history, thereby increasing user satisfaction. Furthermore, by using an industry-specific generative AI, optimal content recommendations can be made according to the needs of a specific industry.

[1796] The "data analysis means" is a means for analyzing data provided by a user and extracting useful information from the data.

[1797] A "means for selecting generative AI" is a means for selecting the AI ​​model that is best suited to a user's specific purpose or industry from among multiple generative AI models.

[1798] A "means for generating hypotheses useful for a business" is a means for generating hypotheses useful for a specific business using analyzed data and a selected generative AI model.

[1799] The "means for presenting the generated hypotheses" is a means for presenting the generated hypotheses to the user in an easy-to-understand manner.

[1800] "Means for analyzing viewing trends from user data and recommending content based on viewing history" refers to means for analyzing a user's viewing history and evaluation data and recommending the most suitable content to the user based on the results.

[1801] An embodiment of the present invention is based on a system configured as follows: This system has the function of allowing a user to provide viewing history and rating data, analyzing the data, generating hypotheses, and recommending optimal content to the user.

[1802] Uploading data

[1803] Users upload their viewing history and rating data to the system in CSV files. For example, a user might upload a file called "user_watch_data.csv." At this time, the device sends the user's data to the server.

[1804] Data Preprocessing

[1805] The server receives the uploaded data and performs data cleansing, imputing missing values ​​and outliers, and arranging the data format. Specifically, it uses the Pandas and NumPy libraries to impute missing values ​​and remove outliers.

[1806] Feature extraction

[1807] Next, the server extracts viewing and rating trends from the viewing data, including the number of views and average ratings. Based on this, the server generates data features and uses them for analysis.

[1808] Selecting a generative AI model

[1809] Users can select the generative AI model that best suits their needs and industry from among the multiple generative AI models provided. For example, they can select a specialized generative AI model for recommending entertainment content.

[1810] Hypothesis generation

[1811] Using the selected generative AI model, the server generates recommended content based on viewing habits from user data. This hypothesis generation process uses a generative AI model specialized for the entertainment industry.

[1812] Presenting a hypothesis

[1813] The generated recommended content is presented to the user via the device, and the user can check their viewing history and a list of recommended content in an intuitive manner.

[1814] Examples and prompts

[1815] For example, by providing the following prompt to a generative AI model, it can generate optimal recommendations for the user:

[1816] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[1817] To realize this system, Python programs, data analysis libraries such as Pandas and NumPy, and generative AI models specialized for specific applications are used.Technically, the system is configured to seamlessly upload data, preprocess it, extract features, analyze it using the generative AI model, and present the results.

[1818] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1819] Step 1:

[1820] Users upload their viewing history and rating data in CSV file format to their device. The device then sends this file to the server. The input is a data file such as "user_watch_data.csv," and the output is the raw data received by the server.

[1821] Step 2:

[1822] The server performs a data cleansing process on the received data. For example, it uses Pandas to fill in missing values ​​and remove outliers. The input is raw data, and the output is cleansed, formatted data. Specifically, the process involves using data.fillna(data.mean(), inplace=True).

[1823] Step 3:

[1824] The server extracts features from the cleansed data. For example, it aggregates the number of views and average ratings to generate a new dataset. The input is the cleansed formatted data, and the output is the extracted feature data. Specifically, the following process is performed: features = data.groupby('content_id').agg({'views': 'sum', 'ratings': 'mean'}).reset_index().

[1825] Step 4:

[1826] The user selects an appropriate generative AI model from among several provided models. The selected generative AI model is selected to be specialized in a specific field. The input is the user's selection, and the output is the selected generative AI model itself.

[1827] Step 5:

[1828] The server uses the selected generative AI model to generate a hypothesis based on the extracted feature data. This hypothesis is what is presented as recommended content to the user. The input is the feature data and the selected generative AI model, and the output is the generated recommendation hypothesis. Specifically, the server inputs a prompt to the generative AI model and obtains the result.

[1829] Step 6:

[1830] The device presents the generated hypotheses, i.e., recommended content, to the user. The user selects, watches, and rates content based on these hypotheses. The input is the generated recommendation hypotheses, and the output is a content list presented to the user.

