system

Abstract

We provide the system. [Solution] A means of acquiring a large dataset including location data from multiple external data sources, A means of performing format standardization and data cleaning on acquired data, A means for automatically inferring potential causal relationships from the dataset using generative artificial intelligence, A means for generating an analysis report based on inferred causal relationships, A means of delivering and displaying the generated analysis report on a terminal, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a system using modern servers, a huge amount of data is generated, but there is a problem that it is difficult to find effective causal relationships from that data. This problem has become a major obstacle in decision-making and business strategy formulation in many enterprises. In particular, in small and medium-sized enterprises, due to constraints on human resources and resources and the difficulty of obtaining effective insights from data, there is a need for a technology that can efficiently and effectively analyze data and link it to specific business actions.

Means for Solving the Problems

[0005] This invention provides a system that automatically analyzes large datasets containing location data acquired from multiple external data sources using generative artificial intelligence. The system performs formatting standardization and data cleaning on the acquired data, and then uses generative artificial intelligence to infer potential causal relationships within the dataset. This clarifies causal relationships that were difficult to discern from correlation alone, and the generated analysis report is delivered and displayed on the user's terminal, thereby supporting the formulation of concrete business strategies and action plans. Furthermore, by including data cleaning processes such as the removal of duplicate data and the imputation of missing values, the system can improve data integrity and quality.

[0006] "External data sources" refer to external information sources that provide the system with various forms of data, including location data.

[0007] "Location data" refers to data that indicates geographical location and is used to identify the location and movement history of a moving object.

[0008] A "large-scale dataset" refers to a massive collection of data obtained from multiple sources, forming the foundation necessary for advanced analysis.

[0009] "Generative artificial intelligence" is a type of artificial intelligence technology that has the ability to automatically generate new insights by finding regularities and patterns from vast amounts of data through learning.

[0010] "Causality" is a concept that describes the relationship in which one event causes another event, and it is an important element in inferring mutual influences.

[0011] An "analysis report" is a document that summarizes the insights gained from data analysis, and it includes visual graphs and specific action plans.

[0012] "Data cleaning" refers to a series of processes that prepare a dataset before data analysis, removing duplicate data and errors.

[0013] A "terminal" refers to an electronic device used by a user to view or manipulate reports. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of a data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] In an embodiment for carrying out the present invention, a data analysis system is built on a server. This system is specialized for analyzing large datasets and acquires location data and other information in real time from external data sources. The server first performs data cleaning on the acquired data, automatically removing duplicate data and imputing missing values. For example, if location information logs for moving objects are duplicated, the server detects the duplicate data and integrates it into a single entry.

[0036] The cleaned data is analyzed by the server using generative artificial intelligence. This AI has the ability to infer latent causal relationships from large amounts of data and generates an analysis report based on the extracted causal relationships. For example, the server can analyze retail store promotion data and find a causal relationship such as "an increase in the number of visitors during the promotion period has a positive impact on sales."

[0037] The generated analysis report is provided to the user via a terminal. The terminal has a report display interface, allowing the user to intuitively understand the data analysis results. Users can review the report on the terminal and adjust their sales strategies and marketing plans based on it. For example, based on the displayed report, a user can formulate a promotional strategy that would be more effective when implemented during a specific season.

[0038] Thus, the present invention provides a system that comprehensively handles everything from data collection and analysis to report generation and presentation, supporting the decision-making process of companies.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server retrieves datasets containing location data in real time from external data sources. This includes periodically polling the data via an API and saving new data to storage on the server.

[0042] Step 2:

[0043] The server performs data cleaning on the retrieved data, removing duplicate data and imputing missing values. This process uses an algorithm to consolidate duplicate information in case multiple identical data entries exist.

[0044] Step 3:

[0045] The server feeds the cleaned data into generative artificial intelligence to infer causal relationships. This AI automatically extracts potential causal relationships from large datasets and generates a causal network model.

[0046] Step 4:

[0047] The server generates an analytical report with detailed and visualized content based on the inferred causal relationships. This report includes recommended actions, graphs, and charts.

[0048] Step 5:

[0049] The server distributes the generated report to the terminal. The terminal receives this information and prepares to display it in a user-friendly interface.

[0050] Step 6:

[0051] Users view reports through their devices. They review the visualized causal relationships and make business decisions based on the findings. If necessary, they can also send feedback on the report to the server.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] Acquiring large datasets in real time and rapidly and automatically inferring potential causal relationships to generate analysis results is difficult with conventional methods. Such tasks require significant manual effort and expertise, making it inefficient in supporting a company's decision-making process. A solution to this problem is needed.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing format unification and information organization on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generative machine learning model. This enables rapid and automatic inference of causal relationships and generation of analysis results based on a large-scale information set.

[0057] "External information sources" refer to systems and devices that supply data, and are the sources from which information is obtained in real time.

[0058] "Location information" refers to data that indicates a specific point or area, and is usually composed of longitude and latitude.

[0059] A "large-scale information set" refers to a very large dataset that is used for analytical purposes.

[0060] "Information organization" is the process of removing duplicates from collected data and filling in any missing values.

[0061] A "generative machine learning model" is a type of artificial intelligence that has the ability to infer latent patterns and causal relationships based on large amounts of data.

[0062] "Causal relationship" refers to the cause-and-effect relationship that exists between different factors or data.

[0063] "Analysis results" refer to the final output obtained during the data analysis process, and include information that can be used to inform decision-making.

[0064] A "terminal" is a device that a user uses to receive and display information and to operate it through an interface.

[0065] To implement this invention, the data analysis system must be built primarily on a server. This system is specialized for processing large amounts of information, and the server acquires location information in real time from multiple external information sources. This allows the server to quickly collect dynamically changing data.

[0066] The server then performs formatting and information organization on the retrieved data. This step involves removing duplicate data and imputing missing values. Specifically, it uses database queries to consolidate duplicate entries. For example, a database management system using SQL is suitable for this process.

[0067] Next, the server analyzes the cleaned data using a generative machine learning model. This model detects potential causal relationships within the vast amount of data and performs inference. The AI ​​model used is a generative AI model. By utilizing this AI model, companies can make management decisions based on large-scale data.

[0068] The analysis results are compiled by the server and delivered to the user via the terminal. The terminal provides a display interface designed to allow users to easily understand the information. The reports received by the user can be used to review sales strategies and marketing plans.

[0069] As an example of a prompt, one could input a specific question into the generating AI model, such as, "Please analyze the impact of an increase in the number of visitors on sales." This would allow users to gain valuable insights that enable data-driven decision-making.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The server acquires a large collection of information, including location data, in real time from multiple external information sources. Its input is raw data obtained from APIs, and its output is unprocessed data stored in the server's storage. Specifically, the server accesses the API endpoints of the information sources and requests data using specified parameters.

[0073] Step 2:

[0074] The server performs formatting and information organization on the retrieved raw data. Raw data is taken as input, and cleaned data is generated as output. Specifically, the server uses database queries to remove duplicate data and impute missing values. For example, an SQL query is executed to group data by date and location as keys and merge duplicates.

[0075] Step 3:

[0076] The server inputs the cleaned data into a generative machine learning model to infer potential causal relationships. The input is organized data, and the output is the model's inference results showing causal relationships. Specifically, the server starts a generative AI model, generates prompts based on the data, and then inputs them into the AI. For example, the prompt "Analyze the impact of an increase in the number of visitors on sales" might be sent to the AI.

[0077] Step 4:

[0078] The server generates and visualizes analysis results based on the inference results. The input is the inference results from the AI ​​model, and the output is an analysis result that can be displayed on the terminal. Specifically, the server uses visualization libraries such as Matplotlib and Plotly in Python to create graphs and packages the results in HTML format.

[0079] Step 5:

[0080] The terminal receives analysis results sent from the server and displays them to the user. The input is an HTML-formatted analysis report sent from the server, and the output is a visual report accessible to the user via an interface. Specifically, the terminal renders the report using a browser or dedicated application, providing the user with an intuitive interface.

[0081] Step 6:

[0082] Users make decisions based on analytical reports displayed on their devices. The input is a visual report displayed on the device, and the output is the formulation of specific marketing and sales strategies. In terms of actions, users review the report and develop action plans based on the information presented in graphs and charts.

[0083] (Application Example 1)

[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] In today's information society, efficiently analyzing the effectiveness of advertising campaigns and understanding their impact on purchasing behavior is crucial for corporate strategy. However, traditional methods have made it difficult to analyze vast amounts of data in real time and immediately evaluate the effectiveness of advertising. Furthermore, insufficient information cleaning and causal relationship inference have hindered the optimization of advertising strategies.

[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0087] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing formatting standardization and information cleaning on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generating AI. This makes it possible to verify the effectiveness of mobile advertising campaigns in real time and to analyze in detail the impact of ad delivery on purchasing behavior.

[0088] An "external information source" is an information provider that exists outside the system and provides location information and other related data.

[0089] "Location information" refers to data that indicates the geographical location of an object or moving object.

[0090] A "large-scale information set" is an information collection containing a vast amount of data, which is the subject of analysis.

[0091] "Format standardization" refers to organizing and arranging data of different formats and types according to a set of rules.

[0092] "Information cleaning" refers to the process of correcting and deleting unnecessary, redundant, or missing information from a data set.

[0093] "Generative AI" is an artificial intelligence technology that learns patterns from large-scale data and performs inference and prediction.

[0094] "Causal relationship" refers to an analytical result that shows a relationship in which one event influences another event.

[0095] An "analysis report" is a format that summarizes and visually displays the results of data analysis.

[0096] An "information processing device" is a device that inputs, processes, and outputs data, and serves as a terminal for users to check the results.

[0097] A "mobile advertising campaign" refers to an advertising strategy and its implementation activities that are targeted at mobile devices.

[0098] "Purchasing behavior" refers to the series of actions that consumers take in order to purchase a product.

[0099] A "causal relationship model" is a tool for visually representing the causal connections between data points.

[0100] In an embodiment of this invention, the server first acquires location information and other related data in real time from multiple external information sources. This data is often provided in different formats such as JSON or CSV. The server receives this data in bulk and unifies the format. For example, it aggregates location information in real time using the PositionStack API or Google® Maps API.

[0101] After the data is collected, the server uses Python to perform data cleaning via the Pandas library. At this stage, duplicate data is removed and missing values ​​are imputed. This ensures the accuracy and consistency of the data.

[0102] Next, a generative AI model is used to infer potential causal relationships from the cleaned data. This AI model is built on TENSORFLOW® or Keras and has the ability to analyze hidden patterns in the data. Based on the causal relationships obtained, the server verifies the effectiveness of mobile advertising campaigns and identifies the specific impact that advertisements have on consumer purchasing behavior.

[0103] The generated analysis report is delivered to an information processing device and displayed on the terminal. This device has a visual user interface built with React Native, allowing users to intuitively understand the information. Based on this report, users can optimize their advertising strategy.

[0104] As a specific example, a report generated by a company's advertising campaign for soda beverages conducted in a particular region during the summer revealed that increasing advertising exposure during the evening hours resulted in a 20% increase in sales.

[0105] The generative AI model can be input with prompts such as: "Based on the given location data set, infer when and where a particular advertising campaign was most effective, and clearly indicate the causal relationship." This prompt allows the AI ​​model to extract meaningful results from the data and provide foundational information for use in business strategies.

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server acquires location information and user behavior data in real time from external sources. Input is raw data in JSON or CSV format, collected via external APIs. Output is data converted from different formats into a unified format. The server performs this data conversion to ensure smooth subsequent processing.

[0109] Step 2:

[0110] The server performs data cleaning using the Python Pandas library. The input for this step is data in a consistent format, and it is checked for incomplete or redundant records. The server improves data consistency by removing duplicate data and imputing missing data. The output is a clean dataset, ready for analysis.

