system

Abstract

We provide the system. [Solution] A means of collecting location information, social network data, and behavioral history from diverse data sources, A means of analyzing the aforementioned collected data to identify region-specific trends and individual interests, A means for generating advertisements and information based on the analysis results using a generative model, Means for distributing the generated information to the user's mobile terminal and electronic display device, A means for obtaining the user's response to the aforementioned information and reflecting it in the next information generation, 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 performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern advertising and information-providing systems, personalization according to regional characteristics and individual users' interests is insufficient, which is a problem. As a result, the relevance of information for users decreases, not only reducing the effectiveness of advertisements but also missing opportunities to activate the local economy and promote tourism.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a system that generates advertising and guidance information using a generative model based on location information, social network data, and behavioral history collected from diverse data sources, and delivers it to the user's mobile device or electronic display device. This enables the provision of dynamically adjusted information in real time based on the user's location and interests, improving advertising effectiveness and providing information that takes regional characteristics into account. Furthermore, by acquiring user responses and reflecting them in the generation of information in the future, more accurate personalization can be achieved.

[0006] A "data source" refers to the origin or provider of information used to collect it.

[0007] "Location information" refers to data that indicates the geographical location where a specific user or object is located.

[0008] "Social interaction network data" refers to data about posts and reactions collected from interactions between users on online platforms.

[0009] "Behavioral history" refers to a record of activities and choices a user has made in the past.

[0010] A "generative model" is a model that uses artificial intelligence to create new information based on input data.

[0011] "Advertising" refers to communication messages created to promote awareness and purchase of specific products or services.

[0012] "Information" refers to information that provides explanations or instructions regarding a specific region or service.

[0013] "User's mobile device" refers to an electronic device that utilizes mobile technology and is owned by an individual.

[0014] An "electronic display device" is a screen or device that can display information in digital form.

[0015] "User response" refers to the reaction or action shown by the user to the provided information.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the labeled 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.

[0020] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the labeled 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, and the like.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system for effectively providing users with advertising and guidance information tailored to regional characteristics. The main components of the system consist of data collection, analysis, generation, distribution, and feedback processes.

[0038] First, the server collects location information, social network data, and behavioral history from various data sources. This data can be obtained in real time via APIs or directly through applications. For example, it can retrieve a user's current location and social media posts in real time.

[0039] Next, the server analyzes this data to identify user interests, regional characteristics, and current trends. Using machine learning, it extracts useful patterns and insights from this data to identify trends in specific areas. For example, it might detect that "cafes" are rapidly gaining attention in a particular region.

[0040] Next, the server utilizes a generative model to generate advertisements and information based on the analysis results. This data generation model is tailored to provide the most relevant information according to the user's profile and situation. For example, it might generate an advertisement offering discounts at a specific cafe.

[0041] The server then distributes the generated information to the user's mobile device or electronic display device. This can be done using push notifications or digital signage, and the information is presented at the appropriate time based on the user's location. For example, when a user passes by a particular cafe, promotional information may be displayed on their smartphone.

[0042] Ultimately, users respond to the information provided, and their feedback is incorporated back into the system. User responses are used in subsequent data collection and ad generation processes to improve the system's accuracy. By analyzing user feedback, personalization is continuously improved.

[0043] In this way, this system provides advertising information tailored to the user's location and interests in real time, enabling effective marketing strategies that leverage local characteristics.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects information from a variety of data sources, including location data from the user's mobile device, data from social networking sites, and past behavioral history. It uses APIs to periodically retrieve social media posts and updates the data in real time.

[0047] Step 2:

[0048] The server analyzes the collected data using statistical analysis and machine learning models. It analyzes social media posts using natural language processing to extract local trends and popular keywords. It also identifies categories that users may be interested in based on their browsing history.

[0049] Step 3:

[0050] The server uses a generative model to generate advertisements and information tailored to the user's profile. Based on the analysis results, it selects the information most relevant to the user's interests and location, and creates appropriate messages.

[0051] Step 4:

[0052] The server delivers generated advertisements and information to the user's mobile device and electronic display device. Using geofencing technology, it uses push notifications as a trigger when the user approaches a specific location to provide location-related information in a timely manner.

[0053] Step 5:

[0054] Users respond to the information provided, for example by clicking on ads they are interested in. This feedback is sent to the server and used in the next ad generation process. User behavior data is re-evaluated to improve the accuracy and relevance of ads.

[0055] (Example 1)

[0056] 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."

[0057] In today's information-saturated society, users receive a vast amount of information, making it difficult to obtain accurate information based on their individual interests and concerns. Furthermore, the lack of information provision that takes regional characteristics into account hinders effective marketing activities.

[0058] 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.

[0059] In this invention, the server includes means for acquiring location information, communication network data, and behavioral history from various information sources; means for analyzing the acquired data to identify region-specific trends and individual interests; and means for generating public relations and information based on the analysis results using a generation module. This enables the provision of accurate information based on the user's location and interests.

[0060] "Diverse sources" refers to data provided from multiple different sources, including location-based devices, social media networks, and user activity history.

[0061] "Location information" is data that indicates a specific geographical location, which makes it possible to identify the user's current location and travel route.

[0062] "Network data" refers to information about interactions and relationships that users have with others through social networks.

[0063] "Activity history" refers to a record of actions taken by a user in the past, including places visited, services used, and online activities.

[0064] A "generative module" refers to a program or algorithm used to create new content or information based on data.

[0065] "Analysis results" refer to conclusions about trends and patterns in the data obtained through the analysis of collected data.

[0066] "Public relations and information" refers to messages and notifications that should be conveyed to users, including advertisements, and is based on the generated analysis results.

[0067] This invention is an information provision system based on regional characteristics, which analyzes data obtained from diverse information sources and provides users with highly relevant information. This system mainly consists of three main elements: a server, a terminal, and the user.

[0068] First, the server acquires location information, network data, and behavioral history data from various sources. This process utilizes software that collects data via APIs using communication technologies. The server implements machine learning algorithms to analyze this data, identifying the user's personal interests and regional characteristics. Specifically, the server can analyze data patterns to identify popular activities and locations in the area and grasp trends.

[0069] Next, the server utilizes a generative AI model to generate advertisements and information based on the analysis results. In this generation process, data-driven prompts are input into the AI ​​model. For example, using the prompt "Create discount information about newly opened cafes in a specific area," the AI ​​model generates relevant information. The generated information is customized according to the user's profile and surrounding circumstances, selecting the most relevant content.

[0070] Finally, the server delivers the generated information to the user's mobile device or visual display device. This delivery is done using push notifications or digital signage, taking the user's location into account and timing appropriately. For example, when a user passes near a particular cafe, the server sends promotional information about that cafe and displays a notification on their smartphone.

[0071] This system provides users with the information they need in a timely manner, creating a personalized experience and supporting effective marketing strategies tailored to local characteristics.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects data from diverse sources. It accepts location information, network data, and behavioral history as input. This data collection is performed in real time using APIs. The server integrates this data and outputs it as a standardized dataset. Specifically, it obtains the current location from GPS devices and collects user posts by calling social media APIs.

[0075] Step 2:

[0076] The server analyzes the collected data. Using an integrated dataset as input, it begins the analysis using machine learning algorithms. This process processes the data to identify regional trends and user interests, extracting key patterns. The output generates analysis results that reflect user interests and regional characteristics. Specifically, it identifies current trends through anomaly detection and analysis of frequently occurring words.

[0077] Step 3:

[0078] The server generates information using a generative AI model. It uses analysis results and prompt statements (such as "Create discount information about a newly opened cafe in a specific area") as input. The server inputs this data into the AI ​​model and generates advertisements and information tailored to the user's profile. The output is the generated customized information. Specifically, the AI ​​model constructs text and images according to the prompt statements.

[0079] Step 4:

[0080] The server distributes the generated information. It uses the generated information and the user's current location as input. The server sends the information to the user's mobile device or visual display device at the appropriate time via push notifications or digital signage. Output includes notifications and display information received by the user. Specifically, a notification is displayed on the user's smartphone when they approach a specific location.

[0081] Step 5:

[0082] The user responds to the information provided. Input includes notifications and displayed information. The user's response is an action (e.g., using a coupon or clicking a link). The output is user behavior data, which is then re-entered into the system. Specifically, if a coupon is used within the app, that data is used for subsequent analysis.

[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] Providing effective and timely advertising and information tailored to local needs and individual interests is crucial in modern marketing. However, the challenge lies in how to analyze data collected from diverse sources and generate and deliver dynamic advertisements based on user location and interests. In particular, technology for providing real-time, location-appropriate notifications when users are in a specific area remains insufficient.

[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 collecting location data, social interaction network data, and movement history from various information sources; means for analyzing the collected data to identify regional characteristics and individual interests; and means for generating sales promotion information and guidance information based on the analysis results using a generation algorithm. This makes it possible to provide users with region-specific information and advertisements based on their personal interests in an effective and timely manner.

[0088] "Information source" refers to the underlying source or platform from which data is obtained.

[0089] "Location data" refers to information that indicates the geographical location where the user is currently located.

[0090] "Social interaction network data" refers to information that shows how users interact with others online.

[0091] "Location history" is a record of places a user has visited in the past.

[0092] "Analysis" is the process of examining collected data in detail to find meaning and relationships.

[0093] "Regional characteristics" refer to distinctive trends and cultural elements in a particular geographical area.

[0094] "Personal interests" refer to the things or areas that individual users find particularly interesting or exciting.

[0095] A "generation algorithm" is a set of calculation procedures used to create advertisements and informational materials based on input data.

[0096] "Sales promotion information" refers to promotional content designed to encourage the purchase of products or services.

[0097] "Guidance information" refers to information that provides users with necessary directions and service overviews.

[0098] An "electronic display medium" is a device or apparatus that provides information to users in a visible form through digital means.

[0099] "Dynamic adjustment" refers to changing and optimizing information in real time according to the user's current situation.

[0100] The system that realizes this invention consists of a server and a user terminal. The server collects location data, social interaction network data, and movement history from various sources. This data is collected through APIs and direct connections, and tracks user behavior and location in real time. The server analyzes this data and uses machine learning algorithms to identify regional characteristics and individual interests. This analysis extracts useful patterns from the data by using frameworks such as TENSORFLOW®.

[0101] Using a generation algorithm, the server generates sales promotion and information based on the analysis results. The generated information is immediately delivered to the user's mobile device. On the user's terminal, an application developed using React Native receives the information and displays it to the user as a notification. For example, when a user is visiting a specific area, it is possible to notify them of the latest sales information and discount coupons for that area. This notification is dynamically adjusted based on the user's location and interests.

[0102] Furthermore, the user's response to the presented information is sent back to the server and used to improve accuracy in subsequent data collection and information generation processes. Through the analysis of user feedback, the system's personalization is continuously improved. For example, when a user visits a cafe, they can receive notifications about new promotions and services at that cafe. Additionally, by utilizing a generative AI model, it is possible to generate accurate advertisements based on instructions such as the prompt "Generate information on popular cafes in the specified area and create notifications that effectively reach nearby users."

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server collects location data, social interaction network data, and movement history from APIs and sensors. Inputs include real-time location information and user SNS activity logs. This data is stored in a database. The output is raw data prepared for analysis.

[0106] Step 2:

[0107] The server analyzes the collected data. TensorFlow is used to apply a model to identify regional features and individual interests. The input is the raw data saved in the previous step. Each data point is extracted as a feature and analyzed by the model. The output is the analysis results, including user-specific interests and regional trends.

[0108] Step 3:

[0109] The server uses a generation algorithm to generate sales promotion and guidance information based on the analysis results. The prompt "Generate information on popular cafes in the specified area and create notifications that effectively reach nearby users" is input to the generation AI model. The input is the analysis results from step 2. The generated output is a customized advertising message for each user.

[0110] Step 4:

[0111] The server sends the generated information to the user's device. The React Native app implemented on the device notifies the user of this information. The input is the advertising message generated in step 3. The action to be performed is to display a push notification based on the user's current location. The output is the advertising notification received by the user.