[1831] Examples and prompts

[1832] For example, in the following example, a prompt sentence based on the viewing history of user ID: 12345 is input to the generative AI model:

[1833] "Based on the viewing history of user ID: 12345, please recommend content that this user would enjoy watching next."

[1834] Based on this prompt, the generative AI model analyzes it, generates recommended content tailored to the user, and presents it to the user via their device.

[1835] 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.

[1836] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from that data. This system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the user's emotions. Users provide data, and the system analyzes it and presents useful hypotheses, supporting fast and accurate decision-making.

[1837] Program processing

[1838] Uploading data

[1839] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[1840] Examples:

[1841] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[1842] Data Preprocessing

[1843] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[1844] Examples:

[1845] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[1846] Feature extraction

[1847] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[1848] Examples:

[1849] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[1850] Selecting the Generator AI

[1851] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1852] Examples:

[1853] Users select a generative AI specialized for the retail industry.

[1854] Hypothesis generation

[1855] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[1856] Examples:

[1857] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[1858] Acquiring and analyzing emotion data

[1859] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1860] Examples:

[1861] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[1862] Emotional Hypothesis Adjustment

[1863] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[1864] Examples:

[1865] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[1866] Presenting a hypothesis

[1867] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[1868] Examples:

[1869] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[1870] decision support

[1871] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[1872] Examples:

[1873] Based on the above-mentioned hypothesis, the user plans a promotion campaign for a specific region and prepares for its execution.

[1874] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[1875] The processing flow will be explained below.

[1876] Program processing steps

[1877] The process flow in the system of the present invention will be specifically explained below step by step.

[1878] Step 1: Upload Data (User)

[1879] Users log in to the system, select the data file to be analyzed, and upload it. At this time, the data format is typically CSV or Excel.

[1880] Specific behavior:

[1881] Users access the system through a browser.

[1882] Use the data file specification dialog box to select a local file.

[1883] Click the "Upload" button to send the data to the server.

[1884] Step 2: Data preprocessing (server)

[1885] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to prepare it for analysis.

[1886] Specific behavior:

[1887] The server detects missing values ​​in the data and performs the appropriate imputation process.

[1888] Anomalous data points are detected and corrected or removed accordingly.

[1889] Consistency of data types (e.g. converting strings to numbers).

[1890] Step 3: Feature extraction (server)

[1891] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[1892] Specific behavior:

[1893] The server performs trend analysis on the time series data to identify seasonal patterns and periodicities.

[1894] Analyze the frequency distribution of categorical data and extract important features.

[1895] Statistical analysis is performed on numerical data to calculate distributions and basic statistics.

[1896] Step 4: User selection of the generating AI

[1897] Users can select the generative AI that best suits their business field from among the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[1898] Specific behavior:

[1899] Users select an industry from a drop-down menu within the system.

[1900] Users select the most appropriate generative AI model from options such as "retail" or "manufacturing."

[1901] Step 5: Hypothesis generation (server)

[1902] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data. The generation AI uses a model learned from large amounts of data to make appropriate business proposals.

[1903] Specific behavior:

[1904] The server provides the features as input data to the generative AI model.

[1905] Generative AI analyzes input data and generates hypotheses.

[1906] Hypotheses are formalized into concrete action items.

[1907] Step 6: Acquiring and analyzing emotion data (server)

[1908] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[1909] Specific behavior:

[1910] The server receives text comments and voice data entered by the user.

[1911] The emotion engine analyzes the received data and recognizes the user's emotional state (happiness, sadness, anger, etc.).

[1912] The recognized emotional state is stored as emotion data.

[1913] Step 7: Emotion-based hypothesis adjustment (server)

[1914] The server adjusts the hypotheses based on the acquired emotional data, and by making specific suggestions that take the user's emotional state into account, the accuracy and usefulness of the hypotheses are improved.

[1915] Specific behavior:

[1916] The server integrates the generated hypotheses with emotional data and makes adjustments according to the user's interests and expectations.

[1917] Regenerate the adjusted hypotheses as a new business proposition.

[1918] Step 8: Present the hypothesis (terminal)

[1919] The device presents the generated hypotheses and related data to the user, and simultaneously visualizes the data based on the hypotheses, providing information in a format that is easy for the user to understand.