[0111] Step 3:

[0112] The generative AI model is run on the server to infer potential causal relationships from cleaned data. The input for this step is a clean dataset that can be analyzed for causal relationships using statistical methods. Through this analysis, the server gains insights into how specific advertisements performed under specific conditions and models the causal relationships. The output is the analysis results regarding causal relationships.

[0113] Step 4:

[0114] The server generates an analysis report based on the analysis results and delivers it to the terminal. The input at this stage is the results of the causal relationship analysis, which includes specific information on the impact of the advertisements. The server converts this into a visual report so that the user can intuitively understand the results. The output is a visualized analysis report for the user. The user can use this to re-evaluate and optimize their advertising strategy.

[0115] Step 5:

[0116] Users review reports on their devices and adjust their advertising campaign strategies based on them. The input is an analytical report delivered from the server, which includes detailed causal relationships. Users can use this information to consider effective advertising strategies and, if necessary, re-enter prompts into the AI ​​model to gain new insights.

[0117] In this way, a consistent process is carried out from data collection to report generation, enabling users to obtain a foundation for effective decision-making.

[0118] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0119] Embodiments of the present invention include the construction of a data analysis system that recognizes user emotions and reflects them in the presentation of analysis results. This system is installed on a server and aims to improve the user experience by analyzing user emotions through the integration of an emotion engine.

[0120] The server acquires large datasets from external data sources and collects various information, including location data. The acquired data is formatted and cleaned by the server, with duplicate data removed and missing values ​​imputed. Next, generative artificial intelligence performs causal relationship inference on the dataset and generates an analysis report based on the results.

[0121] In this process, the emotion engine plays a crucial role. Based on user interactions and input data, the emotion engine performs sentiment analysis to understand the user's emotional state. This analysis is protected by the server and reflected in the analysis report. For example, if the server, through the emotion engine, recognizes that the user has expectations or anxieties about understanding a problem, it can customize the report content to reflect those sentiments.

[0122] On the device, the display of reports is dynamically adjusted to match the user's emotional state. This allows users to receive information in a format that aligns with their emotions, making it easier for them to make decisions. For example, as a user views a report, the device can change the emphasis of graphs and the way recommended actions are presented based on the user's emotions.

[0123] This invention combines emotion recognition technology with data analysis to create a system that provides personalized insights to each individual user, going beyond simply providing numbers and graphs.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The server obtains location data and other related data from external data sources. This data is collected in real time via API communication and stored in the server's database.

[0127] Step 2:

[0128] The server performs data cleaning on the collected data. This step involves detecting and removing duplicate data, identifying and imputing missing values, and performing maintenance work to improve the accuracy of the data.

[0129] Step 3:

[0130] The server inputs the cleaned data into generative artificial intelligence, which automatically infers potential causal relationships. The AI ​​model analyzes data patterns and builds a causal network.

[0131] Step 4:

[0132] The server uses an emotion engine to analyze the user's emotional state based on their past behavior patterns and current interactions. This utilizes user feedback and behavior logs.

[0133] Step 5:

[0134] The server generates individually customized analysis reports based on inferred causal relationships and sentiment analysis results. These reports include recommendations and cautionary notes that take the user's emotions into consideration.

[0135] Step 6:

[0136] The server delivers the generated report to the user's terminal. The terminal generates an interface to display the received report according to the user's emotional state.

[0137] Step 7:

[0138] Users review reports displayed on their devices and consider the suggested actions. They can also provide feedback from their devices as needed, requesting further improvements.

[0139] (Example 2)

[0140] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0141] Traditional data analysis systems analyze data without considering the user's emotional state and generate static reports, resulting in insufficient support for users to effectively understand information and make appropriate decisions. Furthermore, there is a need for mechanisms to efficiently standardize and clean data.

[0142] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0143] In this invention, the server includes means for acquiring large-scale data including geographic location information from multiple information sources, means for standardizing and purifying the acquired data, means for automatically estimating potential relationships from the data using artificial intelligence technology, means for distributing reports to a display device, and means for dynamically adjusting the display of the generated report based on the user's emotional state. This makes it possible to provide personalized reports that take into account the user's emotions.

[0144] A "data source" is a system or platform that supplies data from an external source.

[0145] "Geographic location information" refers to information used to identify a place or location within data.

[0146] A "large-scale dataset" is a dataset containing a vast amount of information.

[0147] "Standardization" is the process of unifying data formats into a consistent form.

[0148] "Purification" is the process of removing noise and unwanted elements from data.

[0149] "Artificial intelligence technology" refers to technologies that use machine learning and natural language processing to analyze data and gain insights.

[0150] "Relevance" refers to the correlation or causal relationship between different data points.

[0151] A "report" is a document that summarizes the results of an analysis and is a collection of information provided to the user.

[0152] A "display device" is hardware used to visually present data and information to a user.

[0153] "Dynamic adjustment" refers to the process of changing the content and format in real time according to the situation and conditions.

[0154] This invention is a data analysis system that utilizes a server and terminals. The server acquires large-scale data, including geographical location information, from multiple information sources. This includes data acquisition via APIs from cloud services and online databases. For example, it is possible to acquire user location information and behavioral data from social media platforms.

[0155] Next, the server standardizes the acquired data to unify the data format. During this process, data cleaning is also performed to remove noise and duplicate information. For example, the Python Pandas library can be used to efficiently process the data.

[0156] Subsequently, the server uses artificial intelligence technology, specifically generative AI models, to automatically estimate potential relationships within the data. This process utilizes machine learning algorithms to infer causal relationships within the data. Specifically, libraries such as Scikit-learn and TensorFlow are employed.

[0157] The generated analysis results are documented as a report. This report is dynamically displayed on the device based on the user's emotional state. This ensures that the report is delivered in a personalized way for each user, aiding their understanding. For example, if a user shows anxiety while viewing the report, the device will adjust to highlight information that alleviates that anxiety.

[0158] An example of a prompt might be, "Please provide recommended actions to alleviate the user's concerns about the new product." By inputting this prompt into the AI ​​model, it can generate specific action suggestions based on the user's emotions.

[0159] Users view this report through their device and make decisions based on the information provided. This allows them to receive support that takes their emotions into consideration, leading to a deeper understanding of the information and making more informed decisions. For example, when a user requests a review of a new product, the emotion engine can highlight positive feedback, potentially increasing the user's willingness to purchase.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server acquires large-scale data, including geographical location information, from various data sources. This process involves collecting real-time data using APIs. The input is raw data obtained from the data sources, and the output is an integrated, large-scale dataset. Specifically, the server executes scheduled tasks and periodically accesses data sources to download essential data.

[0163] Step 2:

[0164] The server performs standardization and data purification on the acquired data. The input is a large, integrated dataset, and the output is a standardized, clean dataset free from noise and duplicates. This process includes specific actions such as unifying the data format, removing duplicates, and imputing missing values ​​using the Python Pandas library.

[0165] Step 3:

[0166] The server uses artificial intelligence techniques to estimate potential relationships in standardized data. The input is a clean dataset, and the output is an analysis result that includes the estimated relationships. In this process, generative AI models are utilized, and machine learning is performed using libraries such as Scikit-learn and TensorFlow. Specifically, prompt sentences are input to the AI ​​model, setting the task to "estimate the causal relationship between user behavior and emotion."

[0167] Step 4:

[0168] The server generates an analysis result as a report based on the estimated correlations. The input is the analysis result, and the output is a documented report. The server uses a template engine to output the report in PDF format, incorporating visualized graphs and charts.

[0169] Step 5:

[0170] The terminal delivers and displays the generated report to the user. The input is a documented report, and the output is a dynamically adjusted report displayed on the user's terminal. Upon receiving the report, the terminal evaluates the user's emotional state and performs specific actions to adjust the report's highlighting and layout based on that evaluation.

[0171] Step 6:

[0172] Users view reports displayed via their devices and make decisions based on the insights provided. The input is a dynamically adjusted report, and the output is the user's decision. Users interact with the device to find the information they need and interpret the data in a way that suits their own emotions.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0175] In today's commercial environment, it is crucial to offer products and services that take consumer emotions and interactions into consideration. However, conventional systems lack the ability to grasp consumers' emotional states in real time and dynamically present information accordingly. As a result, there are limitations to improving customer experience and increasing repeat purchase rates.

[0176] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0177] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for standardizing the format and cleaning the acquired information, and means for automatically inferring potential causal relationships from the information set using generative artificial intelligence. This makes it possible to present dynamically customized product suggestions and promotional information based on the consumer's emotional state.

[0178] "External information sources" refer to a collection of external data providers, databases, and other resources that a system uses to acquire information.

[0179] "Location information" refers to data that indicates a geographical location, and is used to pinpoint the precise geographical location of a user or device.

[0180] A "large-scale information collection" is an information resource that collects a vast amount of data, and it forms the basis for various analyses and processing.

[0181] "Format standardization" is the process of converting information in different formats into a consistent format to maintain the integrity of the information.

[0182] "Information cleansing" is a process of improving data quality by removing inaccurate or unnecessary information from a dataset.

[0183] "Generative artificial intelligence" refers to algorithms or programs that automatically generate new insights and causal relationships based on data.

[0184] "Latent causal relationships" refer to potential cause-and-effect relationships hidden within the data that are revealed through analysis.

[0185] "User emotions" refer to information that indicates the user's feelings and mood, and are used to adapt interfaces and services.

[0186] "Dynamic adjustment of displayed content" is a function that changes the information displayed in real time according to the user's state and environment.

[0187] An "analysis report" is a document or presentation format that summarizes the results of data analysis and is used to support decision-making.

[0188] In this embodiment, the server acquires a large set of information, including location data, from various external sources. This information may also include customer trends and purchase history. The server then performs formatting standardization and data cleansing on the acquired information. In this process, duplicate information is removed and missing values ​​are filled in to maintain data integrity. This improves data quality and yields reliable analysis results.

[0189] Next, the server uses generative artificial intelligence to automatically infer potential causal relationships from the collected information. In this analysis process, the AI ​​can generate new insights based on user interactions and purchase patterns.

[0190] The user's device can recognize their emotions in real time. Specifically, cameras and sensors are used to detect emotions from the user's facial expressions and voice, and this information is sent to a server. Based on this emotional data, the displayed content is dynamically adjusted, providing product recommendations and promotional information optimized for each individual user. This improves the consumer experience and increases convenience.

[0191] As a concrete example, if a customer in a physical store shows excitement in front of a new product, the terminal can offer special discount information related to that product. An example of a prompt message in this case would be, "If you feel excited when you see the new product, please show me discount information related to that product."

[0192] The hardware used includes devices such as smartphones and tablets, and the software utilizes emotion recognition APIs (e.g., Microsoft® Azure® Emotion API) and Python. This makes it possible to create a system that always provides the user with the most optimal information.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The server acquires a large collection of information, including location data, from various external sources. This information includes customer location data, purchase history, and sensor data. The server receives this information and stores it in a temporary database. The input consists of various data from external sources, and the output is raw data with no unified format.

[0196] Step 2:

[0197] The server performs formatting standardization and data cleaning on the acquired information. This process resolves data format inconsistencies, removes unnecessary duplicate data, and fills in missing values. Specifically, this is done using certain scripts or database queries. The input is unstandardized raw data, and the output is cleaned data.

[0198] Step 3:

[0199] The server uses generative artificial intelligence to automatically infer potential causal relationships from a cleaned data set. In this process, the AI ​​algorithm analyzes the correlations and patterns in the data and generates new causal insights. The input is cleaned data, and the output is an analytical report reflecting the causal relationships.

[0200] Step 4:

[0201] The device recognizes the user's emotions in real time via the user's camera and sensors. The recognized emotional data is sent to a server where it is used for analysis. The input is raw emotional data obtained from the user, and the output is the analyzed emotional state.

[0202] Step 5:

[0203] The server dynamically adjusts the displayed content based on the user's emotional state and delivers customized product recommendations and promotional information to the device. An AI model selects and displays appropriate information using prompts. Inputs are emotional state and analysis reports, while output is customized information presentation.