[0112] Step 5:

[0113] Users can respond to notifications through their devices. This response is sent back to the server and used for subsequent data collection and ad generation processes. The input is the user's response data. The server analyzes the feedback received for future personalization. The output is an improved user model.

[0114] 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.

[0115] This invention is a system that collects location information, social network data, and behavioral history from various data sources and combines them with an emotion engine. This makes it possible to provide advertising and guidance information that takes into account the user's emotions.

[0116] First, the server collects location information via the user's mobile device and aggregates data from social networking sites and past activity history. This allows the server to understand the user's current situation and past activities. For example, it can identify events the user has attended and places they have visited based on their social media posts.

[0117] Next, the server uses an emotion engine to analyze the user's emotional state. This emotion engine can detect emotions from voice input and facial expressions captured using the device's camera. For example, it recognizes a positive emotional state when the user smiles at the camera.

[0118] Subsequently, the server uses a generative model to generate advertisements and information based on the collected data and sentiment analysis results. This generative model dynamically adjusts the content to match the user's current emotions. For example, if the user is expressing joy, it will provide event information that enhances their excitement and enjoyment.

[0119] The server also delivers the generated advertisements and information to the user's mobile device or electronic display device. Because personalization is performed based on emotional state, the information provided matches the user's mood, and a higher advertising effect can be expected. For example, a user passing by a cafe can be attracted by being shown new menu items that match their preferences and mood.

[0120] Finally, the user responds to the information provided, and this data is fed back into the system and used for future analysis and information generation. New emotional data is accumulated from the user's responses, continuously improving the overall personalization accuracy of the system.

[0121] In this way, by combining emotion recognition, this system achieves highly personalized information delivery that takes into account regional characteristics and individual emotional states.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server collects location information in real time from the user's mobile device. Using GPS functionality, it determines the user's current location and stores that information in a database.

[0125] Step 2:

[0126] The server uses APIs from social networking services to collect user activity data such as posts, comments, and likes. This allows for a detailed understanding of users' interests and behavioral patterns.

[0127] Step 3:

[0128] The device uses its built-in camera and microphone to capture the user's facial expressions and voice. This data is sent to an emotion engine to analyze the user's emotions.

[0129] Step 4:

[0130] The server analyzes emotional data, processed by the emotion engine, in combination with location information and social media data. Machine learning algorithms are used to identify the user's current emotional trends.

[0131] Step 5:

[0132] Based on the emotional state and behavioral information obtained in the previous stage, the server uses a generative model to generate personalized advertisements and information. This model is tuned to generate content that best appeals to the user's immediate emotions.

[0133] Step 6:

[0134] The server distributes the generated information to the user's mobile device and electronic display device. Based on the notification permissions set by the user, it sends advertisements via push notifications and display devices at timely intervals.

[0135] Step 7:

[0136] Users may show interest in or react to advertisements and information presented on their devices or display devices. This interaction data is continuously fed back to the server.

[0137] Step 8:

[0138] The server incorporates user feedback as training data for its emotion engine and generative models, improving the accuracy of future ads and information delivered. This cycle allows the system to constantly evolve, enabling it to provide a more highly personalized experience.

[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] This invention aims to solve the problem that conventional information provision systems do not adequately provide personalized information that takes into account the user's emotional state. Furthermore, it is necessary to improve advertising effectiveness and information usefulness by dynamically adjusting information based on the user's location and interests. In addition, there is a need for a mechanism that efficiently incorporates user feedback into future information generation.

[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 collecting geographic information, communication network data, and operation history from various information sources; means for using an emotion estimation device to analyze emotional states; and means for generating advertisements and information guidance based on the analysis results and emotional information using a generative model. This enables personalized information provision that takes into account the user's emotional state, and by dynamically adjusting information according to the user's interests and emotions, it becomes possible to achieve higher advertising effectiveness and user satisfaction.

[0144] "Information sources" refer to various sources that provide data for a specific purpose. These include sensors, social networking platforms, and user devices.

[0145] "Geographic information" refers to location data represented in digital format, which may include information related to a specific point or area.

[0146] "Network data" refers to information obtained as a result of users communicating with others through online platforms, and includes posted content and conversation history.

[0147] "Activity history" refers to a record of actions and events a specific person has performed in the past. This includes places visited and event participation history.

[0148] An "emotion estimation device" refers to software or hardware that analyzes a user's voice, facial expressions, text, etc., to infer their emotional state.

[0149] A "generative model" refers to an algorithm or system that generates new information or content based on collected data.

[0150] "Advertising and information provision" refers to advertising content and information presentations based on users' interests.

[0151] An "electronic display unit" refers to a digital device used to provide information visually, and includes display devices and monitors.

[0152] This invention provides a system that collects user location information, network data, and behavioral history from various information sources, and analyzes the user's emotional state using an emotion estimation device based on this information. This makes it possible to provide personalized advertisements and informational guidance to users.

[0153] The server uses the GPS function of the user's mobile device to obtain location information. It also collects network data such as the user's posts and conversation history from SNS applications installed on the device. User permission is required for this. Furthermore, it records the history of places the user has visited and events they have attended, and saves this as activity history.

[0154] The server transmits the collected location information and data to an emotion estimation device, which analyzes the user's voice and facial expressions. The emotion estimation device uses sensor data obtained from cameras and microphones to estimate the user's emotional state.

[0155] Subsequently, the server uses a generative AI model to dynamically generate advertisements and informational guidance based on the analysis results and emotional information. This generative AI model can create content that responds to the collected data and the user's emotional state. For example, a prompt such as "Generate suitable spot information if the user is currently excited" is used.

[0156] The generated information is distributed from the server to the user's mobile device and electronic display unit. The device presents the information to the user as push notifications or in-app messages. This information is personalized based on the user's interests and emotions, and is tailored to their specific location and real-time emotional state. For example, if the user is expressing joy, information about nearby festivals and events will be provided.

[0157] Ultimately, users respond to the information they receive, and this response data is fed back to the server. This feedback data is used to improve future information generation and enhance the user experience.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The server obtains location information from the device. This input includes geographic coordinate data obtained via a GPS sensor. The server analyzes this data to determine the user's real-time location. Specifically, the server works with a map database to map the user's location onto a map.

[0161] Step 2:

[0162] The server collects network data from the terminal. With the user's permission, this data includes posting history and conversation content from social networking platforms. The server analyzes this data using natural language processing algorithms to extract the user's interests. Specifically, text analysis is performed, taking into account keyword frequency and context.

[0163] Step 3:

[0164] The server simultaneously acquires emotion data from the emotion estimation device. The input here consists of facial expressions and voice data obtained through the camera and microphone installed in the device. The server analyzes this sensor data using an emotion estimation algorithm to identify the user's emotional state. For example, if a smile is detected using image recognition technology, it is output as a positive emotion.

[0165] Step 4:

[0166] The server inputs the outputs from steps 1, 2, and 3 into the generating AI model, which then generates advertisements and informational guidance based on the prompt. Specifically, the generating AI model receives prompts such as "Suggest suitable leisure facilities if the user is excited," and dynamically generates relevant content.

[0167] Step 5:

[0168] The server distributes the generated information to the terminal and the electronic display unit. Here, the generated advertisements and informational announcements are output, and the terminal displays this information to the user as a push notification. Specifically, the terminal's display shows "information about a music festival being held nearby."

[0169] Step 6:

[0170] Users respond to the information provided. Their clicks and participation serve as input, and this response data is sent to the server as feedback. The server stores this feedback data in a database to help with future information analysis and generation. Specifically, if a user clicks on event information to view details, this indicates interest and is reflected in future personalized content.

[0171] (Application Example 2)

[0172] 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".

[0173] In today's world, consumers receive vast amounts of information through diverse media, but because this information is not appropriately customized to individual emotional states and interests, it is becoming increasingly difficult to capture their attention. In this context, a system is needed that enables the provision of information tailored to consumers' emotions and individual interests. Furthermore, a key challenge is to improve consumer satisfaction by providing appropriate information based on emotional states in real time.

[0174] 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.

[0175] In this invention, the server includes means for collecting location information, social network data, and behavioral history from various data sources; means for analyzing the user's facial expression data using an emotion engine and detecting their emotional state; and means for generating advertising and guidance information based on the analysis results and emotional state using a generative model. This enables the provision of dynamic information tailored to the user's emotions and interests.

[0176] "Diverse data sources" refer to multiple different sources of information, including location information, social network data, and behavioral history.

[0177] "Location information" refers to geographical information that shows the user's current location and past travel history.

[0178] "Social interaction network data" refers to information about posts and activities made by users on online platforms.

[0179] "Behavioral history" refers to data that shows what actions a user has taken in the past, including places visited and events attended.

[0180] An "emotion engine" is software that has the ability to analyze a user's emotional state from their facial expressions and voice.

[0181] A "generative model" is an AI-based algorithm that dynamically creates personalized advertisements and information using collected data and analysis results.

[0182] "Advertising and informational content" refers to commercial messages and useful information provided to users that are tailored to their individual emotional state and interests.

[0183] An "information processing device" is a digital device owned by a user, including smartphones and tablets.

[0184] An "electronic display device" is an output device used to display generated information.

[0185] "User response" refers to a user's actions or feedback regarding the information provided.

[0186] In this invention, a server plays a central role in collecting and analyzing various information to realize a system that provides advertisements and guidance information tailored to the user's emotions and interests.

[0187] The server first obtains location information from the user's information processing device and aggregates the user's behavioral history and posting data via the social network. This makes it possible to comprehensively understand the user's current situation and past activities.

[0188] Next, the server uses an emotion engine to analyze the user's facial expressions and voice data collected through the information processing device's camera and microphone to identify their current emotional state. The emotion engine has the ability to quickly classify emotions using AI technology and provide corresponding feedback.

[0189] Based on this data and analysis results, the server uses a generative AI model to dynamically generate advertisements and information optimized for the user's emotions and interests. The generated information is then adjusted based on the user's emotional state and current location to enhance its relevance.

[0190] Finally, the server transmits the generated content to an information processing device or electronic display device for display to the user. The user may then decide on an action based on this information, and the user's feedback will be used to improve future information generation.

[0191] As a concrete example, if the emotion engine detects a relaxed state from a user's facial expression as they pass a cafe in a city, the server generates an advertisement related to the cafe's special menu and delivers it directly to the information processing device. The user is more likely to react positively to the advertisement and stop by the cafe.

[0192] An example of a prompt for a generative AI model is a question like, "How are you feeling today? Generate recommended ads for the user based on their emotional data and location." This allows the system to enrich the user's individual experience.

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

[0194] Step 1:

[0195] The server obtains location information from the user's information processing device. It collects the user's location data as input and obtains geographical coordinate information as output. The information processing device utilizes a GPS sensor to transmit the user's real-time location to the server.

[0196] Step 2:

[0197] The server collects user activity history and posting data from social networking sites via APIs. It uses user posting data from SNS platforms as input and aggregates users' past activity history as output. The server analyzes this data to generate foundational information for identifying trends and interests.

[0198] Step 3:

[0199] The server acquires the user's facial expressions and voice via the camera and microphone of the information processing device, and analyzes them using an emotion engine. Facial expression data and voice data are used as input. The emotion engine analyzes this data and identifies the user's emotional state as output. The server stores the analysis results from the emotion engine and uses them to generate advertisements.

[0200] Step 4:

[0201] The server uses a generative AI model to generate advertisements and guidance information based on collected location data, behavioral history, and emotional state. As input, prompt text is passed to the generative AI model based on data obtained in the previous step, and customized advertisements are generated as output. The AI ​​model adjusts the generated content to suit the user's situation.

[0202] Step 5:

[0203] The server transmits generated advertisements and informational data to an electronic display device or information processing device and presents it to the user. It sends generated advertising data as input and displays it on the user's digital device as output. The device provides appropriate notifications to attract the user's attention.

[0204] Step 6:

[0205] The server retrieves data from users who respond to advertisements and promotional information. It collects user response data as input and stores feedback information as output. The server uses this feedback to improve the accuracy of future advertisement generation.