[1920] Specific behavior:

[1921] The terminal displays the hypotheses and data received from the server on a user interface.

[1922] Visualize data using graphs and charts.

[1923] Displays a summary of the hypothesis in text format.

[1924] Step 9: Decision Support (User)

[1925] Users develop business strategies based on the presented hypotheses, formulate specific action plans, and evaluate the usefulness of the hypotheses to determine appropriate actions.

[1926] Specific behavior:

[1927] The user checks the details of the hypothesis on the interface.

[1928] Share your hypotheses with team members and gather feedback.

[1929] Formulate a specific business strategy based on the hypothesis and prepare for its implementation.

[1930] Through these steps, the system of the present invention efficiently analyzes the data provided by the user and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[1931] Example 2

[1932] 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."

[1933] Conventional data analysis systems do not generate or adjust hypotheses taking user emotions into account, making it difficult to provide business proposals that truly interest users. Furthermore, the accuracy of generated hypotheses can be reduced by not being able to select industry-specific AI. This makes it difficult to support fast and accurate decision-making.

[1934] 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.

[1935] In this invention, the server includes a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for a business, a means for activating an emotion engine that recognizes the user's emotions, and a means for adjusting the hypotheses based on the user's emotion data, thereby enabling highly accurate hypothesis generation that takes the user's emotions into consideration.

[1936] "Data analysis means" refers to means for analyzing the provided data, extracting information, preprocessing, and analyzing features.

[1937] The "means for selecting a generative AI" is a means for a user to select an AI specialized for a specific industry.

[1938] The "means for generating hypotheses" is a means for generating hypotheses useful for a business using analyzed data and selected artificial intelligence.

[1939] The "means for presenting hypotheses" is a means for visually displaying the generated hypotheses and providing them to the user in a format that is easy to understand.

[1940] The "emotion engine" is an engine that analyzes emotions from the user's facial expressions, voice, and text, and generates emotional data.

[1941] The "means for adjusting hypotheses based on user emotional data" refers to a means for adjusting existing hypotheses based on user emotional data and placing emphasis on items that interest or are considered important by the user.

[1942] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a means for selecting a generative artificial intelligence, a means for generating hypotheses useful for business, a means for presenting the generated hypotheses, and an emotion engine that recognizes the emotions of the user. Specific embodiments of the present invention are described in detail below.

[1943] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data format is typically a CSV or Excel file. Specifically, the user opens a web browser, accesses the system's login page, enters their login information, and logs in to the system. After logging in, they click the upload button, select the data file (for example, "sales_data.csv"), and upload it.

[1944] The server then receives the received data and performs an initial data cleansing process. The server loads the data into memory and uses a missing value imputation algorithm to fill in any missing values ​​in the data. The server also uses an outlier detection algorithm to correct any outliers, and standardizes the data format to make it suitable for analysis.

[1945] Next, the server extracts features from the preprocessed data. The server runs data analysis algorithms (e.g., principal component analysis (PCA) or clustering) to extract key features from the data. The server detects trends and patterns in the sales data and classifies it by time axis and product. The extracted features are used as the basis for hypothesis generation in the next step.

[1946] The user then selects the generative AI that is best suited to their business field from the multiple generative AI models provided by the system. The user checks the list of generative AI models displayed on the dashboard and selects the generative AI model that is best suited to their business field. For example, the user can select a generative AI specialized for the retail industry. The user clicks the selection button to notify the system of their selection.

[1947] After selecting a generative AI model, the server uses the selected generative AI to generate hypotheses based on the features extracted from the data. The server initializes the selected generative AI model and prepares it for analysis. The server inputs the feature data into the generative AI and executes the hypothesis generation process. The generated hypotheses are provided as specific business proposals, and the server stores the generated hypotheses in a database and organizes them into a format that can be presented to users.

[1948] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences. The server collects the user's input media (e.g., text comments and speech data) and runs an emotion analysis algorithm to analyze the user's emotional state. The server generates emotion data such as "happiness," "dissatisfaction," and "surprise," which are used in the hypothesis adjustment process.