[0204] Step 6:

[0205] Users receive the presented information on their devices and enjoy an optimized shopping experience, which improves consumer satisfaction. The input is customized information received from the device, and the output is the user's experience and behavioral changes. Specific actions include making purchase decisions and changing the user's movement within the store.

[0206] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0207] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0208] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0212] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0213] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0214] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0215] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0216] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0217] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0218] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0219] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0220] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0221] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0222] In an embodiment for carrying out the present invention, a data analysis system is built on a server. This system is specialized for analyzing large datasets and acquires location data and other information in real time from external data sources. The server first performs data cleaning on the acquired data, automatically removing duplicate data and imputing missing values. For example, if location information logs for moving objects are duplicated, the server detects the duplicate data and integrates it into a single entry.

[0223] The cleaned data is analyzed by the server using generative artificial intelligence. This AI has the ability to infer latent causal relationships from large amounts of data and generates an analysis report based on the extracted causal relationships. For example, the server can analyze retail store promotion data and find a causal relationship such as "an increase in the number of visitors during the promotion period has a positive impact on sales."

[0224] The generated analysis report is provided to the user via a terminal. The terminal has a report display interface, allowing the user to intuitively understand the data analysis results. Users can review the report on the terminal and adjust their sales strategies and marketing plans based on it. For example, based on the displayed report, a user can formulate a promotional strategy that would be more effective when implemented during a specific season.

[0225] Thus, the present invention provides a system that comprehensively handles everything from data collection and analysis to report generation and presentation, supporting the decision-making process of companies.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The server retrieves datasets containing location data in real time from external data sources. This includes periodically polling the data via an API and saving new data to storage on the server.

[0229] Step 2:

[0230] The server performs data cleaning on the retrieved data, removing duplicate data and imputing missing values. This process uses an algorithm to consolidate duplicate information in case multiple identical data entries exist.

[0231] Step 3:

[0232] The server feeds the cleaned data into generative artificial intelligence to infer causal relationships. This AI automatically extracts potential causal relationships from large datasets and generates a causal network model.

[0233] Step 4:

[0234] The server generates an analytical report with detailed and visualized content based on the inferred causal relationships. This report includes recommended actions, graphs, and charts.

[0235] Step 5:

[0236] The server distributes the generated report to the terminal. The terminal receives this information and prepares to display it in a user-friendly interface.

[0237] Step 6:

[0238] Users view reports through their devices. They review the visualized causal relationships and make business decisions based on the findings. If necessary, they can also send feedback on the report to the server.

[0239] (Example 1)

[0240] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0241] Acquiring large datasets in real time and rapidly and automatically inferring potential causal relationships to generate analysis results is difficult with conventional methods. Such tasks require significant manual effort and expertise, making it inefficient in supporting a company's decision-making process. A solution to this problem is needed.

[0242] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0243] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing format unification and information organization on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generative machine learning model. This enables rapid and automatic inference of causal relationships and generation of analysis results based on a large-scale information set.

[0244] "External information sources" refer to systems and devices that supply data, and are the sources from which information is obtained in real time.

[0245] "Location information" refers to data that indicates a specific point or area, and is usually composed of longitude and latitude.

[0246] A "large-scale information set" refers to a very large dataset that is used for analytical purposes.

[0247] "Information organization" is the process of removing duplicates from collected data and filling in any missing values.

[0248] A "generative machine learning model" is a type of artificial intelligence that has the ability to infer latent patterns and causal relationships based on large amounts of data.

[0249] "Causal relationship" refers to the cause-and-effect relationship that exists between different factors or data.

[0250] "Analysis results" refer to the final output obtained during the data analysis process, and include information that can be used to inform decision-making.

[0251] A "terminal" is a device that a user uses to receive and display information and to operate it through an interface.

[0252] To implement this invention, the data analysis system must be built primarily on a server. This system is specialized for processing large amounts of information, and the server acquires location information in real time from multiple external information sources. This allows the server to quickly collect dynamically changing data.

[0253] The server then performs formatting and information organization on the retrieved data. This step involves removing duplicate data and imputing missing values. Specifically, it uses database queries to consolidate duplicate entries. For example, a database management system using SQL is suitable for this process.

[0254] Next, the server analyzes the cleaned data using a generative machine learning model. This model detects potential causal relationships within the vast amount of data and performs inference. The AI ​​model used is a generative AI model. By utilizing this AI model, companies can make management decisions based on large-scale data.

[0255] The analysis results are compiled by the server and delivered to the user via the terminal. The terminal provides a display interface designed to allow users to easily understand the information. The reports received by the user can be used to review sales strategies and marketing plans.

[0256] As an example of a prompt, one could input a specific question into the generating AI model, such as, "Please analyze the impact of an increase in the number of visitors on sales." This would allow users to gain valuable insights that enable data-driven decision-making.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server acquires a large collection of information, including location data, in real time from multiple external information sources. Its input is raw data obtained from APIs, and its output is unprocessed data stored in the server's storage. Specifically, the server accesses the API endpoints of the information sources and requests data using specified parameters.

[0260] Step 2:

[0261] The server performs formatting and information organization on the retrieved raw data. Raw data is taken as input, and cleaned data is generated as output. Specifically, the server uses database queries to remove duplicate data and impute missing values. For example, an SQL query is executed to group data by date and location as keys and merge duplicates.

[0262] Step 3:

[0263] The server inputs the cleaned data into a generative machine learning model to infer potential causal relationships. The input is organized data, and the output is the model's inference results showing causal relationships. Specifically, the server starts a generative AI model, generates prompts based on the data, and then inputs them into the AI. For example, the prompt "Analyze the impact of an increase in the number of visitors on sales" might be sent to the AI.

[0264] Step 4:

[0265] The server generates and visualizes analysis results based on the inference results. The input is the inference results from the AI ​​model, and the output is an analysis result that can be displayed on the terminal. Specifically, the server uses visualization libraries such as Matplotlib and Plotly in Python to create graphs and packages the results in HTML format.

[0266] Step 5:

[0267] The terminal receives analysis results sent from the server and displays them to the user. The input is an HTML-formatted analysis report sent from the server, and the output is a visual report accessible to the user via an interface. Specifically, the terminal renders the report using a browser or dedicated application, providing the user with an intuitive interface.

[0268] Step 6:

[0269] Users make decisions based on analytical reports displayed on their devices. The input is a visual report displayed on the device, and the output is the formulation of specific marketing and sales strategies. In terms of actions, users review the report and develop action plans based on the information presented in graphs and charts.

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] In today's information society, efficiently analyzing the effectiveness of advertising campaigns and understanding their impact on purchasing behavior is crucial for corporate strategy. However, traditional methods have made it difficult to analyze vast amounts of data in real time and immediately evaluate the effectiveness of advertising. Furthermore, insufficient information cleaning and causal relationship inference have hindered the optimization of advertising strategies.

[0273] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0274] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing formatting standardization and information cleaning on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generating AI. This makes it possible to verify the effectiveness of mobile advertising campaigns in real time and to analyze in detail the impact of ad delivery on purchasing behavior.

[0275] An "external information source" is an information provider that exists outside the system and provides location information and other related data.

[0276] "Location information" refers to data that indicates the geographical location of an object or moving object.

[0277] A "large-scale information set" is an information collection containing a vast amount of data, which is the subject of analysis.

[0278] "Format standardization" refers to organizing and arranging data of different formats and types according to a set of rules.

[0279] "Information cleaning" refers to the process of correcting and deleting unnecessary, redundant, or missing information from a data set.

[0280] "Generative AI" is an artificial intelligence technology that learns patterns from large-scale data and performs inference and prediction.

[0281] "Causal relationship" refers to an analytical result that shows a relationship in which one event influences another event.

[0282] An "analysis report" is a format that summarizes and visually displays the results of data analysis.

[0283] An "information processing device" is a device that inputs, processes, and outputs data, and serves as a terminal for users to check the results.

[0284] A "mobile advertising campaign" refers to an advertising strategy and its implementation activities developed for mobile devices.

[0285] "Purchase behavior" refers to a series of actions taken by consumers to purchase products.

[0286] A "causal relationship model" is a tool for visually representing the causal connections between data.

[0287] As a form of implementing this invention, first, the server acquires location information and other related data from multiple external information sources in real time. This data is often provided in different formats such as JSON format or CSV format. The server receives these data in a batch and performs format unification. For example, using PositionStack API or Google Maps API, etc., the location information is aggregated in real time.

[0288] After the data is collected, the server uses Python to perform data cleaning through the Pandas library. At this stage, duplicate data is deleted and missing values are complemented. This ensures the accuracy and consistency of the data.

[0289] Next, a generative AI model is used to infer potential causal relationships from the cleaned data. This AI model is built based on TensorFlow or Keras and has the ability to analyze hidden patterns in the data. The server verifies the effectiveness of the mobile advertising campaign based on the obtained causal relationships and identifies the specific impact of the advertisement on consumers' purchase behavior.

[0290] The generated analysis report is distributed to the information processing device and displayed on the terminal. This information processing device has a visual user interface built with React Native, enabling users to intuitively understand the information. Users can optimize the advertising strategy based on this report.

[0291] As a specific example, a report generated by a company's soda beverage advertising campaign in a particular region during the summer revealed that increasing advertising exposure during the evening hours resulted in a 20% increase in sales.

[0292] The generative AI model can be input with prompts such as: "Based on the given location data set, infer when and where a particular advertising campaign was most effective, and clearly indicate the causal relationship." This prompt allows the AI ​​model to extract meaningful results from the data and provide foundational information for use in business strategies.

[0293] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0294] Step 1:

[0295] The server acquires location information and user behavior data in real time from external sources. Input is raw data in JSON or CSV format, collected via external APIs. Output is data converted from different formats into a unified format. The server performs this data conversion to ensure smooth subsequent processing.

[0296] Step 2:

[0297] The server performs data cleaning using the Python Pandas library. The input for this step is data in a consistent format, and it is checked for incomplete or redundant records. The server improves data consistency by removing duplicate data and imputing missing data. The output is a clean dataset, ready for analysis.

[0298] Step 3:

[0299] The generative AI model is run on the server to infer potential causal relationships from cleaned data. The input for this step is a clean dataset that can be analyzed for causal relationships using statistical methods. Through this analysis, the server gains insights into how specific advertisements performed under specific conditions and models the causal relationships. The output is the analysis results regarding causal relationships.

[0300] Step 4:

[0301] The server generates an analysis report based on the analysis results and delivers it to the terminal. The input at this stage is the results of the causal relationship analysis, which includes specific information on the impact of the advertisements. The server converts this into a visual report so that the user can intuitively understand the results. The output is a visualized analysis report for the user. The user can use this to re-evaluate and optimize their advertising strategy.

[0302] Step 5:

[0303] Users review reports on their devices and adjust their advertising campaign strategies based on them. The input is an analytical report delivered from the server, which includes detailed causal relationships. Users can use this information to consider effective advertising strategies and, if necessary, re-enter prompts into the AI ​​model to gain new insights.

[0304] In this way, a consistent process is carried out from data collection to report generation, enabling users to obtain a foundation for effective decision-making.

[0305] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0306] The embodiments for implementing the present invention include constructing a data analysis system that recognizes the user's emotions and reflects them in the presentation of analysis results. This system is installed on a server and aims to analyze the user's emotions and improve the user experience by integrating an emotion engine.

[0307] The server acquires a large-scale dataset from an external data source and collects various types of information including location information data. The acquired data is unified in format and cleaned by the server, duplicate data is deleted, and missing values are complemented. Next, causal relationship inferences are performed on the dataset by generative artificial intelligence, and the results are generated as an analysis report.

[0308] In this process, the emotion engine plays an important role. The emotion engine performs sentiment analysis based on the user's interactions and input data, and analyzes the user's emotional state. The analysis results are protected by the server and reflected in the analysis report. For example, when the server recognizes through the emotion engine that the user has expectations or anxieties regarding the understanding of the issue, the content of the report can be customized according to that sentiment.