[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] This invention is a system for effectively providing users with advertising and guidance information tailored to regional characteristics. The main components of the system consist of data collection, analysis, generation, distribution, and feedback processes.

[0223] First, the server collects location information, social network data, and behavioral history from various data sources. This data can be obtained in real time via APIs or directly through applications. For example, it can retrieve a user's current location and social media posts in real time.

[0224] Next, the server analyzes this data to identify user interests, regional characteristics, and current trends. Using machine learning, it extracts useful patterns and insights from this data to identify trends in specific areas. For example, it might detect that "cafes" are rapidly gaining attention in a particular region.

[0225] Next, the server utilizes a generative model to generate advertisements and information based on the analysis results. This data generation model is tailored to provide the most relevant information according to the user's profile and situation. For example, it might generate an advertisement offering discounts at a specific cafe.

[0226] The server then distributes the generated information to the user's mobile device or electronic display device. This can be done using push notifications or digital signage, and the information is presented at the appropriate time based on the user's location. For example, when a user passes by a particular cafe, promotional information may be displayed on their smartphone.

[0227] Ultimately, users respond to the information provided, and their feedback is incorporated back into the system. User responses are used in subsequent data collection and ad generation processes to improve the system's accuracy. By analyzing user feedback, personalization is continuously improved.

[0228] In this way, this system provides advertising information tailored to the user's location and interests in real time, enabling effective marketing strategies that leverage local characteristics.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The server collects information from a variety of data sources, including location data from the user's mobile device, data from social networking sites, and past behavioral history. It uses APIs to periodically retrieve social media posts and updates the data in real time.

[0232] Step 2:

[0233] The server analyzes the collected data using statistical analysis and machine learning models. It analyzes social media posts using natural language processing to extract local trends and popular keywords. It also identifies categories that users may be interested in based on their browsing history.

[0234] Step 3:

[0235] The server uses a generative model to generate advertisements and information tailored to the user's profile. Based on the analysis results, it selects the information most relevant to the user's interests and location, and creates appropriate messages.

[0236] Step 4:

[0237] The server delivers generated advertisements and information to the user's mobile device and electronic display device. Using geofencing technology, it uses push notifications as a trigger when the user approaches a specific location to provide location-related information in a timely manner.

[0238] Step 5:

[0239] Users respond to the information provided, for example by clicking on ads they are interested in. This feedback is sent to the server and used in the next ad generation process. User behavior data is re-evaluated to improve the accuracy and relevance of ads.

[0240] (Example 1)

[0241] 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."

[0242] In today's information-saturated society, users receive a vast amount of information, making it difficult to obtain accurate information based on their individual interests and concerns. Furthermore, the lack of information provision that takes regional characteristics into account hinders effective marketing activities.

[0243] 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.

[0244] In this invention, the server includes means for acquiring location information, communication network data, and behavioral history from various information sources; means for analyzing the acquired data to identify region-specific trends and individual interests; and means for generating public relations and information based on the analysis results using a generation module. This enables the provision of accurate information based on the user's location and interests.

[0245] "Diverse sources" refers to data provided from multiple different sources, including location-based devices, social media networks, and user activity history.

[0246] "Location information" is data that indicates a specific geographical location, which makes it possible to identify the user's current location and travel route.

[0247] "Network data" refers to information about interactions and relationships that users have with others through social networks.

[0248] "Activity history" refers to a record of actions taken by a user in the past, including places visited, services used, and online activities.

[0249] A "generative module" refers to a program or algorithm used to create new content or information based on data.

[0250] "Analysis results" refer to conclusions about trends and patterns in the data obtained through the analysis of collected data.

[0251] "Public relations and information" refers to messages and notifications that should be conveyed to users, including advertisements, and is based on the generated analysis results.

[0252] This invention is an information provision system based on regional characteristics, which analyzes data obtained from diverse information sources and provides users with highly relevant information. This system mainly consists of three main elements: a server, a terminal, and the user.

[0253] First, the server acquires location information, network data, and behavioral history data from various sources. This process utilizes software that collects data via APIs using communication technologies. The server implements machine learning algorithms to analyze this data, identifying the user's personal interests and regional characteristics. Specifically, the server can analyze data patterns to identify popular activities and locations in the area and grasp trends.

[0254] Next, the server utilizes a generative AI model to generate advertisements and information based on the analysis results. In this generation process, data-driven prompts are input into the AI ​​model. For example, using the prompt "Create discount information about newly opened cafes in a specific area," the AI ​​model generates relevant information. The generated information is customized according to the user's profile and surrounding circumstances, selecting the most relevant content.

[0255] Finally, the server delivers the generated information to the user's mobile device or visual display device. This delivery is done using push notifications or digital signage, taking the user's location into account and timing appropriately. For example, when a user passes near a particular cafe, the server sends promotional information about that cafe and displays a notification on their smartphone.

[0256] This system provides users with the information they need in a timely manner, creating a personalized experience and supporting effective marketing strategies tailored to local characteristics.

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

[0258] Step 1:

[0259] The server collects data from diverse sources. It accepts location information, network data, and behavioral history as input. This data collection is performed in real time using APIs. The server integrates this data and outputs it as a standardized dataset. Specifically, it obtains the current location from GPS devices and collects user posts by calling social media APIs.

[0260] Step 2:

[0261] The server analyzes the collected data. Using an integrated dataset as input, it begins the analysis using machine learning algorithms. This process processes the data to identify regional trends and user interests, extracting key patterns. The output generates analysis results that reflect user interests and regional characteristics. Specifically, it identifies current trends through anomaly detection and analysis of frequently occurring words.

[0262] Step 3:

[0263] The server generates information using a generative AI model. It uses analysis results and prompt statements (such as "Create discount information about a newly opened cafe in a specific area") as input. The server inputs this data into the AI ​​model and generates advertisements and information tailored to the user's profile. The output is the generated customized information. Specifically, the AI ​​model constructs text and images according to the prompt statements.

[0264] Step 4:

[0265] The server distributes the generated information. It uses the generated information and the user's current location as input. The server sends the information to the user's mobile device or visual display device at the appropriate time via push notifications or digital signage. Output includes notifications and display information received by the user. Specifically, a notification is displayed on the user's smartphone when they approach a specific location.

[0266] Step 5:

[0267] The user responds to the information provided. Input includes notifications and displayed information. The user's response is an action (e.g., using a coupon or clicking a link). The output is user behavior data, which is then re-entered into the system. Specifically, if a coupon is used within the app, that data is used for subsequent analysis.

[0268] (Application Example 1)

[0269] 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."

[0270] Providing effective and timely advertising and information tailored to local needs and individual interests is crucial in modern marketing. However, the challenge lies in how to analyze data collected from diverse sources and generate and deliver dynamic advertisements based on user location and interests. In particular, technology for providing real-time, location-appropriate notifications when users are in a specific area remains insufficient.

[0271] 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.

[0272] In this invention, the server includes means for collecting location data, social interaction network data, and movement history from various information sources; means for analyzing the collected data to identify regional characteristics and individual interests; and means for generating sales promotion information and guidance information based on the analysis results using a generation algorithm. This makes it possible to provide users with region-specific information and advertisements based on their personal interests in an effective and timely manner.

[0273] "Information source" refers to the underlying source or platform from which data is obtained.

[0274] "Location data" refers to information that indicates the geographical location where the user is currently located.

[0275] "Social interaction network data" refers to information that shows how users interact with others online.

[0276] "Location history" is a record of places a user has visited in the past.

[0277] "Analysis" is the process of examining collected data in detail to find meaning and relationships.

[0278] "Regional characteristics" refer to distinctive trends and cultural elements in a particular geographical area.

[0279] "Personal interest" refers to matters or areas in which individual users feel particular interest or excitement.

[0280] "Generation algorithm" is a computational procedure for creating advertisements and guidance information based on the input data.

[0281] "Sales promotion information" is the promotional content for promoting the purchase of products and services.

[0282] "Guidance information" is information that provides users with necessary route guidance and an overview of services.

[0283] "Electronic display medium" is a device or apparatus that provides information to users in a visible form by digital means.

[0284] "Dynamically adjust" refers to changing and optimizing information in real time according to the current situation of the user.

[0285] The system for realizing this invention is composed of a server and user terminals. The server collects location data, social interaction network data, and movement history from various information sources. These data are collected through APIs or direct connections to track the actions and locations of users in real time. The server analyzes this data and uses machine learning algorithms to identify regional characteristics and personal interests. For this analysis, frameworks such as TensorFlow are used to extract useful patterns from the data.

[0286] Using the generation algorithm, the server generates sales promotion information and guidance information based on the analysis results. The generated information is immediately delivered to the user's mobile device. On the user terminal, an application developed using React Native receives the information and displays it to the user as a notification. For example, when the user visits a specific area, it is possible to notify the user of the latest sales information and discount coupons in that area. This notification is dynamically adjusted based on the user's location and interests.

[0287] Also, the response made by the user to the presented information is sent back to the server again and utilized to improve the accuracy in the next data collection and information generation process. Through the analysis of user feedback, the personalization of the system is continuously improved. As a specific example, for instance, when the user visits a café, the user can receive notifications about new promotions and services at the café. Additionally, by leveraging the generation AI model, it is possible to generate accurate advertisements based on the instruction of the prompt sentence "Generate popular café information in the specified area and create notifications that can effectively reach nearby users."

[0288] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] The server collects location data, social interaction network data, and movement history from APIs and sensors. The inputs include real-time location information and the user's SNS activity logs. These data are stored in a database. The output is the raw data prepared for analysis. <(

[0291] Step 2:

[0292] The server analyzes the collected data. TensorFlow is used to apply a model to identify regional features and individual interests. The input is the raw data saved in the previous step. Each data point is extracted as a feature and analyzed by the model. The output is the analysis results, including user-specific interests and regional trends.

[0293] Step 3:

[0294] The server uses a generation algorithm to generate sales promotion and guidance information based on the analysis results. The prompt "Generate information on popular cafes in the specified area and create notifications that effectively reach nearby users" is input to the generation AI model. The input is the analysis results from step 2. The generated output is a customized advertising message for each user.

[0295] Step 4:

[0296] The server sends the generated information to the user's device. The React Native app implemented on the device notifies the user of this information. The input is the advertising message generated in step 3. The action to be performed is to display a push notification based on the user's current location. The output is the advertising notification received by the user.

[0297] Step 5:

[0298] Users can respond to notifications through their devices. This response is sent back to the server and used for subsequent data collection and ad generation processes. The input is the user's response data. The server analyzes the feedback received for future personalization. The output is an improved user model.

[0299] 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.

[0300] This invention is a system that collects location information, social network data, and behavioral history from various data sources and combines them with an emotion engine. This makes it possible to provide advertising and guidance information that takes into account the user's emotions.

[0301] First, the server collects location information via the user's mobile device and aggregates data from social networking sites and past activity history. This allows the server to understand the user's current situation and past activities. For example, it can identify events the user has attended and places they have visited based on their social media posts.

[0302] Next, the server uses an emotion engine to analyze the user's emotional state. This emotion engine can detect emotions from voice input and facial expressions captured using the device's camera. For example, it recognizes a positive emotional state when the user smiles at the camera.

[0303] Subsequently, the server uses a generative model to generate advertisements and information based on the collected data and sentiment analysis results. This generative model dynamically adjusts the content to match the user's current emotions. For example, if the user is expressing joy, it will provide event information that enhances their excitement and enjoyment.

[0304] The server also delivers the generated advertisements and information to the user's mobile device or electronic display device. Because personalization is performed based on emotional state, the information provided matches the user's mood, and a higher advertising effect can be expected. For example, a user passing by a cafe can be attracted by being shown new menu items that match their preferences and mood.

[0305] Finally, the user responds to the information provided, and this data is fed back into the system and used for future analysis and information generation. New emotional data is accumulated from the user's responses, continuously improving the overall personalization accuracy of the system.