[1949] Next, the server adjusts the generated hypotheses based on the emotional data. The server analyzes the user's emotional data to identify the user's interests and important items. The server prioritizes the generated hypotheses and makes important suggestions based on the user's emotions. The adjusted hypotheses are saved in the database again and presented to the user via the device.

[1950] Finally, the device presents the generated hypotheses and related data to the user. The device displays the hypotheses and related data (e.g., graphs and maps) using visualization tools. The user then develops a business strategy based on the presented hypotheses. By formulating a specific action plan and evaluating the usefulness of the hypotheses, the user determines the appropriate action. For example, the user may plan a promotional campaign in a specific region based on the previously presented hypotheses and prepare for its implementation.

[1951] As described above, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using generative AI and an emotion engine, thereby supporting fast and accurate decision-making.

[1952] Example prompt sentence:

[1953] "Analyze seasonal sales trends from the given sales data and propose a hypothesis for the marketing strategy for the next season."

[1954] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1955] Step 1:

[1956] The user logs into the system and uploads the data file to be analyzed.

[1957] input:

[1958] The user provides login information (username, password) and the data file to be analyzed (e.g., "sales_data.csv").

[1959] Specific behavior:

[1960] The user opens a web browser and accesses the system's login page.

[1961] The user enters the login information and logs into the system.

[1962] The user clicks the upload button, selects the data file and uploads it.

[1963] output:

[1964] Data files uploaded to the server.

[1965] Step 2:

[1966] The server pre-processes the received data files.

[1967] input:

[1968] The uploaded data file (for example, "sales_data.csv").

[1969] Specific behavior:

[1970] The server reads the data file into memory.

[1971] The server uses a missing value imputation algorithm to impute missing values.

[1972] The server uses an outlier detection algorithm to correct the outliers.

[1973] The server will standardize the data format and prepare it in a state suitable for analysis.

[1974] output:

[1975] Clean data after preprocessing.

[1976] Step 3:

[1977] The server extracts features from the pre-processed data.

[1978] input:

[1979] Clean data after preprocessing.

[1980] Specific behavior:

[1981] The server runs data analysis algorithms (e.g., principal component analysis and clustering).

[1982] The server extracts the key features of the data.

[1983] The server detects trends and patterns in the sales data and categorizes it by timeline and product.

[1984] output:

[1985] Extracted feature data.

[1986] Step 4:

[1987] The user selects the most appropriate model from the generative AI models provided by the system.

[1988] input:

[1989] A list of generative AI models.

[1990] Specific behavior:

[1991] The user sees a list of generative AI models displayed on the dashboard.

[1992] Users select the generative AI model that best suits their business field.

[1993] The user clicks on the selection button to notify the system of the selection.

[1994] output:

[1995] Information about the selected generative AI model.

[1996] Step 5:

[1997] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data.

[1998] input:

[1999] Extracted feature data and information on the selected generative AI model.

[2000] Specific behavior:

[2001] The server initializes the selected generative AI model and prepares it for analysis.

[2002] The server inputs the feature data into the generation AI and executes the hypothesis generation process.

[2003] The server stores the generated hypotheses in a database.

[2004] output:

[2005] Data for generated hypotheses.

[2006] Step 6:

[2007] The server activates an emotion engine to recognize the user's emotions.

[2008] input:

[2009] User input media (text comments, speech data).

[2010] Specific behavior:

[2011] The server collects the user's input media.

[2012] The server runs an emotion analysis algorithm to analyze the emotional state.

[2013] The server generates emotion data such as "happiness," "dissatisfaction," and "surprise."

[2014] output:

[2015] User emotion data.

[2016] Step 7:

[2017] The server adjusts the generated hypotheses based on the user's emotional data.

[2018] input:

[2019] Generated hypothesis data, user emotion data.

[2020] Specific behavior:

[2021] The server analyzes the user's emotional data and identifies the user's interests and important points.

[2022] The server prioritizes and makes key suggestions based on the generated hypotheses based on the user's emotions.

[2023] The server stores the adjusted hypotheses back in the database.

[2024] output:

[2025] Adjusted hypothesis data.

[2026] Step 8:

[2027] The terminal presents the generated hypotheses and associated data to the user.

[2028] input:

[2029] Adjusted hypothesis data.