[0309] On the terminal, the display of the report according to the emotional state is dynamically adjusted for the user. As a result, the user can receive information in a form that conforms to their emotions, making it easier to make decisions. For example, when the user is viewing a report, the terminal can change the emphasis of the graph and the way of presenting recommended actions according to the user's emotions.

[0310] The present invention realizes a system that provides personalized insights for each user beyond simply providing numbers and graphs by combining emotion recognition technology with data analysis.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The server obtains location data and other related data from external data sources. This data is collected in real time via API communication and stored in the server's database.

[0314] Step 2:

[0315] The server performs data cleaning on the collected data. This step involves detecting and removing duplicate data, identifying and imputing missing values, and performing maintenance work to improve the accuracy of the data.

[0316] Step 3:

[0317] The server inputs the cleaned data into generative artificial intelligence, which automatically infers potential causal relationships. The AI ​​model analyzes data patterns and builds a causal network.

[0318] Step 4:

[0319] The server uses an emotion engine to analyze the user's emotional state based on their past behavior patterns and current interactions. This utilizes user feedback and behavior logs.

[0320] Step 5:

[0321] The server generates individually customized analysis reports based on inferred causal relationships and sentiment analysis results. These reports include recommendations and cautionary notes that take the user's emotions into consideration.

[0322] Step 6:

[0323] The server delivers the generated report to the user's terminal. The terminal generates an interface to display the received report according to the user's emotional state.

[0324] Step 7:

[0325] Users review reports displayed on their devices and consider the suggested actions. They can also provide feedback from their devices as needed, requesting further improvements.

[0326] (Example 2)

[0327] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0328] Traditional data analysis systems analyze data without considering the user's emotional state and generate static reports, resulting in insufficient support for users to effectively understand information and make appropriate decisions. Furthermore, there is a need for mechanisms to efficiently standardize and clean data.

[0329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0330] In this invention, the server includes means for acquiring large-scale data including geographic location information from multiple information sources, means for standardizing and purifying the acquired data, means for automatically estimating potential relationships from the data using artificial intelligence technology, means for distributing reports to a display device, and means for dynamically adjusting the display of the generated report based on the user's emotional state. This makes it possible to provide personalized reports that take into account the user's emotions.

[0331] A "data source" is a system or platform that supplies data from an external source.

[0332] "Geographic location information" refers to information used to identify a place or location within data.

[0333] A "large-scale dataset" is a dataset containing a vast amount of information.

[0334] "Standardization" is the process of unifying data formats into a consistent form.

[0335] "Purification" is the process of removing noise and unwanted elements from data.

[0336] "Artificial intelligence technology" refers to technologies that use machine learning and natural language processing to analyze data and gain insights.

[0337] "Relevance" refers to the correlation or causal relationship between different data points.

[0338] A "report" is a document that summarizes the results of an analysis and is a collection of information provided to the user.

[0339] A "display device" is hardware used to visually present data and information to a user.

[0340] "Dynamic adjustment" refers to the process of changing the content and format in real time according to the situation and conditions.

[0341] This invention is a data analysis system that utilizes a server and terminals. The server acquires large-scale data, including geographical location information, from multiple information sources. This includes data acquisition via APIs from cloud services and online databases. For example, it is possible to acquire user location information and behavioral data from social media platforms.

[0342] Next, the server standardizes the acquired data to unify the data format. During this process, data cleaning is also performed to remove noise and duplicate information. For example, the Python Pandas library can be used to efficiently process the data.

[0343] Subsequently, the server uses artificial intelligence technology, specifically generative AI models, to automatically estimate potential relationships within the data. This process utilizes machine learning algorithms to infer causal relationships within the data. Specifically, libraries such as Scikit-learn and TensorFlow are employed.

[0344] The generated analysis results are documented as a report. This report is dynamically displayed on the device based on the user's emotional state. This ensures that the report is delivered in a personalized way for each user, aiding their understanding. For example, if a user shows anxiety while viewing the report, the device will adjust to highlight information that alleviates that anxiety.

[0345] An example of a prompt might be, "Please provide recommended actions to alleviate the user's concerns about the new product." By inputting this prompt into the AI ​​model, it can generate specific action suggestions based on the user's emotions.

[0346] Users view this report through their device and make decisions based on the information provided. This allows them to receive support that takes their emotions into consideration, leading to a deeper understanding of the information and making more informed decisions. For example, when a user requests a review of a new product, the emotion engine can highlight positive feedback, potentially increasing the user's willingness to purchase.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The server acquires large-scale data, including geographical location information, from various data sources. This process involves collecting real-time data using APIs. The input is raw data obtained from the data sources, and the output is an integrated, large-scale dataset. Specifically, the server executes scheduled tasks and periodically accesses data sources to download essential data.

[0350] Step 2:

[0351] The server performs standardization and data purification on the acquired data. The input is a large, integrated dataset, and the output is a standardized, clean dataset free from noise and duplicates. This process includes specific actions such as unifying the data format, removing duplicates, and imputing missing values ​​using the Python Pandas library.

[0352] Step 3:

[0353] The server uses artificial intelligence techniques to estimate potential relationships in standardized data. The input is a clean dataset, and the output is an analysis result that includes the estimated relationships. In this process, generative AI models are utilized, and machine learning is performed using libraries such as Scikit-learn and TensorFlow. Specifically, prompt sentences are input to the AI ​​model, setting the task to "estimate the causal relationship between user behavior and emotion."

[0354] Step 4:

[0355] The server generates an analysis result as a report based on the estimated correlations. The input is the analysis result, and the output is a documented report. The server uses a template engine to output the report in PDF format, incorporating visualized graphs and charts.

[0356] Step 5:

[0357] The terminal delivers and displays the generated report to the user. The input is a documented report, and the output is a dynamically adjusted report displayed on the user's terminal. Upon receiving the report, the terminal evaluates the user's emotional state and performs specific actions to adjust the report's highlighting and layout based on that evaluation.

[0358] Step 6:

[0359] Users view reports displayed via their devices and make decisions based on the insights provided. The input is a dynamically adjusted report, and the output is the user's decision. Users interact with the device to find the information they need and interpret the data in a way that suits their own emotions.

[0360] (Application Example 2)

[0361] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0362] In today's commercial environment, it is crucial to offer products and services that take consumer emotions and interactions into consideration. However, conventional systems lack the ability to grasp consumers' emotional states in real time and dynamically present information accordingly. As a result, there are limitations to improving customer experience and increasing repeat purchase rates.

[0363] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0364] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for standardizing the format and cleaning the acquired information, and means for automatically inferring potential causal relationships from the information set using generative artificial intelligence. This makes it possible to present dynamically customized product suggestions and promotional information based on the consumer's emotional state.

[0365] "External information sources" refer to a collection of external data providers, databases, and other resources that a system uses to acquire information.

[0366] "Location information" refers to data that indicates a geographical location, and is used to pinpoint the precise geographical location of a user or device.

[0367] A "large-scale information collection" is an information resource that collects a vast amount of data, and it forms the basis for various analyses and processing.

[0368] "Format standardization" is the process of converting information in different formats into a consistent format to maintain the integrity of the information.

[0369] "Information cleansing" is a process of improving data quality by removing inaccurate or unnecessary information from a dataset.

[0370] "Generative artificial intelligence" refers to algorithms or programs that automatically generate new insights and causal relationships based on data.

[0371] "Latent causal relationships" refer to potential cause-and-effect relationships hidden within the data that are revealed through analysis.

[0372] "User emotions" refer to information that indicates the user's feelings and mood, and are used to adapt interfaces and services.

[0373] "Dynamic adjustment of displayed content" is a function that changes the information displayed in real time according to the user's state and environment.

[0374] An "analysis report" is a document or presentation format that summarizes the results of data analysis and is used to support decision-making.

[0375] In this embodiment, the server acquires a large set of information, including location data, from various external sources. This information may also include customer trends and purchase history. The server then performs formatting standardization and data cleansing on the acquired information. In this process, duplicate information is removed and missing values ​​are filled in to maintain data integrity. This improves data quality and yields reliable analysis results.

[0376] Next, the server uses generative artificial intelligence to automatically infer potential causal relationships from the collected information. In this analysis process, the AI ​​can generate new insights based on user interactions and purchase patterns.

[0377] The user's device can recognize their emotions in real time. Specifically, cameras and sensors are used to detect emotions from the user's facial expressions and voice, and this information is sent to a server. Based on this emotional data, the displayed content is dynamically adjusted, providing product recommendations and promotional information optimized for each individual user. This improves the consumer experience and increases convenience.

[0378] As a concrete example, if a customer in a physical store shows excitement in front of a new product, the terminal can offer special discount information related to that product. An example of a prompt message in this case would be, "If you feel excited when you see the new product, please show me discount information related to that product."

[0379] The hardware used includes devices such as smartphones and tablets, and the software utilizes emotion recognition APIs (e.g., Microsoft Azure Emotion API) and Python. This makes it possible to create a system that always provides the user with the most optimal information.

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The server acquires a large collection of information, including location data, from various external sources. This information includes customer location data, purchase history, and sensor data. The server receives this information and stores it in a temporary database. The input consists of various data from external sources, and the output is raw data with no unified format.

[0383] Step 2:

[0384] The server performs formatting standardization and data cleaning on the acquired information. This process resolves data format inconsistencies, removes unnecessary duplicate data, and fills in missing values. Specifically, this is done using certain scripts or database queries. The input is unstandardized raw data, and the output is cleaned data.

[0385] Step 3:

[0386] The server uses generative artificial intelligence to automatically infer potential causal relationships from a cleaned data set. In this process, the AI ​​algorithm analyzes the correlations and patterns in the data and generates new causal insights. The input is cleaned data, and the output is an analytical report reflecting the causal relationships.

[0387] Step 4:

[0388] The device recognizes the user's emotions in real time via the user's camera and sensors. The recognized emotional data is sent to a server where it is used for analysis. The input is raw emotional data obtained from the user, and the output is the analyzed emotional state.

[0389] Step 5:

[0390] The server dynamically adjusts the displayed content based on the user's emotional state and delivers customized product recommendations and promotional information to the device. An AI model selects and displays appropriate information using prompts. Inputs are emotional state and analysis reports, while output is customized information presentation.

[0391] Step 6:

[0392] Users receive the presented information on their devices and enjoy an optimized shopping experience, which improves consumer satisfaction. The input is customized information received from the device, and the output is the user's experience and behavioral changes. Specific actions include making purchase decisions and changing the user's movement within the store.

[0393] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0394] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0395] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0399] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0400] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0401] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0402] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0403] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0404] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0405] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0406] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0407] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0408] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0409] In an embodiment for carrying out the present invention, a data analysis system is built on a server. This system is specialized for analyzing large datasets and acquires location data and other information in real time from external data sources. The server first performs data cleaning on the acquired data, automatically removing duplicate data and imputing missing values. For example, if location information logs for moving objects are duplicated, the server detects the duplicate data and integrates it into a single entry.

[0410] The cleaned data is analyzed by the server using generative artificial intelligence. This AI has the ability to infer latent causal relationships from large amounts of data and generates an analysis report based on the extracted causal relationships. For example, the server can analyze retail store promotion data and find a causal relationship such as "an increase in the number of visitors during the promotion period has a positive impact on sales."

[0411] The generated analysis report is provided to the user via a terminal. The terminal has a report display interface, allowing the user to intuitively understand the data analysis results. Users can review the report on the terminal and adjust their sales strategies and marketing plans based on it. For example, based on the displayed report, a user can formulate a promotional strategy that would be more effective when implemented during a specific season.

[0412] Thus, the present invention provides a system that comprehensively handles everything from data collection and analysis to report generation and presentation, supporting the decision-making process of companies.

[0413] The following describes the processing flow.

[0414] Step 1:

[0415] The server retrieves datasets containing location data in real time from external data sources. This includes periodically polling the data via an API and saving new data to storage on the server.

