system

Abstract

We provide the system. [Solution] A means of automatically generating personalized information presentations based on information registered by businesses, A means for receiving location information and usage history information transmitted from a terminal, A means of analyzing acquired information and making personalized behavioral predictions, A means of delivering relevant notifications at the appropriate time based on the analysis results, A means of recording user reactions and feeding them back into analysis, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Individual entrepreneurs and small-scale businesses have difficulty conducting extensive advertising campaigns with large amounts of capital like large enterprises, and there is a problem of lacking effective approach means for specific individual customers. In addition, the creation of advertisements requires specialized knowledge and additional costs, which further burdens small-scale businesses. The problem to be solved by this invention is to enable small-scale businesses to appropriately reach individual customers at low cost and provide information based on interests.

Means for Solving the Problems

[0005] According to the present invention, a system is provided that automatically generates personalized information presentations using a generation AI based on information easily registered by businesses. This system receives location information and usage history from terminals, analyzes them, and makes individual behavior predictions. It delivers relevant notifications based on the analysis results at the appropriate time and further improves the advertising algorithm by recording user responses as feedback. This enables small businesses to provide personalized advertising at low cost and effectively.

[0006] "Information registered by businesses" refers to the content of websites and campaign details provided by small businesses and sole proprietors to contribute to their business activities.

[0007] "Personalized information presentation" refers to specific advertisements and notifications that are customized based on the user's interests and behavior.

[0008] A "device" refers to an electronic device such as a smartphone or tablet that a user carries with them, and information is sent and received through this device.

[0009] "Location information and usage history information" refers to data such as the user's current location and past application usage history.

[0010] "Behavioral prediction" refers to predicting the actions that a user is most likely to take in the future by analyzing their past behavioral data.

[0011] "Relevant notifications" refer to advertisements and information provided that are linked to the analyzed user's interests and behavior.

[0012] "Feeding back into analysis" refers to the process by which information systems accumulate data based on user responses to improve algorithms for behavioral prediction and ad delivery. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0016] In the following embodiments, a tagged 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.

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

[0018] In the following embodiments, a tagged 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.

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

[0020] 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."

[0021] [First Embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a system for small businesses to effectively deliver personalized advertising to customers with limited resources. Embodiments thereof are described below.

[0035] The server performs central processing and receives website content and campaign information that businesses have registered in advance. This information is stored as basic data for later generation of advertising content.

[0036] The device plays a role in routinely collecting the user's location information, payment history, and application usage history, and sending this data to a server. If a user frequently visits a particular location, that location information is used to identify the user's living area.

[0037] The server analyzes the received data to recognize user behavior patterns. For example, it analyzes places users frequently visit on holidays and predicts their interest in services related to those locations. This analysis allows for an automatic understanding of user interests.

[0038] Next, the server uses a generation AI to create personalized advertising content based on the analysis results. This process utilizes information registered by the business, including, for example, announcements of new products and promotions of services. This personalized information is then configured to be delivered to the user's smartphone at the appropriate time.

[0039] User responses to delivered advertisements are recorded on the device. The device acquires data such as click-through rates and ad viewing time, and sends this data to the server as feedback. This feedback information is used to improve the ad delivery algorithm.

[0040] For example, if a user frequently visits a particular cafe, the server can deliver advertisements for the cafe's new menu items to coincide with the user's next visit. In this case, the advertisements are optimized to attract the user's interest, taking into account their visit frequency and past payment history.

[0041] This invention enables small businesses to approach customers more efficiently and accurately.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The device collects the user's location information, app usage history, and payment history. This data is sent to the server as it is collected.

[0045] Step 2:

[0046] The server stores the data received from the terminal in a database. This allows for the storage of detailed activity history for each user.

[0047] Step 3:

[0048] The server analyzes accumulated data to predict user behavior patterns and interests. For example, it may analyze the tendency for users to visit the same store multiple times.

[0049] Step 4:

[0050] The server retrieves campaign information and website content registered by businesses and uses a generation AI to create user-optimized advertising content.

[0051] Step 5:

[0052] The server sends the generated ad content to the user's device at the optimal time. For example, it can be configured to notify the user of an ad when they enter a specific geographical area.

[0053] Step 6:

[0054] The user's device receives advertisements and records how the user reacts to them (clicks, viewing time, etc.).

[0055] Step 7:

[0056] The device sends recorded user response data to the server, which receives it as feedback.

[0057] Step 8:

[0058] The server uses the feedback information to improve its ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery.

[0059] (Example 1)

[0060] 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."

[0061] For small businesses, providing effective and personalized advertising to customers with limited resources is difficult. Existing systems struggle to deliver targeted ads based on user behavior patterns and lack feedback functions to evaluate ad effectiveness. As a result, there is a challenge in accurately delivering ads that attract user interest and continuously improving those ads.

[0062] 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.

[0063] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator; means for receiving location information and usage history information transmitted from the terminal; means for analyzing the acquired information, recognizing user behavior patterns, and making personalized behavior predictions; means for generating optimized advertising content using a generation AI model based on the analysis results; means for delivering the generated content at an appropriate time according to the user's situation; and means for recording user reactions and feeding them back into the analysis to improve the advertising delivery algorithm. This makes it possible for even small businesses to achieve effective and personalized advertising delivery with limited resources, and to further improve its accuracy.

[0064] "Information registered by businesses" refers to content and campaign information provided in advance by businesses conducting commercial activities, which the system uses to generate advertising content.

[0065] "Personalized information presentation" refers to advertisements and notifications that are created individually based on the user's behavioral data and registered information, and delivered to the user.

[0066] A "terminal" is an electronic device used to collect user location information, payment history, and application usage history, and to transmit this information to a server.

[0067] "Location information" refers to information that includes geographical data indicating that a user is located in a specific place.