[2030] Specific behavior:

[2031] The terminal displays the hypotheses and related data (graphs, maps) using visualization tools.

[2032] The terminal provides an interactive user interface that allows users to explore hypotheses in detail.

[2033] output:

[2034] Hypotheses presented to the user and associated data visualized.

[2035] Step 9:

[2036] The user develops a business strategy based on the presented hypotheses.

[2037] input:

[2038] Presented hypotheses and visualized relevant data.

[2039] Specific behavior:

[2040] The user reviews the presented hypotheses and related data.

[2041] Users evaluate the usefulness of the hypotheses and plan to incorporate them into their business strategy.

[2042] The user decides on a specific action plan (e.g., implementing a promotional campaign) and prepares for its implementation.

[2043] output:

[2044] A proposed business strategy and a concrete action plan.

[2045] (Application example 2)

[2046] 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."

[2047] Conventional data analysis systems are limited to analyzing massive amounts of data to generate hypotheses, and the generated hypotheses do not adequately reflect user sentiment or the specific needs of the business, making it difficult to improve the accuracy of decision-making support.In addition, they lack the ability to utilize generative AI models specialized for specific industries, and tend to provide hypotheses with low accuracy.

[2048] 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 a data analysis means, a means for selecting a generative AI, a means for generating hypotheses useful for the business, a means for presenting the generated hypotheses, an emotion recognition means for acquiring and analyzing emotion data, and a means for adjusting the hypotheses based on the emotion data. This makes it possible to analyze user-provided data, select a generative AI model specialized for a specific industry, and generate highly accurate hypotheses that reflect the emotion data.

[2049] "Data analysis means" refers to a device or software that has the function of analyzing data provided by a user and extracting useful information or patterns.

[2050] A "means for selecting generative artificial intelligence" is a device or software that has the function of selecting an artificial intelligence model suitable for a particular industry or application.

[2051] A "means for generating hypotheses useful for a business" is a device or software that has the function of generating hypotheses useful for business decision-making based on analyzed data.

[2052] The "means for presenting the generated hypotheses" refers to a device or software that has the function of presenting the generated hypotheses to the user visually or as text.

[2053] "Emotion recognition means" refers to a device or software that has the function of analyzing emotions from a user's facial expressions, voice, writing, etc., and generating emotion data.

[2054] The "means for adjusting hypotheses based on emotional data" refers to a device or software that has the function of adjusting or correcting hypotheses generated by taking into account emotional data.

[2055] The present invention relates to a system that analyzes large amounts of data provided by users and generates hypotheses useful for business from the data. The system includes a data analysis means, a generation artificial intelligence selection means, a generation hypothesis generation means, a presentation means for generating hypotheses useful for business, an emotion recognition means, and a means for adjusting the hypotheses based on the emotion data.

[2056] Hardware and software used

[2057] Hardware: Regular PC or smartphone

[2058] Software: Python, pandas, scikit-learn, sentiment analysis library (e.g., sentiment_analysis)

[2059] System action

[2060] Uploading data

[2061] Users log in to the system, select the data file to be analyzed, and upload it. Data is typically in CSV or Excel format.

[2062] Examples:

[2063] The user uploads "sales_data.csv" containing sales data for the past year into the system.

[2064] Data Preprocessing

[2065] The server receives the data and performs data cleansing, filling in missing or outlier values ​​and standardizing the data format to make it suitable for analysis.

[2066] Examples:

[2067] The server fills in missing values ​​and corrects outliers, preparing the data in "sales_data.csv" for analysis.

[2068] Feature extraction

[2069] The server then performs feature extraction on the pre-processed data, detecting patterns, trends, and outliers in the data and extracting features that will serve as the basis for generating hypotheses.

[2070] Examples:

[2071] The server performs trend analysis of sales data and extracts monthly sales trends and sales rankings by product.

[2072] Selecting the Generator AI

[2073] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By using AI specialized for a specific industry, more accurate hypotheses can be obtained.

[2074] Examples:

[2075] Users select a generative AI specialized for the retail industry.

[2076] Hypothesis generation

[2077] The server uses the selected generation AI to generate hypotheses based on the features extracted from the data, and presents the hypotheses in the form of specific business proposals.