[0416] Step 2:

[0417] The server performs data cleaning on the retrieved data, removing duplicate data and imputing missing values. This process uses an algorithm to consolidate duplicate information in case multiple identical data entries exist.

[0418] Step 3:

[0419] The server feeds the cleaned data into generative artificial intelligence to infer causal relationships. This AI automatically extracts potential causal relationships from large datasets and generates a causal network model.

[0420] Step 4:

[0421] The server generates an analytical report with detailed and visualized content based on the inferred causal relationships. This report includes recommended actions, graphs, and charts.

[0422] Step 5:

[0423] The server distributes the generated report to the terminal. The terminal receives this information and prepares to display it in a user-friendly interface.

[0424] Step 6:

[0425] Users view reports through their devices. They review the visualized causal relationships and make business decisions based on the findings. If necessary, they can also send feedback on the report to the server.

[0426] (Example 1)

[0427] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0428] Acquiring large datasets in real time and rapidly and automatically inferring potential causal relationships to generate analysis results is difficult with conventional methods. Such tasks require significant manual effort and expertise, making it inefficient in supporting a company's decision-making process. A solution to this problem is needed.

[0429] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0430] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing format unification and information organization on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generative machine learning model. This enables rapid and automatic inference of causal relationships and generation of analysis results based on a large-scale information set.

[0431] "External information sources" refer to systems and devices that supply data, and are the sources from which information is obtained in real time.

[0432] "Location information" refers to data that indicates a specific point or area, and is usually composed of longitude and latitude.

[0433] A "large-scale information set" refers to a very large dataset that is used for analytical purposes.

[0434] "Information organization" is the process of removing duplicates from collected data and filling in any missing values.

[0435] A "generative machine learning model" is a type of artificial intelligence that has the ability to infer latent patterns and causal relationships based on large amounts of data.

[0436] "Causal relationship" refers to the cause-and-effect relationship that exists between different factors or data.

[0437] "Analysis results" refer to the final output obtained during the data analysis process, and include information that can be used to inform decision-making.

[0438] A "terminal" is a device that a user uses to receive and display information and to operate it through an interface.

[0439] To implement this invention, the data analysis system must be built primarily on a server. This system is specialized for processing large amounts of information, and the server acquires location information in real time from multiple external information sources. This allows the server to quickly collect dynamically changing data.

[0440] The server then performs formatting and information organization on the retrieved data. This step involves removing duplicate data and imputing missing values. Specifically, it uses database queries to consolidate duplicate entries. For example, a database management system using SQL is suitable for this process.

[0441] Next, the server analyzes the cleaned data using a generative machine learning model. This model detects potential causal relationships within the vast amount of data and performs inference. The AI ​​model used is a generative AI model. By utilizing this AI model, companies can make management decisions based on large-scale data.

[0442] The analysis results are compiled by the server and delivered to the user via the terminal. The terminal provides a display interface designed to allow users to easily understand the information. The reports received by the user can be used to review sales strategies and marketing plans.

[0443] As an example of a prompt, one could input a specific question into the generating AI model, such as, "Please analyze the impact of an increase in the number of visitors on sales." This would allow users to gain valuable insights that enable data-driven decision-making.

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The server acquires a large collection of information, including location data, in real time from multiple external information sources. Its input is raw data obtained from APIs, and its output is unprocessed data stored in the server's storage. Specifically, the server accesses the API endpoints of the information sources and requests data using specified parameters.

[0447] Step 2:

[0448] The server performs formatting and information organization on the retrieved raw data. Raw data is taken as input, and cleaned data is generated as output. Specifically, the server uses database queries to remove duplicate data and impute missing values. For example, an SQL query is executed to group data by date and location as keys and merge duplicates.

[0449] Step 3:

[0450] The server inputs the cleaned data into a generative machine learning model to infer potential causal relationships. The input is organized data, and the output is the model's inference results showing causal relationships. Specifically, the server starts a generative AI model, generates prompts based on the data, and then inputs them into the AI. For example, the prompt "Analyze the impact of an increase in the number of visitors on sales" might be sent to the AI.

[0451] Step 4:

[0452] The server generates and visualizes analysis results based on the inference results. The input is the inference results from the AI ​​model, and the output is an analysis result that can be displayed on the terminal. Specifically, the server uses visualization libraries such as Matplotlib and Plotly in Python to create graphs and packages the results in HTML format.

[0453] Step 5:

[0454] The terminal receives analysis results sent from the server and displays them to the user. The input is an HTML-formatted analysis report sent from the server, and the output is a visual report accessible to the user via an interface. Specifically, the terminal renders the report using a browser or dedicated application, providing the user with an intuitive interface.

[0455] Step 6:

[0456] Users make decisions based on analytical reports displayed on their devices. The input is a visual report displayed on the device, and the output is the formulation of specific marketing and sales strategies. In terms of actions, users review the report and develop action plans based on the information presented in graphs and charts.

[0457] (Application Example 1)

[0458] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0459] In today's information society, efficiently analyzing the effectiveness of advertising campaigns and understanding their impact on purchasing behavior is crucial for corporate strategy. However, traditional methods have made it difficult to analyze vast amounts of data in real time and immediately evaluate the effectiveness of advertising. Furthermore, insufficient information cleaning and causal relationship inference have hindered the optimization of advertising strategies.

[0460] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0461] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing formatting standardization and information cleaning on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generating AI. This makes it possible to verify the effectiveness of mobile advertising campaigns in real time and to analyze in detail the impact of ad delivery on purchasing behavior.

[0462] An "external information source" is an information provider that exists outside the system and provides location information and other related data.

[0463] "Location information" refers to data that indicates the geographical location of an object or moving object.

[0464] A "large-scale information set" is an information collection containing a vast amount of data, which is the subject of analysis.

[0465] "Format standardization" refers to organizing and arranging data of different formats and types according to a set of rules.

[0466] "Information cleaning" refers to the process of correcting and deleting unnecessary, redundant, or missing information from a data set.

[0467] "Generative AI" is an artificial intelligence technology that learns patterns from large-scale data and performs inference and prediction.

[0468] "Causal relationship" refers to an analytical result that shows a relationship in which one event influences another event.

[0469] An "analysis report" is a format that summarizes and visually displays the results of data analysis.

[0470] An "information processing device" is a device that inputs, processes, and outputs data, and serves as a terminal for users to check the results.

[0471] A "mobile advertising campaign" refers to an advertising strategy and its implementation activities that are targeted at mobile devices.

[0472] "Purchasing behavior" refers to the series of actions that consumers take in order to purchase a product.

[0473] A "causal relationship model" is a tool for visually representing the causal connections between data points.

[0474] In an embodiment of this invention, the server first acquires location information and other related data in real time from multiple external sources. This data is often provided in different formats such as JSON or CSV. The server receives this data in bulk and unifies the format. For example, it aggregates location information in real time using APIs such as PositionStack API or Google Maps API.

[0475] After the data is collected, the server uses Python to perform data cleaning via the Pandas library. At this stage, duplicate data is removed and missing values ​​are imputed. This ensures the accuracy and consistency of the data.

[0476] Next, a generative AI model is used to infer potential causal relationships from the cleaned data. This AI model is built on TensorFlow or Keras and has the ability to analyze hidden patterns in the data. Based on the causal relationships obtained, the server validates the effectiveness of mobile advertising campaigns and identifies the specific impact that advertisements have on consumer purchasing behavior.

[0477] The generated analysis report is delivered to an information processing device and displayed on the terminal. This device has a visual user interface built with React Native, allowing users to intuitively understand the information. Based on this report, users can optimize their advertising strategy.

[0478] As a specific example, a report generated by a company's soda beverage advertising campaign in a particular region during the summer revealed that increasing advertising exposure during the evening hours resulted in a 20% increase in sales.

[0479] The generative AI model can be input with prompts such as: "Based on the given location data set, infer when and where a particular advertising campaign was most effective, and clearly indicate the causal relationship." This prompt allows the AI ​​model to extract meaningful results from the data and provide foundational information for use in business strategies.

[0480] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0481] Step 1:

[0482] The server acquires location information and user behavior data in real time from external sources. Input is raw data in JSON or CSV format, collected via external APIs. Output is data converted from different formats into a unified format. The server performs this data conversion to ensure smooth subsequent processing.

[0483] Step 2:

[0484] The server performs data cleaning using the Python Pandas library. The input for this step is data in a consistent format, and it is checked for incomplete or redundant records. The server improves data consistency by removing duplicate data and imputing missing data. The output is a clean dataset, ready for analysis.

[0485] Step 3:

[0486] The generative AI model is run on the server to infer potential causal relationships from cleaned data. The input for this step is a clean dataset that can be analyzed for causal relationships using statistical methods. Through this analysis, the server gains insights into how specific advertisements performed under specific conditions and models the causal relationships. The output is the analysis results regarding causal relationships.

[0487] Step 4:

[0488] The server generates an analysis report based on the analysis results and delivers it to the terminal. The input at this stage is the results of the causal relationship analysis, which includes specific information on the impact of the advertisements. The server converts this into a visual report so that the user can intuitively understand the results. The output is a visualized analysis report for the user. The user can use this to re-evaluate and optimize their advertising strategy.

[0489] Step 5:

[0490] Users review reports on their devices and adjust their advertising campaign strategies based on them. The input is an analytical report delivered from the server, which includes detailed causal relationships. Users can use this information to consider effective advertising strategies and, if necessary, re-enter prompts into the AI ​​model to gain new insights.

[0491] In this way, a consistent process is carried out from data collection to report generation, enabling users to obtain a foundation for effective decision-making.

[0492] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0493] Embodiments of the present invention include the construction of a data analysis system that recognizes user emotions and reflects them in the presentation of analysis results. This system is installed on a server and aims to improve the user experience by analyzing user emotions through the integration of an emotion engine.

[0494] The server acquires large datasets from external data sources and collects various information, including location data. The acquired data is formatted and cleaned by the server, with duplicate data removed and missing values ​​imputed. Next, generative artificial intelligence performs causal relationship inference on the dataset and generates an analysis report based on the results.

[0495] In this process, the emotion engine plays a crucial role. Based on user interactions and input data, the emotion engine performs sentiment analysis to understand the user's emotional state. This analysis is protected by the server and reflected in the analysis report. For example, if the server, through the emotion engine, recognizes that the user has expectations or anxieties about understanding a problem, it can customize the report content to reflect those sentiments.

[0496] On the device, the display of reports is dynamically adjusted to match the user's emotional state. This allows users to receive information in a format that aligns with their emotions, making it easier for them to make decisions. For example, as a user views a report, the device can change the emphasis of graphs and the way recommended actions are presented based on the user's emotions.

[0497] This invention combines emotion recognition technology with data analysis to create a system that provides personalized insights to each individual user, going beyond simply providing numbers and graphs.

[0498] The following describes the processing flow.

[0499] Step 1:

[0500] The server obtains location data and other related data from external data sources. This data is collected in real time via API communication and stored in the server's database.

[0501] Step 2:

[0502] The server performs data cleaning on the collected data. This step involves detecting and removing duplicate data, identifying and imputing missing values, and performing maintenance work to improve the accuracy of the data.

[0503] Step 3:

[0504] The server inputs the cleaned data into generative artificial intelligence, which automatically infers potential causal relationships. The AI ​​model analyzes data patterns and builds a causal network.

[0505] Step 4:

[0506] The server uses an emotion engine to analyze the user's emotional state based on their past behavior patterns and current interactions. This utilizes user feedback and behavior logs.

[0507] Step 5:

[0508] The server generates individually customized analysis reports based on inferred causal relationships and sentiment analysis results. These reports include recommendations and cautionary notes that take the user's emotions into consideration.

[0509] Step 6:

[0510] The server delivers the generated report to the user's terminal. The terminal generates an interface to display the received report according to the user's emotional state.

[0511] Step 7:

[0512] Users review reports displayed on their devices and consider the suggested actions. They can also provide feedback from their devices as needed, requesting further improvements.