[0306] In this way, by combining emotion recognition, this system realizes highly personalized information provision that takes into account regional characteristics and individual emotional states.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] The server collects location information in real time from the user's mobile terminal. Using the GPS function, the server identifies the user's current location and accumulates the information in the database.

[0310] Step 2:

[0311] The server uses the API of the social communication network to collect activity data such as the user's posts, comments, and likes. This enables detailed understanding of the user's interests and behavior patterns.

[0312] Step 3:

[0313] The terminal uses the built-in camera and microphone to capture the user's expressions and voice. These data are sent to the emotion engine to analyze the user's emotions.

[0314] Step 4:

[0315] The server analyzes the emotion data analyzed by the emotion engine in combination with the location information and SNS data. Using machine learning algorithms, the server identifies the user's current emotion trend.

[0316] Step 5:

[0317] Based on the emotional state and behavioral information obtained in the previous stage, the server uses a generative model to generate personalized advertisements and information. This model is tuned to generate content that best appeals to the user's immediate emotions.

[0318] Step 6:

[0319] The server distributes the generated information to the user's mobile device and electronic display device. Based on the notification permissions set by the user, it sends advertisements via push notifications and display devices at timely intervals.

[0320] Step 7:

[0321] Users may show interest in or react to advertisements and information presented on their devices or display devices. This interaction data is continuously fed back to the server.

[0322] Step 8:

[0323] The server incorporates user feedback as training data for its emotion engine and generative models, improving the accuracy of future ads and information delivered. This cycle allows the system to constantly evolve, enabling it to provide a more highly personalized experience.

[0324] (Example 2)

[0325] 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".

[0326] This invention aims to solve the problem that conventional information provision systems do not adequately provide personalized information that takes into account the user's emotional state. Furthermore, it is necessary to improve advertising effectiveness and information usefulness by dynamically adjusting information based on the user's location and interests. In addition, there is a need for a mechanism that efficiently incorporates user feedback into future information generation.

[0327] 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.

[0328] In this invention, the server includes means for collecting geographic information, communication network data, and operation history from various information sources; means for using an emotion estimation device to analyze emotional states; and means for generating advertisements and information guidance based on the analysis results and emotional information using a generative model. This enables personalized information provision that takes into account the user's emotional state, and by dynamically adjusting information according to the user's interests and emotions, it becomes possible to achieve higher advertising effectiveness and user satisfaction.

[0329] "Information sources" refer to various sources that provide data for a specific purpose. These include sensors, social networking platforms, and user devices.

[0330] "Geographic information" refers to location data represented in digital format, which may include information related to a specific point or area.

[0331] "Network data" refers to information obtained as a result of users communicating with others through online platforms, and includes posted content and conversation history.

[0332] "Activity history" refers to a record of actions and events a specific person has performed in the past. This includes places visited and event participation history.

[0333] An "emotion estimation device" refers to software or hardware that analyzes a user's voice, facial expressions, text, etc., to infer their emotional state.

[0334] A "generative model" refers to an algorithm or system that generates new information or content based on collected data.

[0335] "Advertising and information provision" refers to advertising content and information presentations based on users' interests.

[0336] An "electronic display unit" refers to a digital device used to provide information visually, and includes display devices and monitors.

[0337] This invention provides a system that collects user location information, network data, and behavioral history from various information sources, and analyzes the user's emotional state using an emotion estimation device based on this information. This makes it possible to provide personalized advertisements and informational guidance to users.

[0338] The server uses the GPS function of the user's mobile device to obtain location information. It also collects network data such as the user's posts and conversation history from SNS applications installed on the device. User permission is required for this. Furthermore, it records the history of places the user has visited and events they have attended, and saves this as activity history.

[0339] The server transmits the collected location information and data to an emotion estimation device, which analyzes the user's voice and facial expressions. The emotion estimation device uses sensor data obtained from cameras and microphones to estimate the user's emotional state.

[0340] Subsequently, the server uses a generative AI model to dynamically generate advertisements and informational guidance based on the analysis results and emotional information. This generative AI model can create content that responds to the collected data and the user's emotional state. For example, a prompt such as "Generate suitable spot information if the user is currently excited" is used.

[0341] The generated information is distributed from the server to the user's mobile device and electronic display unit. The device presents the information to the user as push notifications or in-app messages. This information is personalized based on the user's interests and emotions, and is tailored to their specific location and real-time emotional state. For example, if the user is expressing joy, information about nearby festivals and events will be provided.

[0342] Ultimately, users respond to the information they receive, and this response data is fed back to the server. This feedback data is used to improve future information generation and enhance the user experience.

[0343] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0344] Step 1:

[0345] The server obtains location information from the device. This input includes geographic coordinate data obtained via a GPS sensor. The server analyzes this data to determine the user's real-time location. Specifically, the server works with a map database to map the user's location onto a map.

[0346] Step 2:

[0347] The server collects network data from the terminal. With the user's permission, this data includes posting history and conversation content from social networking platforms. The server analyzes this data using natural language processing algorithms to extract the user's interests. Specifically, text analysis is performed, taking into account keyword frequency and context.

[0348] Step 3:

[0349] The server simultaneously acquires emotion data from the emotion estimation device. The input here consists of facial expressions and voice data obtained through the camera and microphone installed in the device. The server analyzes this sensor data using an emotion estimation algorithm to identify the user's emotional state. For example, if a smile is detected using image recognition technology, it is output as a positive emotion.

[0350] Step 4:

[0351] The server inputs the outputs from steps 1, 2, and 3 into the generating AI model, which then generates advertisements and informational guidance based on the prompt. Specifically, the generating AI model receives prompts such as "Suggest suitable leisure facilities if the user is excited," and dynamically generates relevant content.

[0352] Step 5:

[0353] The server distributes the generated information to the terminal and the electronic display unit. Here, the generated advertisements and informational announcements are output, and the terminal displays this information to the user as a push notification. Specifically, the terminal's display shows "information about a music festival being held nearby."

[0354] Step 6:

[0355] Users respond to the information provided. Their clicks and participation serve as input, and this response data is sent to the server as feedback. The server stores this feedback data in a database to help with future information analysis and generation. Specifically, if a user clicks on event information to view details, this indicates interest and is reflected in future personalized content.

[0356] (Application Example 2)

[0357] 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."

[0358] In today's world, consumers receive vast amounts of information through diverse media, but because this information is not appropriately customized to individual emotional states and interests, it is becoming increasingly difficult to capture their attention. In this context, a system is needed that enables the provision of information tailored to consumers' emotions and individual interests. Furthermore, a key challenge is to improve consumer satisfaction by providing appropriate information based on emotional states in real time.

[0359] 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.

[0360] In this invention, the server includes means for collecting location information, social network data, and behavioral history from various data sources; means for analyzing the user's facial expression data using an emotion engine and detecting their emotional state; and means for generating advertising and guidance information based on the analysis results and emotional state using a generative model. This enables the provision of dynamic information tailored to the user's emotions and interests.

[0361] "Diverse data sources" refer to multiple different sources of information, including location information, social network data, and behavioral history.

[0362] "Location information" refers to geographical information that shows the user's current location and past travel history.

[0363] "Social interaction network data" refers to information about posts and activities made by users on online platforms.

[0364] "Behavioral history" refers to data that shows what actions a user has taken in the past, including places visited and events attended.

[0365] An "emotion engine" is software that has the ability to analyze a user's emotional state from their facial expressions and voice.

[0366] A "generative model" is an AI-based algorithm that dynamically creates personalized advertisements and information using collected data and analysis results.

[0367] "Advertising and informational content" refers to commercial messages and useful information provided to users that are tailored to their individual emotional state and interests.

[0368] An "information processing device" is a digital device owned by a user, including smartphones and tablets.

[0369] An "electronic display device" is an output device used to display generated information.

[0370] "User response" refers to a user's actions or feedback regarding the information provided.

[0371] In this invention, a server plays a central role in collecting and analyzing various information to realize a system that provides advertisements and guidance information tailored to the user's emotions and interests.

[0372] The server first obtains location information from the user's information processing device and aggregates the user's behavioral history and posting data via the social network. This makes it possible to comprehensively understand the user's current situation and past activities.

[0373] Next, the server uses an emotion engine to analyze the user's facial expressions and voice data collected through the information processing device's camera and microphone to identify their current emotional state. The emotion engine has the ability to quickly classify emotions using AI technology and provide corresponding feedback.

[0374] Based on this data and analysis results, the server uses a generative AI model to dynamically generate advertisements and information optimized for the user's emotions and interests. The generated information is then adjusted based on the user's emotional state and current location to enhance its relevance.

[0375] Finally, the server transmits the generated content to an information processing device or electronic display device for display to the user. The user may then decide on an action based on this information, and the user's feedback will be used to improve future information generation.

[0376] As a concrete example, if the emotion engine detects a relaxed state from a user's facial expression as they pass a cafe in a city, the server generates an advertisement related to the cafe's special menu and delivers it directly to the information processing device. The user is more likely to react positively to the advertisement and stop by the cafe.

[0377] An example of a prompt for a generative AI model is a question like, "How are you feeling today? Generate recommended ads for the user based on their emotional data and location." This allows the system to enrich the user's individual experience.

[0378] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0379] Step 1:

[0380] The server obtains location information from the user's information processing device. It collects the user's location data as input and obtains geographical coordinate information as output. The information processing device utilizes a GPS sensor to transmit the user's real-time location to the server.

[0381] Step 2:

[0382] The server collects user activity history and posting data from social networking sites via APIs. It uses user posting data from SNS platforms as input and aggregates users' past activity history as output. The server analyzes this data to generate foundational information for identifying trends and interests.

[0383] Step 3:

[0384] The server acquires the user's facial expressions and voice via the camera and microphone of the information processing device, and analyzes them using an emotion engine. Facial expression data and voice data are used as input. The emotion engine analyzes this data and identifies the user's emotional state as output. The server stores the analysis results from the emotion engine and uses them to generate advertisements.

[0385] Step 4:

[0386] The server uses a generative AI model to generate advertisements and guidance information based on collected location data, behavioral history, and emotional state. As input, prompt text is passed to the generative AI model based on data obtained in the previous step, and customized advertisements are generated as output. The AI ​​model adjusts the generated content to suit the user's situation.

[0387] Step 5:

[0388] The server transmits generated advertisements and informational data to an electronic display device or information processing device and presents it to the user. It sends generated advertising data as input and displays it on the user's digital device as output. The device provides appropriate notifications to attract the user's attention.

[0389] Step 6:

[0390] The server retrieves data from users who respond to advertisements and promotional information. It collects user response data as input and stores feedback information as output. The server uses this feedback to improve the accuracy of future advertisement generation.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] [Third Embodiment]

[0395] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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".

[0407] This invention is a system for effectively providing users with advertising and guidance information tailored to regional characteristics. The main components of the system consist of data collection, analysis, generation, distribution, and feedback processes.

[0408] First, the server collects location information, social network data, and behavioral history from various data sources. This data can be obtained in real time via APIs or directly through applications. For example, it can retrieve a user's current location and social media posts in real time.

[0409] Next, the server analyzes this data to identify user interests, regional characteristics, and current trends. Using machine learning, it extracts useful patterns and insights from this data to identify trends in specific areas. For example, it might detect that "cafes" are rapidly gaining attention in a particular region.

[0410] Next, the server utilizes a generative model to generate advertisements and information based on the analysis results. This data generation model is tailored to provide the most relevant information according to the user's profile and situation. For example, it might generate an advertisement offering discounts at a specific cafe.

[0411] The server then distributes the generated information to the user's mobile device or electronic display device. This can be done using push notifications or digital signage, and the information is presented at the appropriate time based on the user's location. For example, when a user passes by a particular cafe, promotional information may be displayed on their smartphone.

[0412] Ultimately, users respond to the information provided, and their feedback is incorporated back into the system. User responses are used in subsequent data collection and ad generation processes to improve the system's accuracy. By analyzing user feedback, personalization is continuously improved.

[0413] In this way, this system provides advertising information tailored to the user's location and interests in real time, enabling effective marketing strategies that leverage local characteristics.

[0414] The following describes the processing flow.