[0068] "Usage history information" refers to data that includes a user's past behavioral history, payment history, and application usage history.

[0069] "Behavioral patterns" are the results of analyzing the regularity, consistency, and habits that indicate a user's daily actions and tendencies.

[0070] A "generative AI model" is an artificial intelligence system that automatically generates advertising content based on user behavior patterns and interests, using prior data learning.

[0071] "Advertising content" refers to media or messages that contain information about specific products or services and are created to attract the user's interest.

[0072] "User response" refers to behavioral data such as clicks and viewing time in response to advertisements and notifications.

[0073] An "ad delivery algorithm" is a computational method used to optimize the delivery of advertising content based on user data and responses.

[0074] This system aims to enable small businesses to effectively deliver personalized advertising with limited resources. The system analyzes users' behavioral patterns based on their location information and usage history in their daily lives, and generates advertising content using a generative AI model.

[0075] The server receives website content and campaign information registered in advance by the service provider and stores this information in a database. This information is used as basic data when generating advertisements. The device collects the user's location information using GPS functionality and also obtains payment history and application usage history. This data is necessary to understand the user's daily behavior.

[0076] The server analyzes the data sent from the terminal to recognize the user's behavior patterns. Based on these analysis results, the server uses a generative AI model to prepare prompts that create personalized advertising content. For example, a prompt could say, "Create an advertisement for an interesting new menu item at a cafe the user visits on their day off."

[0077] The generated advertising content is delivered to the device at the optimal time based on the user's location and usage history. By displaying ads on the screen based on location and time while the user is using their smartphone, a personalized advertising experience is provided.

[0078] For example, when a user is near a cafe they frequently visit, advertisements containing information about the cafe's new menu or discounts could be delivered to them in time for their next visit. In this way, advertisements optimized based on user behavior data can be delivered, enabling small businesses to attract customers more efficiently and supporting business growth.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The device acquires the user's daily location information using GPS functionality. The main process in this step is from the collection of location data to its transmission to the server. The input is GPS location coordinates, and the output is time-series data of these coordinates. Specifically, the device collects location information at regular intervals and temporarily stores it.

[0082] Step 2:

[0083] The terminal retrieves the user's payment history from relevant applications and digital wallets. The purpose of this step is to send the payment history data to the server. The input is a record of transactions, and the output is a historical dataset in which these are aggregated. The terminal periodically retrieves this information and automatically sends it to the server.

[0084] Step 3:

[0085] The device collects the user's application usage history. Specifically, it collects data on how frequently and for how long each application is used. The input is the application usage history log, and the output is aggregated usage statistics. The device collects this data and prepares it to be sent to the server later.

[0086] Step 4:

[0087] The server receives location information, payment history, and application usage history transmitted from the terminal. Receiving this data prepares it for analysis. The input consists of diverse user data, and the output is registration into the database. The server organizes and stores all received data according to its type.

[0088] Step 5:

[0089] The server analyzes the stored data. Specifically, it performs data processing to recognize user behavior patterns and interests. The input is the stored dataset, and the output is the behavior patterns resulting from the analysis. The server uses statistical analysis and machine learning techniques to predict user interests.

[0090] Step 6:

[0091] The server uses an AI model based on the analysis results to prepare prompt messages and generate advertising content. For example, the prompt message might be "Create an optimal cafe advertisement based on the user's behavior patterns." The input is the analyzed behavioral data, and the output is the generated advertising content. The generated content is saved for later distribution.

[0092] Step 7:

[0093] The server delivers advertising content generated according to the user's situation to the device at the appropriate time. The input is the generated advertisement and the user's real-time location information, and the output is the display of the advertisement on the device. The server adjusts the timing of ad delivery based on the user's location and time.

[0094] Step 8:

[0095] The device records how the user interacts with advertisements, such as clicks and viewing time, as response data. The input is user action information, and the output is the recorded response data. The device measures this data and prepares to send it back to the server.

[0096] Step 9:

[0097] The server receives user response data sent from the terminal and uses it to improve the ad delivery algorithm. The input is user feedback data, and the output is the updated ad delivery algorithm. The server then continuously learns from this to improve the accuracy of future ad deliveries.

[0098] (Application Example 1)

[0099] 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."

[0100] It is technically and economically challenging for small businesses to deliver effective, personalized advertising to customers with limited resources. Current large-scale advertising platforms are not sufficiently personalized, and locally-based businesses, in particular, need to deliver pinpoint, relevant information in a timely manner.

[0101] 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.

[0102] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, means for analyzing the acquired information and making personalized behavioral predictions, means for generating advertising content based on the user's interests using a generation AI, and means for delivering notifications to the user's mobile terminal in real time. This makes it possible to dynamically generate and deliver advertising content based on the user's location and interests.

[0103] "Information registered by the business operator" refers to data such as product and service details and campaign information that the business operator has registered in the system in advance in order to provide the service.

[0104] "Means for automatically generating personalized information presentations" refers to a system or algorithm that takes into account user characteristics and behavioral history to generate information and advertisements tailored to individual users.

[0105] "Location information and usage history information transmitted from the device" refers to geographical location data and records of past application usage transmitted from the user's mobile device or similar device.

[0106] "Means for analysis and personalized behavioral prediction" refers to technologies or algorithms for analyzing received data and predicting user behavior patterns.

[0107] "Methods for generating advertising content based on user interests using generative AI" refers to methods that use machine learning models or generative AI to automatically create appropriate advertising content based on the user's past behavior and interests.

[0108] "Means for delivering notifications to users' mobile devices in real time" refers to technologies or communication methods for sending information from a server to a user's mobile device in a timely manner.

[0109] The system for implementing this invention mainly includes a server, a user's mobile terminal, and a database managed by the service provider. The server has the function of holding information registered by the service provider and receiving location information and usage history information from the user's terminal. This makes it possible to predict individualized behavior based on location and activity history.