[0513] (Example 2)

[0514] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0515] Traditional data analysis systems analyze data without considering the user's emotional state and generate static reports, resulting in insufficient support for users to effectively understand information and make appropriate decisions. Furthermore, there is a need for mechanisms to efficiently standardize and clean data.

[0516] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0517] In this invention, the server includes means for acquiring large-scale data including geographic location information from multiple information sources, means for standardizing and purifying the acquired data, means for automatically estimating potential relationships from the data using artificial intelligence technology, means for distributing reports to a display device, and means for dynamically adjusting the display of the generated report based on the user's emotional state. This makes it possible to provide personalized reports that take into account the user's emotions.

[0518] A "data source" is a system or platform that supplies data from an external source.

[0519] "Geographic location information" refers to information used to identify a place or location within data.

[0520] A "large-scale dataset" is a dataset containing a vast amount of information.

[0521] "Standardization" is the process of unifying data formats into a consistent form.

[0522] "Purification" is the process of removing noise and unwanted elements from data.

[0523] "Artificial intelligence technology" refers to technologies that use machine learning and natural language processing to analyze data and gain insights.

[0524] "Relevance" refers to the correlation or causal relationship between different data points.

[0525] A "report" is a document that summarizes the results of an analysis and is a collection of information provided to the user.

[0526] A "display device" is hardware used to visually present data and information to a user.

[0527] "Dynamic adjustment" refers to the process of changing the content and format in real time according to the situation and conditions.

[0528] This invention is a data analysis system that utilizes a server and terminals. The server acquires large-scale data, including geographical location information, from multiple information sources. This includes data acquisition via APIs from cloud services and online databases. For example, it is possible to acquire user location information and behavioral data from social media platforms.

[0529] Next, the server standardizes the acquired data to unify the data format. During this process, data cleaning is also performed to remove noise and duplicate information. For example, the Python Pandas library can be used to efficiently process the data.

[0530] Subsequently, the server uses artificial intelligence technology, specifically generative AI models, to automatically estimate potential relationships within the data. This process utilizes machine learning algorithms to estimate causal relationships within the data. Specifically, libraries such as Scikit-learn and TensorFlow are used.

[0531] The generated analysis results are documented as a report. This report is dynamically displayed on the device based on the user's emotional state. This ensures that the report is delivered in a personalized way for each user, aiding their understanding. For example, if a user shows anxiety while viewing the report, the device will adjust to highlight information that alleviates that anxiety.

[0532] An example of a prompt might be, "Please provide recommended actions to alleviate the user's concerns about the new product." By inputting this prompt into the AI ​​model, it can generate specific action suggestions based on the user's emotions.

[0533] Users view this report through their device and make decisions based on the information provided. This allows them to receive support that takes their emotions into consideration, leading to a deeper understanding of the information and making more informed decisions. For example, when a user requests a review of a new product, the emotion engine can highlight positive feedback, potentially increasing the user's willingness to purchase.

[0534] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0535] Step 1:

[0536] The server acquires large-scale data, including geographical location information, from various data sources. This process involves collecting real-time data using APIs. The input is raw data obtained from the data sources, and the output is an integrated, large-scale dataset. Specifically, the server executes scheduled tasks and periodically accesses data sources to download essential data.

[0537] Step 2:

[0538] The server performs standardization and data purification on the acquired data. The input is a large, integrated dataset, and the output is a standardized, clean dataset free from noise and duplicates. This process includes specific actions such as unifying the data format, removing duplicates, and imputing missing values ​​using the Python Pandas library.

[0539] Step 3:

[0540] The server uses artificial intelligence techniques to estimate potential relationships in standardized data. The input is a clean dataset, and the output is an analysis result that includes the estimated relationships. In this process, generative AI models are utilized, and machine learning is performed using libraries such as Scikit-learn and TensorFlow. Specifically, prompt sentences are input to the AI ​​model, setting the task to "estimate the causal relationship between user behavior and emotion."

[0541] Step 4:

[0542] The server generates an analysis result as a report based on the estimated correlations. The input is the analysis result, and the output is a documented report. The server uses a template engine to output the report in PDF format, incorporating visualized graphs and charts.

[0543] Step 5:

[0544] The terminal delivers and displays the generated report to the user. The input is a documented report, and the output is a dynamically adjusted report displayed on the user's terminal. Upon receiving the report, the terminal evaluates the user's emotional state and performs specific actions to adjust the report's highlighting and layout based on that evaluation.

[0545] Step 6:

[0546] Users view reports displayed via their devices and make decisions based on the insights provided. The input is a dynamically adjusted report, and the output is the user's decision. Users interact with the device to find the information they need and interpret the data in a way that suits their own emotions.

[0547] (Application Example 2)

[0548] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0549] In today's commercial environment, it is crucial to offer products and services that take consumer emotions and interactions into consideration. However, conventional systems lack the ability to grasp consumers' emotional states in real time and dynamically present information accordingly. As a result, there are limitations to improving customer experience and increasing repeat purchase rates.

[0550] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0551] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for standardizing the format and cleaning the acquired information, and means for automatically inferring potential causal relationships from the information set using generative artificial intelligence. This makes it possible to present dynamically customized product suggestions and promotional information based on the consumer's emotional state.

[0552] "External information sources" refer to a collection of external data providers, databases, and other resources that a system uses to acquire information.

[0553] "Location information" refers to data that indicates a geographical location, and is used to pinpoint the precise geographical location of a user or device.

[0554] A "large-scale information collection" is an information resource that collects a vast amount of data, and it forms the basis for various analyses and processing.

[0555] "Format standardization" is the process of converting information in different formats into a consistent format to maintain the integrity of the information.

[0556] "Information cleansing" is a process of improving data quality by removing inaccurate or unnecessary information from a dataset.

[0557] "Generative artificial intelligence" refers to algorithms or programs that automatically generate new insights and causal relationships based on data.

[0558] "Latent causal relationships" refer to potential cause-and-effect relationships hidden within the data that are revealed through analysis.

[0559] "User emotions" refer to information that indicates the user's feelings and mood, and are used to adapt interfaces and services.

[0560] "Dynamic adjustment of displayed content" is a function that changes the information displayed in real time according to the user's state and environment.

[0561] An "analysis report" is a document or presentation format that summarizes the results of data analysis and is used to support decision-making.

[0562] In this embodiment, the server acquires a large set of information, including location data, from various external sources. This information may also include customer trends and purchase history. The server then performs formatting standardization and data cleansing on the acquired information. In this process, duplicate information is removed and missing values ​​are filled in to maintain data integrity. This improves data quality and yields reliable analysis results.

[0563] Next, the server uses generative artificial intelligence to automatically infer potential causal relationships from the collected information. In this analysis process, the AI ​​can generate new insights based on user interactions and purchase patterns.

[0564] The user's device can recognize their emotions in real time. Specifically, cameras and sensors are used to detect emotions from the user's facial expressions and voice, and this information is sent to a server. Based on this emotional data, the displayed content is dynamically adjusted, providing product recommendations and promotional information optimized for each individual user. This improves the consumer experience and increases convenience.

[0565] As a concrete example, if a customer in a physical store shows excitement in front of a new product, the terminal can offer special discount information related to that product. An example of a prompt message in this case would be, "If you feel excited when you see the new product, please show me discount information related to that product."

[0566] The hardware used includes devices such as smartphones and tablets, and the software utilizes emotion recognition APIs (e.g., Microsoft Azure Emotion API) and Python. This makes it possible to create a system that always provides the user with the most optimal information.

[0567] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0568] Step 1:

[0569] The server acquires a large collection of information, including location data, from various external sources. This information includes customer location data, purchase history, and sensor data. The server receives this information and stores it in a temporary database. The input consists of various data from external sources, and the output is raw data with no unified format.

[0570] Step 2:

[0571] The server performs formatting standardization and data cleaning on the acquired information. This process resolves data format inconsistencies, removes unnecessary duplicate data, and fills in missing values. Specifically, this is done using certain scripts or database queries. The input is unstandardized raw data, and the output is cleaned data.

[0572] Step 3:

[0573] The server uses generative artificial intelligence to automatically infer potential causal relationships from a cleaned data set. In this process, the AI ​​algorithm analyzes the correlations and patterns in the data and generates new causal insights. The input is cleaned data, and the output is an analytical report reflecting the causal relationships.

[0574] Step 4:

[0575] The device recognizes the user's emotions in real time via the user's camera and sensors. The recognized emotional data is sent to a server where it is used for analysis. The input is raw emotional data obtained from the user, and the output is the analyzed emotional state.

[0576] Step 5:

[0577] The server dynamically adjusts the displayed content based on the user's emotional state and delivers customized product recommendations and promotional information to the device. An AI model selects and displays appropriate information using prompts. Inputs are emotional state and analysis reports, while output is customized information presentation.

[0578] Step 6:

[0579] Users receive the presented information on their devices and enjoy an optimized shopping experience, which improves consumer satisfaction. The input is customized information received from the device, and the output is the user's experience and behavioral changes. Specific actions include making purchase decisions and changing the user's movement within the store.

[0580] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0581] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0582] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0583] [Fourth Embodiment]

[0584] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0585] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0586] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0587] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0588] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0589] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0590] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0591] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0592] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0593] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0594] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0595] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0596] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0597] In an embodiment for carrying out the present invention, a data analysis system is built on a server. This system is specialized for analyzing large datasets and acquires location data and other information in real time from external data sources. The server first performs data cleaning on the acquired data, automatically removing duplicate data and imputing missing values. For example, if location information logs for moving objects are duplicated, the server detects the duplicate data and integrates it into a single entry.

[0598] The cleaned data is analyzed by the server using generative artificial intelligence. This AI has the ability to infer latent causal relationships from large amounts of data and generates an analysis report based on the extracted causal relationships. For example, the server can analyze retail store promotion data and find a causal relationship such as "an increase in the number of visitors during the promotion period has a positive impact on sales."

[0599] The generated analysis report is provided to the user via a terminal. The terminal has a report display interface, allowing the user to intuitively understand the data analysis results. Users can review the report on the terminal and adjust their sales strategies and marketing plans based on it. For example, based on the displayed report, a user can formulate a promotional strategy that would be more effective when implemented during a specific season.

[0600] Thus, the present invention provides a system that comprehensively handles everything from data collection and analysis to report generation and presentation, supporting the decision-making process of companies.

[0601] The following describes the processing flow.

[0602] Step 1:

[0603] The server retrieves datasets containing location data in real time from external data sources. This includes periodically polling the data via an API and saving new data to storage on the server.

[0604] Step 2:

[0605] The server performs data cleaning on the retrieved data, removing duplicate data and imputing missing values. This process uses an algorithm to consolidate duplicate information in case multiple identical data entries exist.

[0606] Step 3:

[0607] The server feeds the cleaned data into generative artificial intelligence to infer causal relationships. This AI automatically extracts potential causal relationships from large datasets and generates a causal network model.

[0608] Step 4:

[0609] The server generates an analytical report with detailed and visualized content based on the inferred causal relationships. This report includes recommended actions, graphs, and charts.

[0610] Step 5:

[0611] The server distributes the generated report to the terminal. The terminal receives this information and prepares to display it in a user-friendly interface.

[0612] Step 6:

[0613] Users view reports through their devices. They review the visualized causal relationships and make business decisions based on the findings. If necessary, they can also send feedback on the report to the server.

[0614] (Example 1)

[0615] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0616] Acquiring large datasets in real time and rapidly and automatically inferring potential causal relationships to generate analysis results is difficult with conventional methods. Such tasks require significant manual effort and expertise, making it inefficient in supporting a company's decision-making process. A solution to this problem is needed.

[0617] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0618] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing format unification and information organization on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generative machine learning model. This enables rapid and automatic inference of causal relationships and generation of analysis results based on a large-scale information set.

[0619] "External information sources" refer to systems and devices that supply data, and are the sources from which information is obtained in real time.

[0620] "Location information" refers to data that indicates a specific point or area, and is usually composed of longitude and latitude.