[0415] Step 1:

[0416] The server collects information from a variety of data sources, including location data from the user's mobile device, data from social networking sites, and past behavioral history. It uses APIs to periodically retrieve social media posts and updates the data in real time.

[0417] Step 2:

[0418] The server analyzes the collected data using statistical analysis and machine learning models. It analyzes social media posts using natural language processing to extract local trends and popular keywords. It also identifies categories that users may be interested in based on their browsing history.

[0419] Step 3:

[0420] The server uses a generative model to generate advertisements and information tailored to the user's profile. Based on the analysis results, it selects the information most relevant to the user's interests and location, and creates appropriate messages.

[0421] Step 4:

[0422] The server delivers generated advertisements and information to the user's mobile device and electronic display device. Using geofencing technology, it uses push notifications as a trigger when the user approaches a specific location to provide location-related information in a timely manner.

[0423] Step 5:

[0424] Users respond to the information provided, for example by clicking on ads they are interested in. This feedback is sent to the server and used in the next ad generation process. User behavior data is re-evaluated to improve the accuracy and relevance of ads.

[0425] (Example 1)

[0426] 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."

[0427] In today's information-saturated society, users receive a vast amount of information, making it difficult to obtain accurate information based on their individual interests and concerns. Furthermore, the lack of information provision that takes regional characteristics into account hinders effective marketing activities.

[0428] 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.

[0429] In this invention, the server includes means for acquiring location information, communication network data, and behavioral history from various information sources; means for analyzing the acquired data to identify region-specific trends and individual interests; and means for generating public relations and information based on the analysis results using a generation module. This enables the provision of accurate information based on the user's location and interests.

[0430] "Diverse sources" refers to data provided from multiple different sources, including location-based devices, social media networks, and user activity history.

[0431] "Location information" is data that indicates a specific geographical location, which makes it possible to identify the user's current location and travel route.

[0432] "Network data" refers to information about interactions and relationships that users have with others through social networks.

[0433] "Activity history" refers to a record of actions taken by a user in the past, including places visited, services used, and online activities.

[0434] A "generative module" refers to a program or algorithm used to create new content or information based on data.

[0435] "Analysis results" refer to conclusions about trends and patterns in the data obtained through the analysis of collected data.

[0436] "Public relations and information" refers to messages and notifications that should be conveyed to users, including advertisements, and is based on the generated analysis results.

[0437] This invention is an information provision system based on regional characteristics, which analyzes data obtained from diverse information sources and provides users with highly relevant information. This system mainly consists of three main elements: a server, a terminal, and the user.

[0438] First, the server acquires location information, network data, and behavioral history data from various sources. This process utilizes software that collects data via APIs using communication technologies. The server implements machine learning algorithms to analyze this data, identifying the user's personal interests and regional characteristics. Specifically, the server can analyze data patterns to identify popular activities and locations in the area and grasp trends.

[0439] Next, the server utilizes a generative AI model to generate advertisements and information based on the analysis results. In this generation process, data-driven prompts are input into the AI ​​model. For example, using the prompt "Create discount information about newly opened cafes in a specific area," the AI ​​model generates relevant information. The generated information is customized according to the user's profile and surrounding circumstances, selecting the most relevant content.

[0440] Finally, the server delivers the generated information to the user's mobile device or visual display device. This delivery is done using push notifications or digital signage, taking the user's location into account and timing appropriately. For example, when a user passes near a particular cafe, the server sends promotional information about that cafe and displays a notification on their smartphone.

[0441] This system provides users with the information they need in a timely manner, creating a personalized experience and supporting effective marketing strategies tailored to local characteristics.

[0442] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0443] Step 1:

[0444] The server collects data from diverse sources. It accepts location information, network data, and behavioral history as input. This data collection is performed in real time using APIs. The server integrates this data and outputs it as a standardized dataset. Specifically, it obtains the current location from GPS devices and collects user posts by calling social media APIs.

[0445] Step 2:

[0446] The server analyzes the collected data. Using an integrated dataset as input, it begins the analysis using machine learning algorithms. This process processes the data to identify regional trends and user interests, extracting key patterns. The output generates analysis results that reflect user interests and regional characteristics. Specifically, it identifies current trends through anomaly detection and analysis of frequently occurring words.

[0447] Step 3:

[0448] The server generates information using a generative AI model. It uses analysis results and prompt statements (such as "Create discount information about a newly opened cafe in a specific area") as input. The server inputs this data into the AI ​​model and generates advertisements and information tailored to the user's profile. The output is the generated customized information. Specifically, the AI ​​model constructs text and images according to the prompt statements.

[0449] Step 4:

[0450] The server distributes the generated information. It uses the generated information and the user's current location as input. The server sends the information to the user's mobile device or visual display device at the appropriate time via push notifications or digital signage. Output includes notifications and display information received by the user. Specifically, a notification is displayed on the user's smartphone when they approach a specific location.

[0451] Step 5:

[0452] The user responds to the information provided. Input includes notifications and displayed information. The user's response is an action (e.g., using a coupon or clicking a link). The output is user behavior data, which is then re-entered into the system. Specifically, if a coupon is used within the app, that data is used for subsequent analysis.

[0453] (Application Example 1)

[0454] 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."

[0455] Providing effective and timely advertising and information tailored to local needs and individual interests is crucial in modern marketing. However, the challenge lies in how to analyze data collected from diverse sources and generate and deliver dynamic advertisements based on user location and interests. In particular, technology for providing real-time, location-appropriate notifications when users are in a specific area remains insufficient.

[0456] 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.

[0457] In this invention, the server includes means for collecting location data, social interaction network data, and movement history from various information sources; means for analyzing the collected data to identify regional characteristics and individual interests; and means for generating sales promotion information and guidance information based on the analysis results using a generation algorithm. This makes it possible to provide users with region-specific information and advertisements based on their personal interests in an effective and timely manner.

[0458] "Information source" refers to the underlying source or platform from which data is obtained.

[0459] "Location data" refers to information that indicates the geographical location where the user is currently located.

[0460] "Social interaction network data" refers to information that shows how users interact with others online.

[0461] "Location history" is a record of places a user has visited in the past.

[0462] "Analysis" is the process of examining collected data in detail to find meaning and relationships.

[0463] "Regional characteristics" refer to distinctive trends and cultural elements in a particular geographical area.

[0464] "Personal interests" refer to the things or areas that individual users find particularly interesting or exciting.

[0465] A "generation algorithm" is a set of calculation procedures used to create advertisements and informational materials based on input data.

[0466] "Sales promotion information" refers to promotional content designed to encourage the purchase of products or services.

[0467] "Guidance information" refers to information that provides users with necessary directions and service overviews.

[0468] An "electronic display medium" is a device or apparatus that provides information to users in a visible form through digital means.

[0469] "Dynamic adjustment" refers to changing and optimizing information in real time according to the user's current situation.

[0470] The system that realizes this invention consists of a server and a user terminal. The server collects location data, social interaction network data, and movement history from various sources. This data is collected through APIs and direct connections, and tracks user behavior and location in real time. The server analyzes this data and uses machine learning algorithms to identify regional characteristics and individual interests. This analysis uses frameworks such as TensorFlow to extract useful patterns from the data.

[0471] Using a generation algorithm, the server generates sales promotion and information based on the analysis results. The generated information is immediately delivered to the user's mobile device. On the user's terminal, an application developed using React Native receives the information and displays it to the user as a notification. For example, when a user is visiting a specific area, it is possible to notify them of the latest sales information and discount coupons for that area. This notification is dynamically adjusted based on the user's location and interests.

[0472] Furthermore, the user's response to the presented information is sent back to the server and used to improve accuracy in subsequent data collection and information generation processes. Through the analysis of user feedback, the system's personalization is continuously improved. For example, when a user visits a cafe, they can receive notifications about new promotions and services at that cafe. Additionally, by utilizing a generative AI model, it is possible to generate accurate advertisements based on instructions such as the prompt "Generate information on popular cafes in the specified area and create notifications that effectively reach nearby users."

[0473] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0474] Step 1:

[0475] The server collects location data, social interaction network data, and movement history from APIs and sensors. Inputs include real-time location information and user SNS activity logs. This data is stored in a database. The output is raw data prepared for analysis.

[0476] Step 2:

[0477] The server analyzes the collected data. TensorFlow is used to apply a model to identify regional features and individual interests. The input is the raw data saved in the previous step. Each data point is extracted as a feature and analyzed by the model. The output is the analysis results, including user-specific interests and regional trends.

[0478] Step 3:

[0479] The server uses a generation algorithm to generate sales promotion and guidance information based on the analysis results. The prompt "Generate information on popular cafes in the specified area and create notifications that effectively reach nearby users" is input to the generation AI model. The input is the analysis results from step 2. The generated output is a customized advertising message for each user.

[0480] Step 4:

[0481] The server sends the generated information to the user's device. The React Native app implemented on the device notifies the user of this information. The input is the advertising message generated in step 3. The action to be performed is to display a push notification based on the user's current location. The output is the advertising notification received by the user.

[0482] Step 5:

[0483] Users can respond to notifications through their devices. This response is sent back to the server and used for subsequent data collection and ad generation processes. The input is the user's response data. The server analyzes the feedback received for future personalization. The output is an improved user model.

[0484] 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.

[0485] This invention is a system that collects location information, social network data, and behavioral history from various data sources and combines them with an emotion engine. This makes it possible to provide advertising and guidance information that takes into account the user's emotions.

[0486] First, the server collects location information via the user's mobile device and aggregates data from social networking sites and past activity history. This allows the server to understand the user's current situation and past activities. For example, it can identify events the user has attended and places they have visited based on their social media posts.

[0487] Next, the server uses an emotion engine to analyze the user's emotional state. This emotion engine can detect emotions from voice input and facial expressions captured using the device's camera. For example, it recognizes a positive emotional state when the user smiles at the camera.

[0488] Subsequently, the server uses a generative model to generate advertisements and information based on the collected data and sentiment analysis results. This generative model dynamically adjusts the content to match the user's current emotions. For example, if the user is expressing joy, it will provide event information that enhances their excitement and enjoyment.

[0489] The server also delivers the generated advertisements and information to the user's mobile device or electronic display device. Because personalization is performed based on emotional state, the information provided matches the user's mood, and a higher advertising effect can be expected. For example, a user passing by a cafe can be attracted by being shown new menu items that match their preferences and mood.

[0490] Finally, the user responds to the information provided, and this data is fed back into the system and used for future analysis and information generation. New emotional data is accumulated from the user's responses, continuously improving the overall personalization accuracy of the system.

[0491] In this way, by combining emotion recognition, this system achieves highly personalized information delivery that takes into account regional characteristics and individual emotional states.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] The server collects location information in real time from the user's mobile device. Using GPS functionality, it determines the user's current location and stores that information in a database.

[0495] Step 2:

[0496] The server uses APIs from social networking services to collect user activity data such as posts, comments, and likes. This allows for a detailed understanding of users' interests and behavioral patterns.

[0497] Step 3:

[0498] The device uses its built-in camera and microphone to capture the user's facial expressions and voice. This data is sent to an emotion engine to analyze the user's emotions.

[0499] Step 4:

[0500] The server analyzes emotional data, processed by the emotion engine, in combination with location information and social media data. Machine learning algorithms are used to identify the user's current emotional trends.

[0501] Step 5:

[0502] Based on the emotional state and behavioral information obtained in the previous stage, the server uses a generative model to generate personalized advertisements and information. This model is tuned to generate content that best appeals to the user's immediate emotions.

[0503] Step 6:

[0504] The server distributes the generated information to the user's mobile device and electronic display device. Based on the notification permissions set by the user, it sends advertisements via push notifications and display devices at timely intervals.

[0505] Step 7:

[0506] Users may show interest in or react to advertisements and information presented on their devices or display devices. This interaction data is continuously fed back to the server.

[0507] Step 8:

[0508] The server incorporates user feedback as training data for its emotion engine and generative models, improving the accuracy of future ads and information delivered. This cycle allows the system to constantly evolve, enabling it to provide a more highly personalized experience.