[0110] The servers operate on cloud platforms such as AWS® or Google® Cloud and utilize generative AI models (e.g., GPT-3®) to generate ad content based on user interests. These ads are personalized based on the user's past usage history and location information. The generated ads are stored in a database and delivered in real time to the user's mobile device via communication methods such as Firebase Cloud Messaging.

[0111] User responses, such as ad click-through rates and viewing time, are recorded by mobile devices and sent back to the server as feedback. The server uses this data to update and improve its behavioral prediction model.

[0112] For example, if it is determined that a user frequently visits a restaurant in a specific area, an advertisement for new menu items at that restaurant will be generated and appropriately notified during their next visit. This system allows users to receive advertisements that match their interests.

[0113] An example of a prompt message is: "Generate ads based on nearby store information and campaigns related to locations the user frequently visits. The generated ads will be based on the user's interests and past purchase history."

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The device continuously collects the user's location information and usage history information. The input is the device's GPS data and application usage history, and the output is a data stream in which this data is packetized and sent to the server.

[0117] Step 2:

[0118] The server stores the received location information and usage history information in a database. The input is location information and usage history information sent from the terminal, and the output is the storage operation into the database. During this process, the validity and integrity of the data are checked.

[0119] Step 3:

[0120] The server analyzes information in the database to identify user behavior patterns. Inputs are stored location data and usage history, and output is an update to the user behavior prediction model. The analysis is performed using an AI model to extract frequently visited locations and usage patterns.

[0121] Step 4:

[0122] The server uses a generative AI model to generate advertising content based on user behavior patterns and interests. Input is data from the behavioral prediction model and information registered by the business, and output is personalized advertising content. The generated ads include campaign information but are edited to match the user's preferences.

[0123] Step 5:

[0124] The server delivers generated advertising content to the user's device in real time. The input is advertising content, and the output is in the form of a push notification to the device. Reliable delivery is ensured using Firebase Cloud Messaging.

[0125] Step 6:

[0126] The user's device records their response to received advertisements. Input is the user's activity log (ad click-through rate and viewing time), and output is feedback data sent to the server. This provides data that allows for a more accurate understanding of user interests and other factors.

[0127] Step 7:

[0128] The server analyzes feedback data to improve the behavioral prediction model and ad generation algorithm. The input is user feedback data, and the output is the updated behavioral prediction model and ad generation parameters. This continuous improvement leads to more accurate ad delivery.

[0129] 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.

[0130] This invention provides an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This enables small businesses to deliver more personalized advertisements and achieve a more nuanced approach based on user responses.

[0131] The server first acquires information and campaign data provided by the service provider and uses this to create the content that forms the basis of the advertisement. The device continues to acquire normal location information and usage history, and in addition, it collects the user's voice and text data.

[0132] The collected data is analyzed by the server, and the user's emotional state is identified using an emotion engine. The emotion engine analyzes voice tone and text context to determine the type of emotion the user is currently experiencing (e.g., joy, sadness, surprise). This emotional data is added to the analysis results and reflected in the user behavior prediction model.

[0133] Next, the server uses this emotional information to create customized advertising content adapted to the user's emotions using generative AI. For example, if the user is feeling stressed, it can suggest advertisements for relaxation services that can alleviate that stress.

[0134] Once the content is created, the server delivers the ad to the user's device at the optimal time. The user views the ad on their device and takes action as needed. The device also records the user's response to the ad, such as the time spent clicking on the ad or viewing details.

[0135] These responses are fed back to the server and used to improve the ad delivery algorithm. For example, if a user accesses the site at the end of the workday when they are stressed, the emotion engine detects this information and provides ads for products specifically designed for relaxation, making it easier to capture the user's interest.

[0136] Thus, by taking into account the user's emotional state, the present invention achieves even more precise personalization and contributes to effective marketing by businesses.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The device collects the user's location information, app usage history, and voice and text data. In particular, it pays attention to the tone and intensity of conversations when collecting voice data, and sends appropriate data to the server.

[0140] Step 2:

[0141] The server stores location information, usage history, and voice / text data received from the terminal in a database. This allows for the recording of detailed behavioral and emotional history for each user.

[0142] Step 3:

[0143] The server analyzes the accumulated data and uses an emotion engine to identify the user's emotional state. For example, a high tone of voice is interpreted as excitement, while a low tone is interpreted as depression.

[0144] Step 4:

[0145] Based on the emotional data obtained from the emotion engine, the server updates the user behavior prediction model. During this process, the behavioral patterns are adjusted according to the user's current emotional state.

[0146] Step 5:

[0147] The server retrieves information registered by businesses and campaign details, and uses a generation AI to create personalized advertising content tailored to the user's emotional state. For example, if a user is in a somewhat unstable emotional state, it will create relaxation-related advertisements.

[0148] Step 6:

[0149] The server delivers the generated advertising content to the user's device at the most effective time, optimizing notifications based on specific time periods and location information.

[0150] Step 7:

[0151] Users receive advertisements on their devices and review their content. The device records behavioral data (clicks, time spent viewing details, etc.) about how the user reacts to the advertisements.

[0152] Step 8:

[0153] The device sends recorded user response data to the server, which receives it as feedback.

[0154] Step 9:

[0155] The server uses the feedback information to improve the ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery that incorporates emotional data.

[0156] (Example 2)

[0157] 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".

[0158] Traditional advertising delivery systems have faced the challenge of being unable to deliver advertisements tailored to the emotional state of individual users, thus failing to maximize the effectiveness of advertising. As a result, advertisements fail to attract user attention, and consequently, they do not effectively boost the sales of businesses.

[0159] 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.

[0160] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information, usage history, and emotion data transmitted from the terminal, and means for analyzing the acquired voice and text data and identifying the emotional state using an emotion engine. This enables accurate advertising delivery based on the user's emotional state.