[0621] A "large-scale information set" refers to a very large dataset that is used for analytical purposes.

[0622] "Information organization" is the process of removing duplicates from collected data and filling in any missing values.

[0623] A "generative machine learning model" is a type of artificial intelligence that has the ability to infer latent patterns and causal relationships based on large amounts of data.

[0624] "Causal relationship" refers to the cause-and-effect relationship that exists between different factors or data.

[0625] "Analysis results" refer to the final output obtained during the data analysis process, and include information that can be used to inform decision-making.

[0626] A "terminal" is a device that a user uses to receive and display information and to operate it through an interface.

[0627] To implement this invention, the data analysis system must be built primarily on a server. This system is specialized for processing large amounts of information, and the server acquires location information in real time from multiple external information sources. This allows the server to quickly collect dynamically changing data.

[0628] The server then performs formatting and information organization on the retrieved data. This step involves removing duplicate data and imputing missing values. Specifically, it uses database queries to consolidate duplicate entries. For example, a database management system using SQL is suitable for this process.

[0629] Next, the server analyzes the cleaned data using a generative machine learning model. This model detects potential causal relationships within the vast amount of data and performs inference. The AI ​​model used is a generative AI model. By utilizing this AI model, companies can make management decisions based on large-scale data.

[0630] The analysis results are compiled by the server and delivered to the user via the terminal. The terminal provides a display interface designed to allow users to easily understand the information. The reports received by the user can be used to review sales strategies and marketing plans.

[0631] As an example of a prompt, one could input a specific question into the generating AI model, such as, "Please analyze the impact of an increase in the number of visitors on sales." This would allow users to gain valuable insights that enable data-driven decision-making.

[0632] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0633] Step 1:

[0634] The server acquires a large collection of information, including location data, in real time from multiple external information sources. Its input is raw data obtained from APIs, and its output is unprocessed data stored in the server's storage. Specifically, the server accesses the API endpoints of the information sources and requests data using specified parameters.

[0635] Step 2:

[0636] The server performs formatting and information organization on the retrieved raw data. Raw data is taken as input, and cleaned data is generated as output. Specifically, the server uses database queries to remove duplicate data and impute missing values. For example, an SQL query is executed to group data by date and location as keys and merge duplicates.

[0637] Step 3:

[0638] The server inputs the cleaned data into a generative machine learning model to infer potential causal relationships. The input is organized data, and the output is the model's inference results showing causal relationships. Specifically, the server starts a generative AI model, generates prompts based on the data, and then inputs them into the AI. For example, the prompt "Analyze the impact of an increase in the number of visitors on sales" might be sent to the AI.

[0639] Step 4:

[0640] The server generates and visualizes analysis results based on the inference results. The input is the inference results from the AI ​​model, and the output is an analysis result that can be displayed on the terminal. Specifically, the server uses visualization libraries such as Matplotlib and Plotly in Python to create graphs and packages the results in HTML format.

[0641] Step 5:

[0642] The terminal receives analysis results sent from the server and displays them to the user. The input is an HTML-formatted analysis report sent from the server, and the output is a visual report accessible to the user via an interface. Specifically, the terminal renders the report using a browser or dedicated application, providing the user with an intuitive interface.

[0643] Step 6:

[0644] Users make decisions based on analytical reports displayed on their devices. The input is a visual report displayed on the device, and the output is the formulation of specific marketing and sales strategies. In terms of actions, users review the report and develop action plans based on the information presented in graphs and charts.

[0645] (Application Example 1)

[0646] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] In today's information society, efficiently analyzing the effectiveness of advertising campaigns and understanding their impact on purchasing behavior is crucial for corporate strategy. However, traditional methods have made it difficult to analyze vast amounts of data in real time and immediately evaluate the effectiveness of advertising. Furthermore, insufficient information cleaning and causal relationship inference have hindered the optimization of advertising strategies.

[0648] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0649] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for performing formatting standardization and information cleaning on the acquired information, and means for automatically inferring potential causal relationships from the information set using a generating AI. This makes it possible to verify the effectiveness of mobile advertising campaigns in real time and to analyze in detail the impact of ad delivery on purchasing behavior.

[0650] An "external information source" is an information provider that exists outside the system and provides location information and other related data.

[0651] "Location information" refers to data that indicates the geographical location of an object or moving object.

[0652] A "large-scale information set" is an information collection containing a vast amount of data, which is the subject of analysis.

[0653] "Format standardization" refers to organizing and arranging data of different formats and types according to a set of rules.

[0654] "Information cleaning" refers to the process of correcting and deleting unnecessary, redundant, or missing information from a data set.

[0655] "Generative AI" is an artificial intelligence technology that learns patterns from large-scale data and performs inference and prediction.

[0656] "Causal relationship" refers to an analytical result that shows a relationship in which one event influences another event.

[0657] An "analysis report" is a format that summarizes and visually displays the results of data analysis.

[0658] An "information processing device" is a device that inputs, processes, and outputs data, and serves as a terminal for users to check the results.

[0659] A "mobile advertising campaign" refers to an advertising strategy and its implementation activities that are targeted at mobile devices.

[0660] "Purchasing behavior" refers to the series of actions that consumers take in order to purchase a product.

[0661] A "causal relationship model" is a tool for visually representing the causal connections between data points.

[0662] In an embodiment of this invention, the server first acquires location information and other related data in real time from multiple external sources. This data is often provided in different formats such as JSON or CSV. The server receives this data in bulk and unifies the format. For example, it aggregates location information in real time using APIs such as PositionStack API or Google Maps API.

[0663] After the data is collected, the server uses Python to perform data cleaning via the Pandas library. At this stage, duplicate data is removed and missing values ​​are imputed. This ensures the accuracy and consistency of the data.

[0664] Next, a generative AI model is used to infer potential causal relationships from the cleaned data. This AI model is built on TensorFlow or Keras and has the ability to analyze hidden patterns in the data. Based on the causal relationships obtained, the server validates the effectiveness of mobile advertising campaigns and identifies the specific impact that advertisements have on consumer purchasing behavior.

[0665] The generated analysis report is delivered to an information processing device and displayed on the terminal. This device has a visual user interface built with React Native, allowing users to intuitively understand the information. Based on this report, users can optimize their advertising strategy.

[0666] As a specific example, a report generated by a company's soda beverage advertising campaign in a particular region during the summer revealed that increasing advertising exposure during the evening hours resulted in a 20% increase in sales.

[0667] The generative AI model can be input with prompts such as: "Based on the given location data set, infer when and where a particular advertising campaign was most effective, and clearly indicate the causal relationship." This prompt allows the AI ​​model to extract meaningful results from the data and provide foundational information for use in business strategies.

[0668] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0669] Step 1:

[0670] The server acquires location information and user behavior data in real time from external sources. Input is raw data in JSON or CSV format, collected via external APIs. Output is data converted from different formats into a unified format. The server performs this data conversion to ensure smooth subsequent processing.

[0671] Step 2:

[0672] The server performs data cleaning using the Python Pandas library. The input for this step is data in a consistent format, and it is checked for incomplete or redundant records. The server improves data consistency by removing duplicate data and imputing missing data. The output is a clean dataset, ready for analysis.

[0673] Step 3:

[0674] The generative AI model is run on the server to infer potential causal relationships from cleaned data. The input for this step is a clean dataset that can be analyzed for causal relationships using statistical methods. Through this analysis, the server gains insights into how specific advertisements performed under specific conditions and models the causal relationships. The output is the analysis results regarding causal relationships.

[0675] Step 4:

[0676] The server generates an analysis report based on the analysis results and delivers it to the terminal. The input at this stage is the results of the causal relationship analysis, which includes specific information on the impact of the advertisements. The server converts this into a visual report so that the user can intuitively understand the results. The output is a visualized analysis report for the user. The user can use this to re-evaluate and optimize their advertising strategy.

[0677] Step 5:

[0678] Users review reports on their devices and adjust their advertising campaign strategies based on them. The input is an analytical report delivered from the server, which includes detailed causal relationships. Users can use this information to consider effective advertising strategies and, if necessary, re-enter prompts into the AI ​​model to gain new insights.

[0679] In this way, a consistent process is carried out from data collection to report generation, enabling users to obtain a foundation for effective decision-making.

[0680] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0681] Embodiments of the present invention include the construction of a data analysis system that recognizes user emotions and reflects them in the presentation of analysis results. This system is installed on a server and aims to improve the user experience by analyzing user emotions through the integration of an emotion engine.

[0682] The server acquires large datasets from external data sources and collects various information, including location data. The acquired data is formatted and cleaned by the server, with duplicate data removed and missing values ​​imputed. Next, generative artificial intelligence performs causal relationship inference on the dataset and generates an analysis report based on the results.

[0683] In this process, the emotion engine plays a crucial role. Based on user interactions and input data, the emotion engine performs sentiment analysis to understand the user's emotional state. This analysis is protected by the server and reflected in the analysis report. For example, if the server, through the emotion engine, recognizes that the user has expectations or anxieties about understanding a problem, it can customize the report content to reflect those sentiments.

[0684] On the device, the display of reports is dynamically adjusted to match the user's emotional state. This allows users to receive information in a format that aligns with their emotions, making it easier for them to make decisions. For example, as a user views a report, the device can change the emphasis of graphs and the way recommended actions are presented based on the user's emotions.

[0685] This invention combines emotion recognition technology with data analysis to create a system that provides personalized insights to each individual user, going beyond simply providing numbers and graphs.

[0686] The following describes the processing flow.

[0687] Step 1:

[0688] The server obtains location data and other related data from external data sources. This data is collected in real time via API communication and stored in the server's database.

[0689] Step 2:

[0690] The server performs data cleaning on the collected data. This step involves detecting and removing duplicate data, identifying and imputing missing values, and performing maintenance work to improve the accuracy of the data.

[0691] Step 3:

[0692] The server inputs the cleaned data into generative artificial intelligence, which automatically infers potential causal relationships. The AI ​​model analyzes data patterns and builds a causal network.

[0693] Step 4:

[0694] The server uses an emotion engine to analyze the user's emotional state based on their past behavior patterns and current interactions. This utilizes user feedback and behavior logs.

[0695] Step 5:

[0696] The server generates individually customized analysis reports based on inferred causal relationships and sentiment analysis results. These reports include recommendations and cautionary notes that take the user's emotions into consideration.

[0697] Step 6:

[0698] The server delivers the generated report to the user's terminal. The terminal generates an interface to display the received report according to the user's emotional state.

[0699] Step 7:

[0700] Users review reports displayed on their devices and consider the suggested actions. They can also provide feedback from their devices as needed, requesting further improvements.

[0701] (Example 2)

[0702] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] Traditional data analysis systems analyze data without considering the user's emotional state and generate static reports, resulting in insufficient support for users to effectively understand information and make appropriate decisions. Furthermore, there is a need for mechanisms to efficiently standardize and clean data.

[0704] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0705] In this invention, the server includes means for acquiring large-scale data including geographic location information from multiple information sources, means for standardizing and purifying the acquired data, means for automatically estimating potential relationships from the data using artificial intelligence technology, means for distributing reports to a display device, and means for dynamically adjusting the display of the generated report based on the user's emotional state. This makes it possible to provide personalized reports that take into account the user's emotions.

[0706] A "data source" is a system or platform that supplies data from an external source.

[0707] "Geographic location information" refers to information used to identify a place or location within data.

[0708] A "large-scale dataset" is a dataset containing a vast amount of information.

[0709] "Standardization" is the process of unifying data formats into a consistent form.

[0710] "Purification" is the process of removing noise and unwanted elements from data.

[0711] "Artificial intelligence technology" refers to technologies that use machine learning and natural language processing to analyze data and gain insights.

[0712] "Relevance" refers to the correlation or causal relationship between different data points.

[0713] A "report" is a document that summarizes the results of an analysis and is a collection of information provided to the user.

[0714] A "display device" is hardware used to visually present data and information to a user.