[0509] (Example 2)

[0510] 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."

[0511] This invention aims to solve the problem that conventional information provision systems do not adequately provide personalized information that takes into account the user's emotional state. Furthermore, it is necessary to improve advertising effectiveness and information usefulness by dynamically adjusting information based on the user's location and interests. In addition, there is a need for a mechanism that efficiently incorporates user feedback into future information generation.

[0512] 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.

[0513] In this invention, the server includes means for collecting geographic information, communication network data, and operation history from various information sources; means for using an emotion estimation device to analyze emotional states; and means for generating advertisements and information guidance based on the analysis results and emotional information using a generative model. This enables personalized information provision that takes into account the user's emotional state, and by dynamically adjusting information according to the user's interests and emotions, it becomes possible to achieve higher advertising effectiveness and user satisfaction.

[0514] "Information sources" refer to various sources that provide data for a specific purpose. These include sensors, social networking platforms, and user devices.

[0515] "Geographic information" refers to location data represented in digital format, which may include information related to a specific point or area.

[0516] "Network data" refers to information obtained as a result of users communicating with others through online platforms, and includes posted content and conversation history.

[0517] "Activity history" refers to a record of actions and events a specific person has performed in the past. This includes places visited and event participation history.

[0518] An "emotion estimation device" refers to software or hardware that analyzes a user's voice, facial expressions, text, etc., to infer their emotional state.

[0519] A "generative model" refers to an algorithm or system that generates new information or content based on collected data.

[0520] "Advertising and information provision" refers to advertising content and information presentations based on users' interests.

[0521] An "electronic display unit" refers to a digital device used to provide information visually, and includes display devices and monitors.

[0522] This invention provides a system that collects user location information, network data, and behavioral history from various information sources, and analyzes the user's emotional state using an emotion estimation device based on this information. This makes it possible to provide personalized advertisements and informational guidance to users.

[0523] The server uses the GPS function of the user's mobile device to obtain location information. It also collects network data such as the user's posts and conversation history from SNS applications installed on the device. User permission is required for this. Furthermore, it records the history of places the user has visited and events they have attended, and saves this as activity history.

[0524] The server transmits the collected location information and data to an emotion estimation device, which analyzes the user's voice and facial expressions. The emotion estimation device uses sensor data obtained from cameras and microphones to estimate the user's emotional state.

[0525] Subsequently, the server uses a generative AI model to dynamically generate advertisements and informational guidance based on the analysis results and emotional information. This generative AI model can create content that responds to the collected data and the user's emotional state. For example, a prompt such as "Generate suitable spot information if the user is currently excited" is used.

[0526] The generated information is distributed from the server to the user's mobile device and electronic display unit. The device presents the information to the user as push notifications or in-app messages. This information is personalized based on the user's interests and emotions, and is tailored to their specific location and real-time emotional state. For example, if the user is expressing joy, information about nearby festivals and events will be provided.

[0527] Ultimately, users respond to the information they receive, and this response data is fed back to the server. This feedback data is used to improve future information generation and enhance the user experience.

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] The server obtains location information from the device. This input includes geographic coordinate data obtained via a GPS sensor. The server analyzes this data to determine the user's real-time location. Specifically, the server works with a map database to map the user's location onto a map.

[0531] Step 2:

[0532] The server collects network data from the terminal. With the user's permission, this data includes posting history and conversation content from social networking platforms. The server analyzes this data using natural language processing algorithms to extract the user's interests. Specifically, text analysis is performed, taking into account keyword frequency and context.

[0533] Step 3:

[0534] The server simultaneously acquires emotion data from the emotion estimation device. The input here consists of facial expressions and voice data obtained through the camera and microphone installed in the device. The server analyzes this sensor data using an emotion estimation algorithm to identify the user's emotional state. For example, if a smile is detected using image recognition technology, it is output as a positive emotion.

[0535] Step 4:

[0536] The server inputs the outputs from steps 1, 2, and 3 into the generating AI model, which then generates advertisements and informational guidance based on the prompt. Specifically, the generating AI model receives prompts such as "Suggest suitable leisure facilities if the user is excited," and dynamically generates relevant content.

[0537] Step 5:

[0538] The server distributes the generated information to the terminal and the electronic display unit. Here, the generated advertisements and informational announcements are output, and the terminal displays this information to the user as a push notification. Specifically, the terminal's display shows "information about a music festival being held nearby."

[0539] Step 6:

[0540] Users respond to the information provided. Their clicks and participation serve as input, and this response data is sent to the server as feedback. The server stores this feedback data in a database to help with future information analysis and generation. Specifically, if a user clicks on event information to view details, this indicates interest and is reflected in future personalized content.

[0541] (Application Example 2)

[0542] 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."

[0543] In today's world, consumers receive vast amounts of information through diverse media, but because this information is not appropriately customized to individual emotional states and interests, it is becoming increasingly difficult to capture their attention. In this context, a system is needed that enables the provision of information tailored to consumers' emotions and individual interests. Furthermore, a key challenge is to improve consumer satisfaction by providing appropriate information based on emotional states in real time.

[0544] 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.

[0545] In this invention, the server includes means for collecting location information, social network data, and behavioral history from various data sources; means for analyzing the user's facial expression data using an emotion engine and detecting their emotional state; and means for generating advertising and guidance information based on the analysis results and emotional state using a generative model. This enables the provision of dynamic information tailored to the user's emotions and interests.

[0546] "Diverse data sources" refer to multiple different sources of information, including location information, social network data, and behavioral history.

[0547] "Location information" refers to geographical information that shows the user's current location and past travel history.

[0548] "Social interaction network data" refers to information about posts and activities made by users on online platforms.

[0549] "Behavioral history" refers to data that shows what actions a user has taken in the past, including places visited and events attended.

[0550] An "emotion engine" is software that has the ability to analyze a user's emotional state from their facial expressions and voice.

[0551] A "generative model" is an AI-based algorithm that dynamically creates personalized advertisements and information using collected data and analysis results.

[0552] "Advertising and informational content" refers to commercial messages and useful information provided to users that are tailored to their individual emotional state and interests.

[0553] An "information processing device" is a digital device owned by a user, including smartphones and tablets.

[0554] An "electronic display device" is an output device used to display generated information.

[0555] "User response" refers to a user's actions or feedback regarding the information provided.

[0556] In this invention, a server plays a central role in collecting and analyzing various information to realize a system that provides advertisements and guidance information tailored to the user's emotions and interests.

[0557] The server first obtains location information from the user's information processing device and aggregates the user's behavioral history and posting data via the social network. This makes it possible to comprehensively understand the user's current situation and past activities.

[0558] Next, the server uses an emotion engine to analyze the user's facial expressions and voice data collected through the information processing device's camera and microphone to identify their current emotional state. The emotion engine has the ability to quickly classify emotions using AI technology and provide corresponding feedback.

[0559] Based on this data and analysis results, the server uses a generative AI model to dynamically generate advertisements and information optimized for the user's emotions and interests. The generated information is then adjusted based on the user's emotional state and current location to enhance its relevance.

[0560] Finally, the server transmits the generated content to an information processing device or electronic display device for display to the user. The user may then decide on an action based on this information, and the user's feedback will be used to improve future information generation.

[0561] As a concrete example, if the emotion engine detects a relaxed state from a user's facial expression as they pass a cafe in a city, the server generates an advertisement related to the cafe's special menu and delivers it directly to the information processing device. The user is more likely to react positively to the advertisement and stop by the cafe.

[0562] An example of a prompt for a generative AI model is a question like, "How are you feeling today? Generate recommended ads for the user based on their emotional data and location." This allows the system to enrich the user's individual experience.

[0563] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0564] Step 1:

[0565] The server obtains location information from the user's information processing device. It collects the user's location data as input and obtains geographical coordinate information as output. The information processing device utilizes a GPS sensor to transmit the user's real-time location to the server.

[0566] Step 2:

[0567] The server collects user activity history and posting data from social networking sites via APIs. It uses user posting data from SNS platforms as input and aggregates users' past activity history as output. The server analyzes this data to generate foundational information for identifying trends and interests.

[0568] Step 3:

[0569] The server acquires the user's facial expressions and voice via the camera and microphone of the information processing device, and analyzes them using an emotion engine. Facial expression data and voice data are used as input. The emotion engine analyzes this data and identifies the user's emotional state as output. The server stores the analysis results from the emotion engine and uses them to generate advertisements.

[0570] Step 4:

[0571] The server uses a generative AI model to generate advertisements and guidance information based on collected location data, behavioral history, and emotional state. As input, prompt text is passed to the generative AI model based on data obtained in the previous step, and customized advertisements are generated as output. The AI ​​model adjusts the generated content to suit the user's situation.

[0572] Step 5:

[0573] The server transmits generated advertisements and informational data to an electronic display device or information processing device and presents it to the user. It sends generated advertising data as input and displays it on the user's digital device as output. The device provides appropriate notifications to attract the user's attention.

[0574] Step 6:

[0575] The server retrieves data from users who respond to advertisements and promotional information. It collects user response data as input and stores feedback information as output. The server uses this feedback to improve the accuracy of future advertisement generation.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] [Fourth Embodiment]

[0580] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0581] 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.

[0582] 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).

[0583] 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.

[0584] 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.

[0585] 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).

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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".

[0593] This invention is a system for effectively providing users with advertising and guidance information tailored to regional characteristics. The main components of the system consist of data collection, analysis, generation, distribution, and feedback processes.

[0594] First, the server collects location information, social network data, and behavioral history from various data sources. This data can be obtained in real time via APIs or directly through applications. For example, it can retrieve a user's current location and social media posts in real time.

[0595] Next, the server analyzes this data to identify user interests, regional characteristics, and current trends. Using machine learning, it extracts useful patterns and insights from this data to identify trends in specific areas. For example, it might detect that "cafes" are rapidly gaining attention in a particular region.

[0596] Next, the server utilizes a generative model to generate advertisements and information based on the analysis results. This data generation model is tailored to provide the most relevant information according to the user's profile and situation. For example, it might generate an advertisement offering discounts at a specific cafe.

[0597] The server then distributes the generated information to the user's mobile device or electronic display device. This can be done using push notifications or digital signage, and the information is presented at the appropriate time based on the user's location. For example, when a user passes by a particular cafe, promotional information may be displayed on their smartphone.

[0598] Ultimately, users respond to the information provided, and their feedback is incorporated back into the system. User responses are used in subsequent data collection and ad generation processes to improve the system's accuracy. By analyzing user feedback, personalization is continuously improved.

[0599] In this way, this system provides advertising information tailored to the user's location and interests in real time, enabling effective marketing strategies that leverage local characteristics.

[0600] The following describes the processing flow.

[0601] Step 1:

[0602] The server collects information from a variety of data sources, including location data from the user's mobile device, data from social networking sites, and past behavioral history. It uses APIs to periodically retrieve social media posts and updates the data in real time.

[0603] Step 2:

[0604] The server analyzes the collected data using statistical analysis and machine learning models. It analyzes social media posts using natural language processing to extract local trends and popular keywords. It also identifies categories that users may be interested in based on their browsing history.

[0605] Step 3:

[0606] The server uses a generative model to generate advertisements and information tailored to the user's profile. Based on the analysis results, it selects the information most relevant to the user's interests and location, and creates appropriate messages.

[0607] Step 4:

[0608] The server delivers generated advertisements and information to the user's mobile device and electronic display device. Using geofencing technology, it uses push notifications as a trigger when the user approaches a specific location to provide location-related information in a timely manner.

[0609] Step 5:

[0610] Users respond to the information provided, for example by clicking on ads they are interested in. This feedback is sent to the server and used in the next ad generation process. User behavior data is re-evaluated to improve the accuracy and relevance of ads.

[0611] (Example 1)

[0612] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0613] In today's information-saturated society, users receive a vast amount of information, making it difficult to obtain accurate information based on their individual interests and concerns. Furthermore, the lack of information provision that takes regional characteristics into account hinders effective marketing activities.