[0161] A "business operator" is an entity that uses the system to provide advertisements or informational content, and is responsible for managing registration information within the system.

[0162] "Personalized information presentation" is the process of providing customized information and advertisements to each user, generating content that is tailored to the user's attributes and current emotional state.

[0163] A "terminal" is a device that users directly operate and use to exchange information, and it is responsible for collecting location information, usage history, voice and text data and sending it to the server.

[0164] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from their voice tone and text context, and is used to customize advertising content.

[0165] An "emotion engine" is a software module that analyzes collected data and identifies the user's emotional state from voice, text, and other sources.

[0166] A "generative AI model" is a pre-trained algorithm that has the ability to automatically generate advertising content tailored to the user's attributes and emotional state.

[0167] An "ad delivery algorithm" is a series of methods that implement a process to analyze user behavior data and emotional data to determine when and which advertisements should be delivered.

[0168] "Feedback" is the process of returning user response data to the server to help improve the accuracy and customization of the system in the future.

[0169] This invention includes an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This system has the function of generating and delivering personalized advertisements that correspond to the user's emotional state, based on information registered by the business operator.

[0170] The server acquires campaign information and product data provided by businesses and creates the basic data for advertising content. The server receives user location information, usage history, voice, and text data from the device. The device collects this data using hardware such as sensors, microphones, and text input.

[0171] The server analyzes the acquired data and uses an emotion engine to identify the user's emotional state from changes in voice tone and text content. The emotion engine used here is a software module that includes acoustic analysis and natural language processing algorithms.

[0172] Next, the server uses a generative AI model to generate advertising content that is best suited to the analyzed emotional state. The generative AI model is an algorithm pre-trained to adapt to the user's emotions. An example of a prompt is, "Generate an advertisement for a relaxation service that is appropriate when the user is feeling stressed."

[0173] Ultimately, the server delivers the generated advertisements to the user's device at the appropriate time. Users can view the advertisements on their devices and take the necessary actions. The device records the user's response and feeds this information back to the server. This feedback is used to improve the ad delivery algorithm, enhancing the accuracy of future advertisements. This enables more effective marketing that responds to the user's emotions.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The device collects user location information, app usage history, and voice and text data. Inputs include data from the GPS sensor, microphone, and keyboard. This data is acquired in real time and stored on the device in various formats. For example, if the user says, "I want to go to a nearby cafe," voice data is collected. As output, this data is prepared to be sent to a server.

[0177] Step 2:

[0178] The server receives location information, usage history, and voice and text data transmitted from the terminal. This data itself is provided as input. The server then processes the voice data with a speech recognition engine and analyzes the context of the text data using natural language processing. This process determines the user's emotional state. For example, it analyzes background sounds in the voice and keywords in the text to determine whether the user wants to relax or is excited. The analysis results are output as the user's emotional state.

[0179] Step 3:

[0180] The server takes the analyzed emotional state as input and generates appropriate advertising content using a generative AI model. The AI ​​is activated by the prompt "Generate an advertisement for a relaxation service suitable for when the user wants to relax." The generation process optimizes content that matches the user's current emotional state and outputs it in a specific advertisement format. For example, a special offer from a relaxation service provider might be presented to the user.

[0181] Step 4:

[0182] The server delivers the generated ad content to the user's device. At this stage, an ad delivery algorithm is used to select the optimal timing and method. The inputs are the ad content generated by the AI ​​and the user's past browsing patterns. The output is the delivery of the ad to the user's device, displayed in the form of a notification or pop-up. User actions on the device, such as ad clicks, are recorded.

[0183] Step 5:

[0184] The device acquires user responses to advertisements and provides feedback to the server. Inputs include the number of clicks and ad viewing time. This data functions as an indicator of user interest and engagement. Finally, this feedback data is sent to the server and used to optimize future ad delivery. As output, the feedback data is aggregated on the server, contributing to improvements in the ad delivery algorithm.

[0185] (Application Example 2)

[0186] 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".

[0187] A challenge in modern advertising delivery systems is the lack of personalized information presentation that takes into account the user's emotional state. Traditional systems are limited to ad delivery based on location information and usage history, making it difficult to provide ads that reflect the user's psychological state.

[0188] 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.

[0189] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, emotion recognition means for analyzing voice data and text data to identify the user's emotional state, and advertisement generation means for dynamically adjusting the information content in response to the user's emotional state. This enables optimized advertisement delivery that is tailored to the user's emotional state.

[0190] "Information registered by businesses" refers to data about products and services that advertisers and companies enter into the system.

[0191] "Personalized information presentation" refers to the display of information that is tailored to the user's specific interests and emotional state.

[0192] "Means of automatic generation" refers to methods in which a system generates information using information processing technology without human intervention.

[0193] "Location information" refers to data that indicates the user's geographical location.

[0194] "Usage history information" refers to data that shows the history of operations and actions performed by a user in the past.

[0195] "Audio data" refers to data that records the voice spoken by the user.

[0196] "Text data" refers to data that represents text or messages entered by the user.

[0197] "Emotion recognition methods" refer to methods for identifying a user's emotional state through voice and text analysis.

[0198] "Advertising generation method" refers to a method of generating and providing advertising content based on the emotional state of the user.

[0199] "Ad delivery" is the process of sending generated advertisements to users' devices at the appropriate time.

[0200] To realize this invention, a system program is constructed that performs emotion recognition and advertisement generation. The server first automatically generates personalized information presentations based on product and service information registered in a database provided by advertisers and companies. Next, the server receives geographical location information and user operation history transmitted from the terminal and analyzes the user's past behavior patterns.