[0715] "Dynamic adjustment" refers to the process of changing the content and format in real time according to the situation and conditions.

[0716] This invention is a data analysis system that utilizes a server and terminals. The server acquires large-scale data, including geographical location information, from multiple information sources. This includes data acquisition via APIs from cloud services and online databases. For example, it is possible to acquire user location information and behavioral data from social media platforms.

[0717] Next, the server standardizes the acquired data to unify the data format. During this process, data cleaning is also performed to remove noise and duplicate information. For example, the Python Pandas library can be used to efficiently process the data.

[0718] Subsequently, the server uses artificial intelligence technology, specifically generative AI models, to automatically estimate potential relationships within the data. This process utilizes machine learning algorithms to estimate causal relationships within the data. Specifically, libraries such as Scikit-learn and TensorFlow are used.

[0719] The generated analysis results are documented as a report. This report is dynamically displayed on the device based on the user's emotional state. This ensures that the report is delivered in a personalized way for each user, aiding their understanding. For example, if a user shows anxiety while viewing the report, the device will adjust to highlight information that alleviates that anxiety.

[0720] An example of a prompt might be, "Please provide recommended actions to alleviate the user's concerns about the new product." By inputting this prompt into the AI ​​model, it can generate specific action suggestions based on the user's emotions.

[0721] Users view this report through their device and make decisions based on the information provided. This allows them to receive support that takes their emotions into consideration, leading to a deeper understanding of the information and making more informed decisions. For example, when a user requests a review of a new product, the emotion engine can highlight positive feedback, potentially increasing the user's willingness to purchase.

[0722] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0723] Step 1:

[0724] The server acquires large-scale data, including geographical location information, from various data sources. This process involves collecting real-time data using APIs. The input is raw data obtained from the data sources, and the output is an integrated, large-scale dataset. Specifically, the server executes scheduled tasks and periodically accesses data sources to download essential data.

[0725] Step 2:

[0726] The server performs standardization and data purification on the acquired data. The input is a large, integrated dataset, and the output is a standardized, clean dataset free from noise and duplicates. This process includes specific actions such as unifying the data format, removing duplicates, and imputing missing values ​​using the Python Pandas library.

[0727] Step 3:

[0728] The server uses artificial intelligence techniques to estimate potential relationships in standardized data. The input is a clean dataset, and the output is an analysis result that includes the estimated relationships. In this process, generative AI models are utilized, and machine learning is performed using libraries such as Scikit-learn and TensorFlow. Specifically, prompt sentences are input to the AI ​​model, setting the task to "estimate the causal relationship between user behavior and emotion."

[0729] Step 4:

[0730] The server generates an analysis result as a report based on the estimated correlations. The input is the analysis result, and the output is a documented report. The server uses a template engine to output the report in PDF format, incorporating visualized graphs and charts.

[0731] Step 5:

[0732] The terminal delivers and displays the generated report to the user. The input is a documented report, and the output is a dynamically adjusted report displayed on the user's terminal. Upon receiving the report, the terminal evaluates the user's emotional state and performs specific actions to adjust the report's highlighting and layout based on that evaluation.

[0733] Step 6:

[0734] Users view reports displayed via their devices and make decisions based on the insights provided. The input is a dynamically adjusted report, and the output is the user's decision. Users interact with the device to find the information they need and interpret the data in a way that suits their own emotions.

[0735] (Application Example 2)

[0736] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] In today's commercial environment, it is crucial to offer products and services that take consumer emotions and interactions into consideration. However, conventional systems lack the ability to grasp consumers' emotional states in real time and dynamically present information accordingly. As a result, there are limitations to improving customer experience and increasing repeat purchase rates.

[0738] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0739] In this invention, the server includes means for acquiring a large-scale information set including location information from multiple external information sources, means for standardizing the format and cleaning the acquired information, and means for automatically inferring potential causal relationships from the information set using generative artificial intelligence. This makes it possible to present dynamically customized product suggestions and promotional information based on the consumer's emotional state.

[0740] "External information sources" refer to a collection of external data providers, databases, and other resources that a system uses to acquire information.

[0741] "Location information" refers to data that indicates a geographical location, and is used to pinpoint the precise geographical location of a user or device.

[0742] A "large-scale information collection" is an information resource that collects a vast amount of data, and it forms the basis for various analyses and processing.

[0743] "Format standardization" is the process of converting information in different formats into a consistent format to maintain the integrity of the information.

[0744] "Information cleansing" is a process of improving data quality by removing inaccurate or unnecessary information from a dataset.

[0745] "Generative artificial intelligence" refers to algorithms or programs that automatically generate new insights and causal relationships based on data.

[0746] "Latent causal relationships" refer to potential cause-and-effect relationships hidden within the data that are revealed through analysis.

[0747] "User emotions" refer to information that indicates the user's feelings and mood, and are used to adapt interfaces and services.

[0748] "Dynamic adjustment of displayed content" is a function that changes the information displayed in real time according to the user's state and environment.

[0749] An "analysis report" is a document or presentation format that summarizes the results of data analysis and is used to support decision-making.

[0750] In this embodiment, the server acquires a large set of information, including location data, from various external sources. This information may also include customer trends and purchase history. The server then performs formatting standardization and data cleansing on the acquired information. In this process, duplicate information is removed and missing values ​​are filled in to maintain data integrity. This improves data quality and yields reliable analysis results.

[0751] Next, the server uses generative artificial intelligence to automatically infer potential causal relationships from the collected information. In this analysis process, the AI ​​can generate new insights based on user interactions and purchase patterns.

[0752] The user's device can recognize their emotions in real time. Specifically, cameras and sensors are used to detect emotions from the user's facial expressions and voice, and this information is sent to a server. Based on this emotional data, the displayed content is dynamically adjusted, providing product recommendations and promotional information optimized for each individual user. This improves the consumer experience and increases convenience.

[0753] As a concrete example, if a customer in a physical store shows excitement in front of a new product, the terminal can offer special discount information related to that product. An example of a prompt message in this case would be, "If you feel excited when you see the new product, please show me discount information related to that product."

[0754] The hardware used includes devices such as smartphones and tablets, and the software utilizes emotion recognition APIs (e.g., Microsoft Azure Emotion API) and Python. This makes it possible to create a system that always provides the user with the most optimal information.

[0755] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0756] Step 1:

[0757] The server acquires a large collection of information, including location data, from various external sources. This information includes customer location data, purchase history, and sensor data. The server receives this information and stores it in a temporary database. The input consists of various data from external sources, and the output is raw data with no unified format.

[0758] Step 2:

[0759] The server performs formatting standardization and data cleaning on the acquired information. This process resolves data format inconsistencies, removes unnecessary duplicate data, and fills in missing values. Specifically, this is done using certain scripts or database queries. The input is unstandardized raw data, and the output is cleaned data.

[0760] Step 3:

[0761] The server uses generative artificial intelligence to automatically infer potential causal relationships from a cleaned data set. In this process, the AI ​​algorithm analyzes the correlations and patterns in the data and generates new causal insights. The input is cleaned data, and the output is an analytical report reflecting the causal relationships.

[0762] Step 4:

[0763] The device recognizes the user's emotions in real time via the user's camera and sensors. The recognized emotional data is sent to a server where it is used for analysis. The input is raw emotional data obtained from the user, and the output is the analyzed emotional state.

[0764] Step 5:

[0765] The server dynamically adjusts the displayed content based on the user's emotional state and delivers customized product recommendations and promotional information to the device. An AI model selects and displays appropriate information using prompts. Inputs are emotional state and analysis reports, while output is customized information presentation.

[0766] Step 6:

[0767] Users receive the presented information on their devices and enjoy an optimized shopping experience, which improves consumer satisfaction. The input is customized information received from the device, and the output is the user's experience and behavioral changes. Specific actions include making purchase decisions and changing the user's movement within the store.

[0768] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0769] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0770] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0771] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0772] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0773] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0774] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0775] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0776] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0777] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0778] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0779] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0780] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0781] 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.

[0782] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0783] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0784] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0785] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0786] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0787] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0788] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0789] The following is further disclosed regarding the embodiments described above.

[0790] (Claim 1)

[0791] A means of acquiring a large dataset including location data from multiple external data sources,

[0792] A means of performing format standardization and data cleaning on acquired data,

[0793] A means for automatically inferring potential causal relationships from the dataset using generative artificial intelligence,

[0794] A means for generating an analysis report based on inferred causal relationships,

[0795] A means of delivering and displaying the generated analysis report on a terminal,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, wherein the data cleaning includes removing duplicate data and imputing missing values.

[0799] (Claim 3)

[0800] The system according to claim 1, wherein the analysis report generation means includes means for performing visualization using a causal network model.

[0801] "Example 1"

[0802] (Claim 1)

[0803] A means for acquiring a large-scale information set including location information from multiple external information sources,

[0804] A means of standardizing the format and organizing the information obtained,

[0805] A means for automatically inferring potential causal relationships from the aforementioned information set using a generative machine learning model,

[0806] A means for generating analysis results based on inferred causal relationships,

[0807] A means of delivering and displaying the generated analysis results on a terminal,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, wherein the information organization includes the removal of duplicate information and the imputation of missing values.

[0811] (Claim 3)

[0812] The system according to claim 1, wherein the analysis result generation means includes means for performing visualization using a causal network model.

[0813] "Application Example 1"

[0814] (Claim 1)

[0815] A means for obtaining a large-scale information set including location information from multiple external sources,

[0816] A means of performing formatting standardization and information cleaning on acquired information,

[0817] A means for automatically inferring potential causal relationships from the aforementioned information set using generative AI,

[0818] A means for generating an analytical report based on inferred causal relationships,

[0819] A means for distributing and displaying the generated analysis report on an information processing device,

[0820] A means to verify the effectiveness of mobile advertising campaigns in real time,

[0821] Methods for analyzing the impact of advertising on purchasing behavior,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, wherein the information cleaning includes the removal of duplicate information and the completion of missing data.

[0825] (Claim 3)

[0826] The system according to claim 1, wherein the analysis report generation means includes means for performing visualization using a causal relationship model.

[0827] "Example 2 of combining an emotion engine"

[0828] (Claim 1)

[0829] A means of acquiring large-scale data including geographic location information from multiple sources,

[0830] A means of standardizing and purifying the acquired data,

[0831] A means for automatically estimating potential relationships from the aforementioned data using artificial intelligence technology,

[0832] Means for generating a report based on estimated relevance,

[0833] A means for dynamically adjusting the display of the generated report based on the user's emotional state,

[0834] A means of delivering the report to a display device,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, wherein the data purification includes reducing duplicate information and imputing missing values.

[0838] (Claim 3)

[0839] The system according to claim 1, wherein the report generation means includes means for performing visualization using a related model.

[0840] "Application example 2 of combining emotional engines"

[0841] (Claim 1)

[0842] A means for obtaining a large-scale information set including location information from multiple external sources,

[0843] Means for standardizing the format and cleaning the information obtained,

[0844] A means for automatically inferring potential causal relationships from the aforementioned information set using generative artificial intelligence,

[0845] A means for recognizing the user's emotions and dynamically adjusting the presented content based on the user's emotional state,

[0846] A means for generating an analysis report and delivering and displaying a customized report based on emotional state to a terminal,

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, wherein the cleaning of the information includes removing duplicate information and filling in missing values.

[0850] (Claim 3)

[0851] The system according to claim 1, wherein the analysis report generation means includes means for performing visualization using a causal relationship model. [Explanation of Symbols]

[0852] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring a large dataset including location data from multiple external data sources, A means of performing format standardization and data cleaning on acquired data, A means for automatically inferring potential causal relationships from the dataset using generative artificial intelligence, A means for generating an analysis report based on inferred causal relationships, A means of delivering and displaying the generated analysis report on a terminal, A system that includes this.

2. The system according to claim 1, wherein the data cleaning includes the removal of duplicate data and the imputation of missing values.

3. The system according to claim 1, wherein the analysis report generation means includes means for performing visualization using a causal network model.

Images