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

[0615] In this invention, the server includes means for acquiring location information, communication network data, and behavioral history from various information sources; means for analyzing the acquired data to identify region-specific trends and individual interests; and means for generating public relations and information based on the analysis results using a generation module. This enables the provision of accurate information based on the user's location and interests.

[0616] "Diverse sources" refers to data provided from multiple different sources, including location-based devices, social media networks, and user activity history.

[0617] "Location information" is data that indicates a specific geographical location, which makes it possible to identify the user's current location and travel route.

[0618] "Network data" refers to information about interactions and relationships that users have with others through social networks.

[0619] "Activity history" refers to a record of actions taken by a user in the past, including places visited, services used, and online activities.

[0620] A "generative module" refers to a program or algorithm used to create new content or information based on data.

[0621] "Analysis results" refer to conclusions about trends and patterns in the data obtained through the analysis of collected data.

[0622] "Public relations and information" refers to messages and notifications that should be conveyed to users, including advertisements, and is based on the generated analysis results.

[0623] This invention is an information provision system based on regional characteristics, which analyzes data obtained from diverse information sources and provides users with highly relevant information. This system mainly consists of three main elements: a server, a terminal, and the user.

[0624] First, the server acquires location information, network data, and behavioral history data from various sources. This process utilizes software that collects data via APIs using communication technologies. The server implements machine learning algorithms to analyze this data, identifying the user's personal interests and regional characteristics. Specifically, the server can analyze data patterns to identify popular activities and locations in the area and grasp trends.

[0625] Next, the server utilizes a generative AI model to generate advertisements and information based on the analysis results. In this generation process, data-driven prompts are input into the AI ​​model. For example, using the prompt "Create discount information about newly opened cafes in a specific area," the AI ​​model generates relevant information. The generated information is customized according to the user's profile and surrounding circumstances, selecting the most relevant content.

[0626] Finally, the server delivers the generated information to the user's mobile device or visual display device. This delivery is done using push notifications or digital signage, taking the user's location into account and timing appropriately. For example, when a user passes near a particular cafe, the server sends promotional information about that cafe and displays a notification on their smartphone.

[0627] This system provides users with the information they need in a timely manner, creating a personalized experience and supporting effective marketing strategies tailored to local characteristics.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] The server collects data from diverse sources. It accepts location information, network data, and behavioral history as input. This data collection is performed in real time using APIs. The server integrates this data and outputs it as a standardized dataset. Specifically, it obtains the current location from GPS devices and collects user posts by calling social media APIs.

[0631] Step 2:

[0632] The server analyzes the collected data. Using an integrated dataset as input, it begins the analysis using machine learning algorithms. This process processes the data to identify regional trends and user interests, extracting key patterns. The output generates analysis results that reflect user interests and regional characteristics. Specifically, it identifies current trends through anomaly detection and analysis of frequently occurring words.

[0633] Step 3:

[0634] The server generates information using a generative AI model. It uses analysis results and prompt statements (such as "Create discount information about a newly opened cafe in a specific area") as input. The server inputs this data into the AI ​​model and generates advertisements and information tailored to the user's profile. The output is the generated customized information. Specifically, the AI ​​model constructs text and images according to the prompt statements.

[0635] Step 4:

[0636] The server distributes the generated information. It uses the generated information and the user's current location as input. The server sends the information to the user's mobile device or visual display device at the appropriate time via push notifications or digital signage. Output includes notifications and display information received by the user. Specifically, a notification is displayed on the user's smartphone when they approach a specific location.

[0637] Step 5:

[0638] The user responds to the information provided. Input includes notifications and displayed information. The user's response is an action (e.g., using a coupon or clicking a link). The output is user behavior data, which is then re-entered into the system. Specifically, if a coupon is used within the app, that data is used for subsequent analysis.

[0639] (Application Example 1)

[0640] 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".

[0641] Providing effective and timely advertising and information tailored to local needs and individual interests is crucial in modern marketing. However, the challenge lies in how to analyze data collected from diverse sources and generate and deliver dynamic advertisements based on user location and interests. In particular, technology for providing real-time, location-appropriate notifications when users are in a specific area remains insufficient.

[0642] 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.

[0643] In this invention, the server includes means for collecting location data, social interaction network data, and movement history from various information sources; means for analyzing the collected data to identify regional characteristics and individual interests; and means for generating sales promotion information and guidance information based on the analysis results using a generation algorithm. This makes it possible to provide users with region-specific information and advertisements based on their personal interests in an effective and timely manner.

[0644] "Information source" refers to the underlying source or platform from which data is obtained.

[0645] "Location data" refers to information that indicates the geographical location where the user is currently located.

[0646] "Social interaction network data" refers to information that shows how users interact with others online.

[0647] "Location history" is a record of places a user has visited in the past.

[0648] "Analysis" is the process of examining collected data in detail to find meaning and relationships.

[0649] "Regional characteristics" refer to distinctive trends and cultural elements in a particular geographical area.

[0650] "Personal interests" refer to the things or areas that individual users find particularly interesting or exciting.

[0651] A "generation algorithm" is a set of calculation procedures used to create advertisements and informational materials based on input data.

[0652] "Sales promotion information" refers to promotional content designed to encourage the purchase of products or services.

[0653] "Guidance information" refers to information that provides users with necessary directions and service overviews.

[0654] An "electronic display medium" is a device or apparatus that provides information to users in a visible form through digital means.

[0655] "Dynamic adjustment" refers to changing and optimizing information in real time according to the user's current situation.

[0656] The system that realizes this invention consists of a server and a user terminal. The server collects location data, social interaction network data, and movement history from various sources. This data is collected through APIs and direct connections, and tracks user behavior and location in real time. The server analyzes this data and uses machine learning algorithms to identify regional characteristics and individual interests. This analysis uses frameworks such as TensorFlow to extract useful patterns from the data.

[0657] Using a generation algorithm, the server generates sales promotion and information based on the analysis results. The generated information is immediately delivered to the user's mobile device. On the user's terminal, an application developed using React Native receives the information and displays it to the user as a notification. For example, when a user is visiting a specific area, it is possible to notify them of the latest sales information and discount coupons for that area. This notification is dynamically adjusted based on the user's location and interests.

[0658] Furthermore, the user's response to the presented information is sent back to the server and used to improve accuracy in subsequent data collection and information generation processes. Through the analysis of user feedback, the system's personalization is continuously improved. For example, when a user visits a cafe, they can receive notifications about new promotions and services at that cafe. Additionally, by utilizing a generative AI model, it is possible to generate accurate advertisements based on instructions such as the prompt "Generate information on popular cafes in the specified area and create notifications that effectively reach nearby users."

[0659] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0660] Step 1:

[0661] The server collects location data, social interaction network data, and movement history from APIs and sensors. Inputs include real-time location information and user SNS activity logs. This data is stored in a database. The output is raw data prepared for analysis.

[0662] Step 2:

[0663] The server analyzes the collected data. TensorFlow is used to apply a model to identify regional features and individual interests. The input is the raw data saved in the previous step. Each data point is extracted as a feature and analyzed by the model. The output is the analysis results, including user-specific interests and regional trends.

[0664] Step 3:

[0665] The server uses a generation algorithm to generate sales promotion and guidance information based on the analysis results. The prompt "Generate information on popular cafes in the specified area and create notifications that effectively reach nearby users" is input to the generation AI model. The input is the analysis results from step 2. The generated output is a customized advertising message for each user.

[0666] Step 4:

[0667] The server sends the generated information to the user's device. The React Native app implemented on the device notifies the user of this information. The input is the advertising message generated in step 3. The action to be performed is to display a push notification based on the user's current location. The output is the advertising notification received by the user.

[0668] Step 5:

[0669] Users can respond to notifications through their devices. This response is sent back to the server and used for subsequent data collection and ad generation processes. The input is the user's response data. The server analyzes the feedback received for future personalization. The output is an improved user model.

[0670] 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.

[0671] This invention is a system that collects location information, social network data, and behavioral history from various data sources and combines them with an emotion engine. This makes it possible to provide advertising and guidance information that takes into account the user's emotions.

[0672] First, the server collects location information via the user's mobile device and aggregates data from social networking sites and past activity history. This allows the server to understand the user's current situation and past activities. For example, it can identify events the user has attended and places they have visited based on their social media posts.

[0673] Next, the server uses an emotion engine to analyze the user's emotional state. This emotion engine can detect emotions from voice input and facial expressions captured using the device's camera. For example, it recognizes a positive emotional state when the user smiles at the camera.

[0674] Subsequently, the server uses a generative model to generate advertisements and information based on the collected data and sentiment analysis results. This generative model dynamically adjusts the content to match the user's current emotions. For example, if the user is expressing joy, it will provide event information that enhances their excitement and enjoyment.

[0675] The server also delivers the generated advertisements and information to the user's mobile device or electronic display device. Because personalization is performed based on emotional state, the information provided matches the user's mood, and a higher advertising effect can be expected. For example, a user passing by a cafe can be attracted by being shown new menu items that match their preferences and mood.

[0676] Finally, the user responds to the information provided, and this data is fed back into the system and used for future analysis and information generation. New emotional data is accumulated from the user's responses, continuously improving the overall personalization accuracy of the system.

[0677] In this way, by combining emotion recognition, this system achieves highly personalized information delivery that takes into account regional characteristics and individual emotional states.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The server collects location information in real time from the user's mobile device. Using GPS functionality, it determines the user's current location and stores that information in a database.

[0681] Step 2:

[0682] The server uses APIs from social networking services to collect user activity data such as posts, comments, and likes. This allows for a detailed understanding of users' interests and behavioral patterns.

[0683] Step 3:

[0684] The device uses its built-in camera and microphone to capture the user's facial expressions and voice. This data is sent to an emotion engine to analyze the user's emotions.

[0685] Step 4:

[0686] The server analyzes emotional data, processed by the emotion engine, in combination with location information and social media data. Machine learning algorithms are used to identify the user's current emotional trends.

[0687] Step 5:

[0688] Based on the emotional state and behavioral information obtained in the previous stage, the server uses a generative model to generate personalized advertisements and information. This model is tuned to generate content that best appeals to the user's immediate emotions.

[0689] Step 6:

[0690] The server distributes the generated information to the user's mobile device and electronic display device. Based on the notification permissions set by the user, it sends advertisements via push notifications and display devices at timely intervals.

[0691] Step 7:

[0692] Users may show interest in or react to advertisements and information presented on their devices or display devices. This interaction data is continuously fed back to the server.

[0693] Step 8:

[0694] The server incorporates user feedback as training data for its emotion engine and generative models, improving the accuracy of future ads and information delivered. This cycle allows the system to constantly evolve, enabling it to provide a more highly personalized experience.

[0695] (Example 2)

[0696] 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".

[0697] This invention aims to solve the problem that conventional information provision systems do not adequately provide personalized information that takes into account the user's emotional state. Furthermore, it is necessary to improve advertising effectiveness and information usefulness by dynamically adjusting information based on the user's location and interests. In addition, there is a need for a mechanism that efficiently incorporates user feedback into future information generation.

[0698] 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.

[0699] In this invention, the server includes means for collecting geographic information, communication network data, and operation history from various information sources; means for using an emotion estimation device to analyze emotional states; and means for generating advertisements and information guidance based on the analysis results and emotional information using a generative model. This enables personalized information provision that takes into account the user's emotional state, and by dynamically adjusting information according to the user's interests and emotions, it becomes possible to achieve higher advertising effectiveness and user satisfaction.

[0700] "Information sources" refer to various sources that provide data for a specific purpose. These include sensors, social networking platforms, and user devices.

[0701] "Geographic information" refers to location data represented in digital format, which may include information related to a specific point or area.

[0702] "Network data" refers to information obtained as a result of users communicating with others through online platforms, and includes posted content and conversation history.

[0703] "Activity history" refers to a record of actions and events a specific person has performed in the past. This includes places visited and event participation history.

[0704] An "emotion estimation device" refers to software or hardware that analyzes a user's voice, facial expressions, text, etc., to infer their emotional state.