[0201] The user's device collects audio data using the smartphone's microphone and text data through text input. This data is sent to a server, which uses an emotion recognition engine to identify the user's emotional state from the tone of voice and the context of the text. Specifically, it uses the Google Cloud Speech-to-Text speech recognition API to convert the audio data into text. Then, it analyzes the text data using the Google Cloud Natural Language API natural language processing model and detects emotions through IBM Watson's emotion recognition capabilities.

[0202] Once emotional information is identified, the server uses OpenAI's GPT-4® generative AI model to dynamically generate advertising content tailored to the user's emotions. In this process, prompts are used to generate appropriate advertisements based on the emotional state. For example, a prompt such as, "The user is feeling stressed; please recommend products that can help them relax," might be used.

[0203] The device receives the generated advertising content and displays the advertisement on the screen of the smartphone, which is the display device. Users can view this advertisement and, if interested, take action such as clicking on a link. The device records this response and sends it back to the server as feedback. The server analyzes this feedback information and continuously improves the advertising delivery algorithm.

[0204] This entire process makes it possible to provide personalized advertisements that are tailored to the user's emotional state, thereby increasing the effectiveness of the advertisements.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server retrieves data on products and services registered by businesses and stores it in a database. This data serves as the input information for future personalized information presentations.

[0208] Step 2:

[0209] The device collects geographical location information through the smartphone's location services and obtains usage history information based on the user's access logs. This input data is sent to the server.

[0210] Step 3:

[0211] The device collects user voice data using the smartphone's microphone and receives text data using the text input function. The input voice data is converted to text using Google Cloud Speech-to-Text and sent to the server.

[0212] Step 4:

[0213] The server receives the transmitted text data and performs text analysis using the Google Cloud Natural Language API. This analysis involves understanding the context of the text and extracting information necessary for sentiment recognition.

[0214] Step 5:

[0215] The server uses IBM Watson's emotion recognition technology to detect the user's emotional state from the analyzed text data. This process identifies the type and intensity of the emotion and passes the results to the next step.

[0216] Step 6:

[0217] The server uses OpenAI's generative AI model (GPT-4) to generate advertising content that matches the detected emotional state. The input to this process is emotional information, and the output is dynamically customized advertisements. The prompt used is "The user is feeling stressed; please recommend products that can help them relax."

[0218] Step 7:

[0219] The generated advertisement is sent from the server to the device and presented to the user on the smartphone screen. The user views the advertisement and generates a response by taking actions such as clicking or interacting with links.

[0220] Step 8:

[0221] The device records the user's response to advertisements and feeds this information back to the server. The server analyzes the received feedback information and uses it as data to improve the ad delivery algorithm.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] This invention provides a system for small businesses to effectively deliver personalized advertising to customers with limited resources. Embodiments thereof are described below.

[0239] The server performs central processing and receives website content and campaign information that businesses have registered in advance. This information is stored as basic data for later generation of advertising content.

[0240] The device plays a role in routinely collecting the user's location information, payment history, and application usage history, and sending this data to a server. If a user frequently visits a particular location, that location information is used to identify the user's living area.

[0241] The server analyzes the received data to recognize user behavior patterns. For example, it analyzes places users frequently visit on holidays and predicts their interest in services related to those locations. This analysis allows for an automatic understanding of user interests.

[0242] Next, the server uses a generation AI to create personalized advertising content based on the analysis results. This process utilizes information registered by the business, including, for example, announcements of new products and promotions of services. This personalized information is then configured to be delivered to the user's smartphone at the appropriate time.

[0243] User responses to delivered advertisements are recorded on the device. The device acquires data such as click-through rates and ad viewing time, and sends this data to the server as feedback. This feedback information is used to improve the ad delivery algorithm.

[0244] For example, if a user frequently visits a particular cafe, the server can deliver advertisements for the cafe's new menu items to coincide with the user's next visit. In this case, the advertisements are optimized to attract the user's interest, taking into account their visit frequency and past payment history.

[0245] This invention enables small businesses to approach customers more efficiently and accurately.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The device collects the user's location information, app usage history, and payment history. This data is sent to the server as it is collected.

[0249] Step 2:

[0250] The server stores the data received from the terminal in a database. This allows for the storage of detailed activity history for each user.

[0251] Step 3:

[0252] The server analyzes accumulated data to predict user behavior patterns and interests. For example, it may analyze the tendency for users to visit the same store multiple times.

[0253] Step 4:

[0254] The server retrieves campaign information and website content registered by businesses and uses a generation AI to create user-optimized advertising content.

[0255] Step 5:

[0256] The server sends the generated ad content to the user's device at the optimal time. For example, it can be configured to notify the user of an ad when they enter a specific geographical area.

[0257] Step 6:

[0258] The user's device receives advertisements and records how the user reacts to them (clicks, viewing time, etc.).

[0259] Step 7:

[0260] The device sends recorded user response data to the server, which receives it as feedback.

[0261] Step 8:

[0262] The server uses the feedback information to improve its ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery.

[0263] (Example 1)

[0264] 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."

[0265] For small businesses, providing effective and personalized advertising to customers with limited resources is difficult. Existing systems struggle to deliver targeted ads based on user behavior patterns and lack feedback functions to evaluate ad effectiveness. As a result, there is a challenge in accurately delivering ads that attract user interest and continuously improving those ads.

[0266] 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.

[0267] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator; means for receiving location information and usage history information transmitted from the terminal; means for analyzing the acquired information, recognizing user behavior patterns, and making personalized behavior predictions; means for generating optimized advertising content using a generation AI model based on the analysis results; means for delivering the generated content at an appropriate time according to the user's situation; and means for recording user reactions and feeding them back into the analysis to improve the advertising delivery algorithm. This makes it possible for even small businesses to achieve effective and personalized advertising delivery with limited resources, and to further improve its accuracy.

[0268] "Information registered by businesses" refers to content and campaign information provided in advance by businesses conducting commercial activities, which the system uses to generate advertising content.