[2078] Examples:

[2079] The server generates a hypothesis that "sales in a particular region increase sharply in winter, so strengthening marketing in that region would be effective."

[2080] Acquiring and analyzing emotion data

[2081] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[2082] Examples:

[2083] The server analyzes emotions from text comments and speech entered by the user and generates emotional data such as "happiness," "dissatisfaction," and "surprise."

[2084] Emotional Hypothesis Adjustment

[2085] The server uses the sentiment data to refine the generated hypotheses, for example, to prioritize suggestions based on the user's strong interests.

[2086] Examples:

[2087] The server proposes an aggressive promotion strategy for new products for which the user expresses a feeling of "surprise."

[2088] Presenting a hypothesis

[2089] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[2090] Examples:

[2091] In addition to the generated hypotheses, the terminal displays graphs of monthly sales and maps of regional sales to the user.

[2092] Prompt Sentence Examples

[2093] "I am very excited about the new product launch"

[2094] As a result, the system of the present invention efficiently analyzes data provided by users and generates and presents useful hypotheses using a generative AI model and emotion engine, thereby supporting fast and accurate decision-making.

[2095] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2096] Step 1:

[2097] The user logs in to the system, selects the data file to be analyzed, and uploads it. The data to be analyzed is typically in CSV or Excel format. As a specific example, the user uploads "sales_data.csv," which contains sales data from the past year, to the system.

[2098] Input: Login information, data file (sales_data.csv)

[2099] Output: Raw data uploaded to the server

[2100] Step 2:

[2101] The server preprocesses the received data, cleansing it, filling in missing and outlier values, and standardizing the data format, thereby preparing the data for analysis.

[2102] Input: raw data (sales_data.csv)

[2103] Output: Cleansed data

[2104] Step 3:

[2105] The server performs feature extraction on the preprocessed data, detecting patterns, trends, and outliers in the data and extracting features that form the basis for hypothesis generation.

[2106] Input: Cleansed data

[2107] Output: Extracted features (e.g., monthly sales trends, product sales rankings)

[2108] Step 4:

[2109] Users can select the generative AI that best suits their business field from the multiple generative AI models provided by the system. By selecting an AI model specialized for a specific industry, more accurate hypotheses can be obtained.

[2110] Input: Generative AI model selection information (e.g., AI specialized for the retail industry)

[2111] Output: The selected generative AI model

[2112] Step 5:

[2113] The server uses the selected generative AI model to generate hypotheses based on the features extracted from the data, and these hypotheses are provided to users as concrete business proposals.

[2114] Input: extracted features, selected generative AI model

[2115] Output: Generated hypotheses (e.g., sales in a particular region spike during the winter, so increased marketing in that region is beneficial)

[2116] Step 6:

[2117] The server activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's emotional state from their facial expressions, voice, and sentences, and generates emotion data.

[2118] Input: User input comments or utterances (e.g., "I am very excited about the new product launch")

[2119] Output: Emotion data (e.g., happiness, surprise)

[2120] Step 7:

[2121] The server adjusts the generated hypotheses based on the emotion data, providing suggestions that focus on items that the user is most interested in.

[2122] Input: Generated hypotheses, emotion data

[2123] Output: Adjusted hypotheses (e.g., a proposal for an aggressive promotion strategy for a new product for which users expressed "surprise")

[2124] Step 8:

[2125] The device presents the generated hypotheses and related data to the user, displaying the hypotheses alongside visualized data to provide information in a format that is easy for the user to understand.

[2126] Input: Adjusted hypotheses, visualization data (e.g., monthly sales graph, regional sales map)

[2127] Output: Hypotheses and associated data presented to the user

[2128] 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.

[2129] 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.

[2130] 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.

[2131] 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.

[2132] 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.

[2133] 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.

[2134] 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).

[2135] 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.

[2136] 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."

[2137] 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.

[2138] 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).

[2139] 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.

[2140] 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.

[2141] 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.

[2142] 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.

[2143] 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.

[2144] 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.

[2145] 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.

[2146] 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.

[2147] 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.

[2148] 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.

[2149] The following is further disclosed regarding the above embodiment.