[0705] A "generative model" refers to an algorithm or system that generates new information or content based on collected data.

[0706] "Advertising and information provision" refers to advertising content and information presentations based on users' interests.

[0707] An "electronic display unit" refers to a digital device used to provide information visually, and includes display devices and monitors.

[0708] This invention provides a system that collects user location information, network data, and behavioral history from various information sources, and analyzes the user's emotional state using an emotion estimation device based on this information. This makes it possible to provide personalized advertisements and informational guidance to users.

[0709] The server uses the GPS function of the user's mobile device to obtain location information. It also collects network data such as the user's posts and conversation history from SNS applications installed on the device. User permission is required for this. Furthermore, it records the history of places the user has visited and events they have attended, and saves this as activity history.

[0710] The server transmits the collected location information and data to an emotion estimation device, which analyzes the user's voice and facial expressions. The emotion estimation device uses sensor data obtained from cameras and microphones to estimate the user's emotional state.

[0711] Subsequently, the server uses a generative AI model to dynamically generate advertisements and informational guidance based on the analysis results and emotional information. This generative AI model can create content that responds to the collected data and the user's emotional state. For example, a prompt such as "Generate suitable spot information if the user is currently excited" is used.

[0712] The generated information is distributed from the server to the user's mobile device and electronic display unit. The device presents the information to the user as push notifications or in-app messages. This information is personalized based on the user's interests and emotions, and is tailored to their specific location and real-time emotional state. For example, if the user is expressing joy, information about nearby festivals and events will be provided.

[0713] Ultimately, users respond to the information they receive, and this response data is fed back to the server. This feedback data is used to improve future information generation and enhance the user experience.

[0714] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0715] Step 1:

[0716] The server obtains location information from the device. This input includes geographic coordinate data obtained via a GPS sensor. The server analyzes this data to determine the user's real-time location. Specifically, the server works with a map database to map the user's location onto a map.

[0717] Step 2:

[0718] The server collects network data from the terminal. With the user's permission, this data includes posting history and conversation content from social networking platforms. The server analyzes this data using natural language processing algorithms to extract the user's interests. Specifically, text analysis is performed, taking into account keyword frequency and context.

[0719] Step 3:

[0720] The server simultaneously acquires emotion data from the emotion estimation device. The input here consists of facial expressions and voice data obtained through the camera and microphone installed in the device. The server analyzes this sensor data using an emotion estimation algorithm to identify the user's emotional state. For example, if a smile is detected using image recognition technology, it is output as a positive emotion.

[0721] Step 4:

[0722] The server inputs the outputs from steps 1, 2, and 3 into the generating AI model, which then generates advertisements and informational guidance based on the prompt. Specifically, the generating AI model receives prompts such as "Suggest suitable leisure facilities if the user is excited," and dynamically generates relevant content.

[0723] Step 5:

[0724] The server distributes the generated information to the terminal and the electronic display unit. Here, the generated advertisements and informational announcements are output, and the terminal displays this information to the user as a push notification. Specifically, the terminal's display shows "information about a music festival being held nearby."

[0725] Step 6:

[0726] Users respond to the information provided. Their clicks and participation serve as input, and this response data is sent to the server as feedback. The server stores this feedback data in a database to help with future information analysis and generation. Specifically, if a user clicks on event information to view details, this indicates interest and is reflected in future personalized content.

[0727] (Application Example 2)

[0728] 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".

[0729] In today's world, consumers receive vast amounts of information through diverse media, but because this information is not appropriately customized to individual emotional states and interests, it is becoming increasingly difficult to capture their attention. In this context, a system is needed that enables the provision of information tailored to consumers' emotions and individual interests. Furthermore, a key challenge is to improve consumer satisfaction by providing appropriate information based on emotional states in real time.

[0730] 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.

[0731] In this invention, the server includes means for collecting location information, social network data, and behavioral history from various data sources; means for analyzing the user's facial expression data using an emotion engine and detecting their emotional state; and means for generating advertising and guidance information based on the analysis results and emotional state using a generative model. This enables the provision of dynamic information tailored to the user's emotions and interests.

[0732] "Diverse data sources" refer to multiple different sources of information, including location information, social network data, and behavioral history.

[0733] "Location information" refers to geographical information that shows the user's current location and past travel history.

[0734] "Social interaction network data" refers to information about posts and activities made by users on online platforms.

[0735] "Behavioral history" refers to data that shows what actions a user has taken in the past, including places visited and events attended.

[0736] An "emotion engine" is software that has the ability to analyze a user's emotional state from their facial expressions and voice.

[0737] A "generative model" is an AI-based algorithm that dynamically creates personalized advertisements and information using collected data and analysis results.

[0738] "Advertising and informational content" refers to commercial messages and useful information provided to users that are tailored to their individual emotional state and interests.

[0739] An "information processing device" is a digital device owned by a user, including smartphones and tablets.

[0740] An "electronic display device" is an output device used to display generated information.

[0741] "User response" refers to a user's actions or feedback regarding the information provided.

[0742] In this invention, a server plays a central role in collecting and analyzing various information to realize a system that provides advertisements and guidance information tailored to the user's emotions and interests.

[0743] The server first obtains location information from the user's information processing device and aggregates the user's behavioral history and posting data via the social network. This makes it possible to comprehensively understand the user's current situation and past activities.

[0744] Next, the server uses an emotion engine to analyze the user's facial expressions and voice data collected through the information processing device's camera and microphone to identify their current emotional state. The emotion engine has the ability to quickly classify emotions using AI technology and provide corresponding feedback.

[0745] Based on this data and analysis results, the server uses a generative AI model to dynamically generate advertisements and information optimized for the user's emotions and interests. The generated information is then adjusted based on the user's emotional state and current location to enhance its relevance.

[0746] Finally, the server transmits the generated content to an information processing device or electronic display device for display to the user. The user may then decide on an action based on this information, and the user's feedback will be used to improve future information generation.

[0747] As a concrete example, if the emotion engine detects a relaxed state from a user's facial expression as they pass a cafe in a city, the server generates an advertisement related to the cafe's special menu and delivers it directly to the information processing device. The user is more likely to react positively to the advertisement and stop by the cafe.

[0748] An example of a prompt for a generative AI model is a question like, "How are you feeling today? Generate recommended ads for the user based on their emotional data and location." This allows the system to enrich the user's individual experience.

[0749] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0750] Step 1:

[0751] The server obtains location information from the user's information processing device. It collects the user's location data as input and obtains geographical coordinate information as output. The information processing device utilizes a GPS sensor to transmit the user's real-time location to the server.

[0752] Step 2:

[0753] The server collects user activity history and posting data from social networking sites via APIs. It uses user posting data from SNS platforms as input and aggregates users' past activity history as output. The server analyzes this data to generate foundational information for identifying trends and interests.

[0754] Step 3:

[0755] The server acquires the user's facial expressions and voice via the camera and microphone of the information processing device, and analyzes them using an emotion engine. Facial expression data and voice data are used as input. The emotion engine analyzes this data and identifies the user's emotional state as output. The server stores the analysis results from the emotion engine and uses them to generate advertisements.

[0756] Step 4:

[0757] The server uses a generative AI model to generate advertisements and guidance information based on collected location data, behavioral history, and emotional state. As input, prompt text is passed to the generative AI model based on data obtained in the previous step, and customized advertisements are generated as output. The AI ​​model adjusts the generated content to suit the user's situation.

[0758] Step 5:

[0759] The server transmits generated advertisements and informational data to an electronic display device or information processing device and presents it to the user. It sends generated advertising data as input and displays it on the user's digital device as output. The device provides appropriate notifications to attract the user's attention.

[0760] Step 6:

[0761] The server retrieves data from users who respond to advertisements and promotional information. It collects user response data as input and stores feedback information as output. The server uses this feedback to improve the accuracy of future advertisement generation.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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."

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] The following is further disclosed regarding the embodiments described above.

[0784] (Claim 1)

[0785] A means of collecting location information, social network data, and behavioral history from diverse data sources,

[0786] A means of analyzing the aforementioned collected data to identify region-specific trends and individual interests,

[0787] A means for generating advertisements and information based on the analysis results using a generative model,

[0788] Means for distributing the generated information to the user's mobile terminal and electronic display device,

[0789] A means for obtaining the user's response to the aforementioned information and reflecting it in the next information generation,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, wherein the generated advertisement is dynamically adjusted based on the user's location and interests.

[0793] (Claim 3)

[0794] The system according to claim 1, wherein the electronic display device receives user input and presents further information based on the input.

[0795] "Example 1"

[0796] (Claim 1)

[0797] Means for obtaining location information, communication network data, and behavioral history from diverse information sources,

[0798] A means of analyzing the acquired data to identify region-specific trends and individual interests,

[0799] A means for generating public relations and information based on the analysis results using a generation module,

[0800] Means for transmitting the generated information to the user's portable device and visual display device,

[0801] A means of collecting user reactions to the aforementioned information and utilizing them for future information generation,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, wherein the generated public announcement is dynamically adapted based on the user's location and interests.

[0805] (Claim 3)

[0806] The system according to claim 1, wherein the visual display device accepts user input and presents additional information based on the input.

[0807] "Application Example 1"

[0808] (Claim 1)

[0809] Means for collecting location data, social interaction network data, and movement history from diverse information sources,

[0810] A means of analyzing the aforementioned collected data to identify regional characteristics and individual interests,

[0811] A means for generating sales promotion information and guidance information based on the analysis results using a generation algorithm,

[0812] Means for transmitting the generated information to the user's mobile device and electronic display medium,

[0813] A means for obtaining the results of the user's response to the aforementioned information and applying them to the generation of the next information,

[0814] A means of providing users with timely notifications based on location information at specific points within a region,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, wherein the generated sales promotion information is dynamically adjusted based on the user's location and interests.

[0818] (Claim 3)

[0819] The system according to claim 1, wherein the electronic display medium accepts user input and presents additional information based on the input.

[0820] "Example 2 of combining an emotion engine"

[0821] (Claim 1)

[0822] Means for collecting geographic information, communication network data, and operational history from diverse information sources,

[0823] A means for analyzing the collected data to identify regional characteristics and individual preferences,

[0824] A means of using an emotion estimation device to analyze emotional states,

[0825] A means for generating advertisements and informational guidance based on the analysis results and emotional information using a generative model,

[0826] Means for distributing the generated information to the user's mobile communication device and electronic display unit,

[0827] A means of collecting user reactions to the aforementioned information and using them to improve future information generation,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, wherein the generated advertisement is dynamically adjusted based on the user's geographical information and preferences.

[0831] (Claim 3)

[0832] The system according to claim 1, wherein the electronic display unit accepts user input and presents additional information based on the input.

[0833] "Application example 2 when combining with an emotional engine"

[0834] (Claim 1)

[0835] A means of collecting location information, social network data, and behavioral history from diverse data sources,

[0836] A means of analyzing the aforementioned collected data to identify region-specific trends and individual interests,

[0837] A means of analyzing a user's facial expression data using an emotion engine to detect their emotional state,

[0838] A means for generating advertising and guidance information based on the analysis results and emotional state using a generative model,

[0839] Means for distributing the generated information to the user's information processing device and electronic display device,

[0840] A means for obtaining the user's response to the aforementioned information and reflecting it in the next information generation,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, wherein the generated advertisement is dynamically adjusted based on the user's location, interests, and emotional state.

[0844] (Claim 3)

[0845] The system according to claim 1, wherein the electronic display device receives user input and presents further information based on the input. [Explanation of symbols]

[0846] 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 collecting location information, social network data, and behavioral history from diverse data sources, A means of analyzing the aforementioned collected data to identify region-specific trends and individual interests, A means for generating advertisements and information based on the analysis results using a generative model, Means for distributing the generated information to the user's mobile terminal and electronic display device, A means for obtaining the user's response to the aforementioned information and reflecting it in the next information generation, A system that includes this.

2. The system according to claim 1, wherein the generated advertisement is dynamically adjusted based on the user's location and interests.

3. The system according to claim 1, wherein the electronic display device receives user input and presents further information based on the input.

Images