[0269] "Personalized information presentation" refers to advertisements and notifications that are created individually based on the user's behavioral data and registered information, and delivered to the user.

[0270] A "terminal" is an electronic device used to collect user location information, payment history, and application usage history, and to transmit this information to a server.

[0271] "Location information" refers to information that includes geographical data indicating that a user is located in a specific place.

[0272] "Usage history information" refers to data that includes a user's past behavioral history, payment history, and application usage history.

[0273] "Behavioral patterns" are the results of analyzing the regularity, consistency, and habits that indicate a user's daily actions and tendencies.

[0274] A "generative AI model" is an artificial intelligence system that automatically generates advertising content based on user behavior patterns and interests, using prior data learning.

[0275] "Advertising content" refers to media or messages that contain information about specific products or services and are created to attract the user's interest.

[0276] "User response" refers to behavioral data such as clicks and viewing time in response to advertisements and notifications.

[0277] An "ad delivery algorithm" is a computational method used to optimize the delivery of advertising content based on user data and responses.

[0278] This system aims to enable small businesses to effectively deliver personalized advertising with limited resources. The system analyzes users' behavioral patterns based on their location information and usage history in their daily lives, and generates advertising content using a generative AI model.

[0279] The server receives website content and campaign information registered in advance by the service provider and stores this information in a database. This information is used as basic data when generating advertisements. The device collects the user's location information using GPS functionality and also obtains payment history and application usage history. This data is necessary to understand the user's daily behavior.

[0280] The server analyzes the data sent from the terminal to recognize the user's behavior patterns. Based on these analysis results, the server uses a generative AI model to prepare prompts that create personalized advertising content. For example, a prompt could say, "Create an advertisement for an interesting new menu item at a cafe the user visits on their day off."

[0281] The generated advertising content is delivered to the device at the optimal time based on the user's location and usage history. By displaying ads on the screen based on location and time while the user is using their smartphone, a personalized advertising experience is provided.

[0282] For example, when a user is near a cafe they frequently visit, advertisements containing information about the cafe's new menu or discounts could be delivered to them in time for their next visit. In this way, advertisements optimized based on user behavior data can be delivered, enabling small businesses to attract customers more efficiently and supporting business growth.

[0283] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0284] Step 1:

[0285] The terminal obtains the user's daily location information using the GPS function. The main process of this step is from when the location information data is collected until it is transmitted to the server. The input is the location coordinates by GPS, and the output is the time-series data of these coordinates. Specifically, the terminal collects location information at regular intervals and temporarily stores it.

[0286] Step 2:

[0287] The terminal obtains the user's payment history from related applications or digital wallets. The purpose of this step is for the payment history data to be transmitted to the server. The input is the record of transactions, and the output is the aggregated history data set of these. The terminal periodically obtains this information and automatically transmits it to the server.

[0288] Step 3:

[0289] The terminal collects the user's application usage history. Specifically, it collects as data how frequently and for how long each application was used. The input is the application usage history log, and the output is the aggregated usage statistics. The terminal collects this data and prepares to send it to the server later.

[0290] Step 4:

[0291] The server receives the location information, payment history, and application usage history sent from the terminal. By receiving this data, it prepares for analysis. The input is various user data, and the output is registration in the database. The server sorts and stores all the received data according to the type.

[0292] Step 5:

[0293] The server analyzes the stored data. Specifically, it performs data processing to recognize user behavior patterns and interests. The input is the stored dataset, and the output is the behavior patterns resulting from the analysis. The server uses statistical analysis and machine learning techniques to predict user interests.

[0294] Step 6:

[0295] The server uses an AI model based on the analysis results to prepare prompt messages and generate advertising content. For example, the prompt message might be "Create an optimal cafe advertisement based on the user's behavior patterns." The input is the analyzed behavioral data, and the output is the generated advertising content. The generated content is saved for later distribution.

[0296] Step 7:

[0297] The server delivers advertising content generated according to the user's situation to the device at the appropriate time. The input is the generated advertisement and the user's real-time location information, and the output is the display of the advertisement on the device. The server adjusts the timing of ad delivery based on the user's location and time.

[0298] Step 8:

[0299] The device records how the user interacts with advertisements, such as clicks and viewing time, as response data. The input is user action information, and the output is the recorded response data. The device measures this data and prepares to send it back to the server.

[0300] Step 9:

[0301] The server receives user response data sent from the terminal and uses it to improve the ad delivery algorithm. The input is user feedback data, and the output is the updated ad delivery algorithm. The server then continuously learns from this to improve the accuracy of future ad deliveries.

[0302] (Application Example 1)

[0303] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0304] For small businesses to deliver effective personalized advertisements to customers with limited resources is technically and economically difficult. In current large-scale advertising platforms, personalization is insufficient, and especially in location-based businesses, it is required to provide appropriate information pinpointedly and in a timely manner.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means respectively.

[0306] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, means for analyzing the acquired information and making personalized behavior predictions, means for generating advertisement content based on the user's interests using a generation AI, and means for delivering notifications to the user's mobile terminal in real time. Thereby, it becomes possible to dynamically generate and deliver advertisement content based on the user's location and interests.

[0307] The "information registered by the business operator" is data such as details of products and services, campaign information, etc. that the business operator has registered in the system in advance to provide services.

[0308] The "means for automatically generating personalized information presentations" is a system or algorithm for generating information and advertisements tailored to individual users considering the user's characteristics and behavior history.

[0309] The "location information and usage history information transmitted from the terminal" are geographical location data and records of past application usage situations transmitted from the user's mobile terminal, etc.

[0310] "Means for analysis and personalized behavioral prediction" refers to technologies or algorithms for analyzing received data and predicting user behavior patterns.

[0311] "Methods for generating advertising content based on user interests using generative AI" refers to methods that use machine learning models or generative AI to automatically create appropriate advertising content based on the user's past behavior and interests.