[2150] (Claim 1)

[2151] data analysis means;

[2152] A means for selecting a generative artificial intelligence;

[2153] A means of generating hypotheses that will be useful for the business,

[2154] a means for presenting the generated hypotheses;

[2155] A system including:

[2156] (Claim 2)

[2157] 2. The system according to claim 1, wherein the data analysis means includes means for extracting data features.

[2158] (Claim 3)

[2159] The system according to claim 1, wherein the means for selecting the generating artificial intelligence includes means for selecting an artificial intelligence specialized in a particular industry desired by the user.

[2160] "Example 1"

[2161] (Claim 1)

[2162] data analysis means;

[2163] A means for selecting a generative artificial intelligence;

[2164] A means of generating hypotheses that will be useful for the business,

[2165] a means for presenting the generated hypotheses;

[2166] A means for uploading data;

[2167] means for performing data preprocessing;

[2168] A means for extracting features;

[2169] Decision support measures;

[2170] A system including:

[2171] (Claim 2)

[2172] 2. The system according to claim 1, wherein the data analysis means includes means for extracting data features.

[2173] (Claim 3)

[2174] The system according to claim 1, wherein the means for selecting the generating artificial intelligence includes means for selecting an artificial intelligence specialized in a particular industry desired by the user.

[2175] "Application Example 1"

[2176] (Claim 1)

[2177] data analysis means;

[2178] A means for selecting a generative artificial intelligence;

[2179] A means of generating hypotheses that will be useful for the business,

[2180] a means for presenting the generated hypotheses;

[2181] A means for analyzing viewing habits from user data and recommending content based on viewing history;

[2182] A system including:

[2183] (Claim 2)

[2184] 2. The system according to claim 1, wherein the data analysis means includes means for extracting data features.

[2185] (Claim 3)

[2186] The system according to claim 1, wherein the means for selecting the generating artificial intelligence includes means for selecting an artificial intelligence specialized in a particular industry desired by the user.

[2187] "Example 2: Combining Emotion Engines"

[2188] (Claim 1)

[2189] data analysis means;

[2190] A means for selecting a generative artificial intelligence;

[2191] A means of generating hypotheses that will be useful for the business,

[2192] a means for presenting the generated hypotheses;

[2193] means for activating an emotion engine that recognizes the user's emotions;

[2194] A means to adjust hypotheses based on user emotional data;

[2195] A system including:

[2196] (Claim 2)

[2197] 2. The system according to claim 1, wherein the data analysis means includes means for extracting data features.

[2198] (Claim 3)

[2199] The system according to claim 1, wherein the means for selecting the generating artificial intelligence includes means for selecting an artificial intelligence specialized in a particular industry desired by the user.

[2200] (Claim 4)

[2201] 2. The system of claim 1, wherein the emotion engine includes means for analyzing the user's emotional state from facial expressions, voice, and sentences.

[2202] (Claim 5)

[2203] 2. The system of claim 1, wherein the hypothesis adjustment means includes means for prioritizing the generated hypotheses based on user interests.

[2204] "Application example 2 when combining emotion engines"

[2205] (Claim 1)

[2206] data analysis means;

[2207] A means for selecting a generative artificial intelligence;

[2208] A means of generating hypotheses that will be useful for the business,

[2209] a means for presenting the generated hypotheses;

[2210] emotion recognition means for acquiring and analyzing emotion data;

[2211] a means of adjusting hypotheses based on emotion data;

[2212] A system including:

[2213] (Claim 2)

[2214] 2. The system according to claim 1, wherein the data analysis means includes means for extracting data features.

[2215] (Claim 3)

[2216] The system according to claim 1, wherein the means for selecting the generating artificial intelligence includes means for selecting an artificial intelligence specialized in a particular industry desired by the user. [Explanation of symbols]

[2217] 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. data analysis means; A means for selecting a generative artificial intelligence; A means of generating hypotheses that will be useful for the business, a means for presenting the generated hypotheses; A system including:

2. 2. The system according to claim 1, wherein the data analysis means includes means for extracting data features.

3. The system according to claim 1 , wherein the means for selecting the generating artificial intelligence includes means for selecting an artificial intelligence specialized in a particular industry desired by the user.

Images