[0312] "Means for delivering notifications to users' mobile devices in real time" refers to technologies or communication methods for sending information from a server to a user's mobile device in a timely manner.

[0313] The system for implementing this invention mainly includes a server, a user's mobile terminal, and a database managed by the service provider. The server has the function of holding information registered by the service provider and receiving location information and usage history information from the user's terminal. This makes it possible to predict individualized behavior based on location and activity history.

[0314] The servers run on cloud platforms such as AWS or Google Cloud and utilize generative AI models (e.g., GPT-3) to generate ad content based on user interests. These ads are personalized based on the user's past usage history and location information. The generated ads are stored in a database and delivered in real time to the user's mobile device via communication methods such as Firebase Cloud Messaging.

[0315] User responses, such as ad click-through rates and viewing time, are recorded by mobile devices and sent back to the server as feedback. The server uses this data to update and improve its behavioral prediction model.

[0316] For example, if it is determined that a user frequently visits a restaurant in a specific area, an advertisement for new menu items at that restaurant will be generated and appropriately notified during their next visit. This system allows users to receive advertisements that match their interests.

[0317] An example of a prompt message is: "Generate ads based on nearby store information and campaigns related to locations the user frequently visits. The generated ads will be based on the user's interests and past purchase history."

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The device continuously collects the user's location information and usage history information. The input is the device's GPS data and application usage history, and the output is a data stream in which this data is packetized and sent to the server.

[0321] Step 2:

[0322] The server stores the received location information and usage history information in a database. The input is location information and usage history information sent from the terminal, and the output is the storage operation into the database. During this process, the validity and integrity of the data are checked.

[0323] Step 3:

[0324] The server analyzes information in the database to identify user behavior patterns. Inputs are stored location data and usage history, and output is an update to the user behavior prediction model. The analysis is performed using an AI model to extract frequently visited locations and usage patterns.

[0325] Step 4:

[0326] The server uses a generative AI model to generate advertising content based on user behavior patterns and interests. Input is data from the behavioral prediction model and information registered by the business, and output is personalized advertising content. The generated ads include campaign information but are edited to match the user's preferences.

[0327] Step 5:

[0328] The server delivers generated advertising content to the user's device in real time. The input is advertising content, and the output is in the form of a push notification to the device. Reliable delivery is ensured using Firebase Cloud Messaging.

[0329] Step 6:

[0330] The user's device records their response to received advertisements. Input is the user's activity log (ad click-through rate and viewing time), and output is feedback data sent to the server. This provides data that allows for a more accurate understanding of user interests and other factors.

[0331] Step 7:

[0332] The server analyzes feedback data to improve the behavioral prediction model and ad generation algorithm. The input is user feedback data, and the output is the updated behavioral prediction model and ad generation parameters. This continuous improvement leads to more accurate ad delivery.

[0333] 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.

[0334] This invention provides an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This enables small businesses to deliver more personalized advertisements and achieve a more nuanced approach based on user responses.

[0335] The server first acquires information and campaign data provided by the service provider and uses this to create the content that forms the basis of the advertisement. The device continues to acquire normal location information and usage history, and in addition, it collects the user's voice and text data.

[0336] The collected data is analyzed by the server, and the user's emotional state is identified using an emotion engine. The emotion engine analyzes voice tone and text context to determine the type of emotion the user is currently experiencing (e.g., joy, sadness, surprise). This emotional data is added to the analysis results and reflected in the user behavior prediction model.

[0337] Next, the server uses this emotional information to create customized advertising content adapted to the user's emotions using generative AI. For example, if the user is feeling stressed, it can suggest advertisements for relaxation services that can alleviate that stress.

[0338] Once the content is created, the server delivers the ad to the user's device at the optimal time. The user views the ad on their device and takes action as needed. The device also records the user's response to the ad, such as the time spent clicking on the ad or viewing details.

[0339] These responses are fed back to the server and used to improve the ad delivery algorithm. For example, if a user accesses the site at the end of the workday when they are stressed, the emotion engine detects this information and provides ads for products specifically designed for relaxation, making it easier to capture the user's interest.

[0340] Thus, by taking into account the user's emotional state, the present invention achieves even more precise personalization and contributes to effective marketing by businesses.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] The device collects the user's location information, app usage history, and voice and text data. In particular, it pays attention to the tone and intensity of conversations when collecting voice data, and sends appropriate data to the server.

[0344] Step 2:

[0345] The server stores location information, usage history, and voice / text data received from the terminal in a database. This allows for the recording of detailed behavioral and emotional history for each user.

[0346] Step 3:

[0347] The server analyzes the accumulated data and uses an emotion engine to identify the user's emotional state. For example, a high tone of voice is interpreted as excitement, while a low tone is interpreted as depression.

[0348] Step 4:

[0349] Based on the emotional data obtained from the emotion engine, the server updates the user behavior prediction model. During this process, the behavioral patterns are adjusted according to the user's current emotional state.

[0350] Step 5:

[0351] The server retrieves information registered by businesses and campaign details, and uses a generation AI to create personalized advertising content tailored to the user's emotional state. For example, if a user is in a somewhat unstable emotional state, it will create relaxation-related advertisements.

[0352] Step 6:

[0353] The server delivers the generated advertising content to the user's device at the most effective time, optimizing notifications based on specific time periods and location information.

[0354] Step 7:

[0355] Users receive advertisements on their devices and review their content. The device records behavioral data (clicks, time spent viewing details, etc.) about how the user reacts to the advertisements.

[0356] Step 8:

[0357] The device sends recorded user response data to the server, which receives it as feedback.

[0358] Step 9:

[0359] The server uses the feedback information to improve the ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery that incorporates emotional data.

[0360] (Example 2)

[0361] 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".

[0362] Traditional advertising delivery systems have faced the challenge of being unable to deliver advertisements tailored to the emotional state of individual users, thus failing to maximize the effectiveness of advertising. As a result, advertisements fail to attract user attention, and consequently, they do not effectively boost the sales of businesses.

[0363] 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.

[0364] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information, usage history, and emotion data transmitted from the terminal, and means for analyzing the acquired voice and text data and identifying the emotional state using an emotion engine. This enables accurate advertising delivery based on the user's emotional state.

[0365] A "business operator" is an entity that uses the system to provide advertisements or informational content, and is responsible for managing registration information within the system.

[0366] "Personalized information presentation" is the process of providing customized information and advertisements to each user, generating content that is tailored to the user's attributes and current emotional state.

[0367] A "terminal" is a device that users directly operate and use to exchange information, and it is responsible for collecting location information, usage history, voice and text data and sending it to the server.

[0368] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from their voice tone and text context, and is used to customize advertising content.

[0369] An "emotion engine" is a software module that analyzes collected data and identifies the user's emotional state from voice, text, and other sources.

[0370] A "generative AI model" is a pre-trained algorithm that has the ability to automatically generate advertising content tailored to the user's attributes and emotional state.

[0371] An "ad delivery algorithm" is a series of methods that implement a process to analyze user behavior data and emotional data to determine when and which advertisements should be delivered.

[0372] "Feedback" is the process of returning user response data to the server to help improve the accuracy and customization of the system in the future.

[0373] This invention includes an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This system has the function of generating and delivering personalized advertisements that correspond to the user's emotional state, based on information registered by the business operator.

[0374] The server acquires campaign information and product data provided by businesses and creates the basic data for advertising content. The server receives user location information, usage history, voice, and text data from the device. The device collects this data using hardware such as sensors, microphones, and text input.

[0375] The server analyzes the acquired data and uses an emotion engine to identify the user's emotional state from changes in voice tone and text content. The emotion engine used here is a software module that includes acoustic analysis and natural language processing algorithms.

[0376] Next, the server uses a generative AI model to generate advertising content that is best suited to the analyzed emotional state. The generative AI model is an algorithm pre-trained to adapt to the user's emotions. An example of a prompt is, "Generate an advertisement for a relaxation service that is appropriate when the user is feeling stressed."

[0377] Ultimately, the server delivers the generated advertisements to the user's device at the appropriate time. Users can view the advertisements on their devices and take the necessary actions. The device records the user's response and feeds this information back to the server. This feedback is used to improve the ad delivery algorithm, enhancing the accuracy of future advertisements. This enables more effective marketing that responds to the user's emotions.

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] The device collects user location information, app usage history, and voice and text data. Inputs include data from the GPS sensor, microphone, and keyboard. This data is acquired in real time and stored on the device in various formats. For example, if the user says, "I want to go to a nearby cafe," voice data is collected. As output, this data is prepared to be sent to a server.

[0381] Step 2:

[0382] The server receives location information, usage history, and voice and text data transmitted from the terminal. This data itself is provided as input. The server then processes the voice data with a speech recognition engine and analyzes the context of the text data using natural language processing. This process determines the user's emotional state. For example, it analyzes background sounds in the voice and keywords in the text to determine whether the user wants to relax or is excited. The analysis results are output as the user's emotional state.

[0383] Step 3:

[0384] The server takes the analyzed emotional state as input and generates appropriate advertising content using a generative AI model. The AI ​​is activated by the prompt "Generate an advertisement for a relaxation service suitable for when the user wants to relax." The generation process optimizes content that matches the user's current emotional state and outputs it in a specific advertisement format. For example, a special offer from a relaxation service provider might be presented to the user.

[0385] Step 4:

[0386] The server delivers the generated ad content to the user's device. At this stage, an ad delivery algorithm is used to select the optimal timing and method. The inputs are the ad content generated by the AI ​​and the user's past browsing patterns. The output is the delivery of the ad to the user's device, displayed in the form of a notification or pop-up. User actions on the device, such as ad clicks, are recorded.

[0387] Step 5:

[0388] The device acquires user responses to advertisements and provides feedback to the server. Inputs include the number of clicks and ad viewing time. This data functions as an indicator of user interest and engagement. Finally, this feedback data is sent to the server and used to optimize future ad delivery. As output, the feedback data is aggregated on the server, contributing to improvements in the ad delivery algorithm.

[0389] (Application Example 2)

[0390] 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."

[0391] A challenge in modern advertising delivery systems is the lack of personalized information presentation that takes into account the user's emotional state. Traditional systems are limited to ad delivery based on location information and usage history, making it difficult to provide ads that reflect the user's psychological state.

[0392] 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.

[0393] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, emotion recognition means for analyzing voice data and text data to identify the user's emotional state, and advertisement generation means for dynamically adjusting the information content in response to the user's emotional state. This enables optimized advertisement delivery that is tailored to the user's emotional state.

[0394] "Information registered by businesses" refers to data about products and services that advertisers and companies enter into the system.

[0395] "Personalized information presentation" refers to the display of information that is tailored to the user's specific interests and emotional state.

[0396] "Means of automatic generation" refers to methods in which a system generates information using information processing technology without human intervention.

[0397] "Location information" refers to data that indicates the user's geographical location.

[0398] "Usage history information" refers to data that shows the history of operations and actions performed by a user in the past.

[0399] "Audio data" refers to data that records the voice spoken by the user.

[0400] "Text data" refers to data that represents text or messages entered by the user.

[0401] "Emotion recognition methods" refer to methods for identifying a user's emotional state through voice and text analysis.

[0402] "Advertising generation method" refers to a method of generating and providing advertising content based on the emotional state of the user.

[0403] "Ad delivery" is the process of sending generated advertisements to users' devices at the appropriate time.

[0404] To realize this invention, a system program is constructed that performs emotion recognition and advertisement generation. The server first automatically generates personalized information presentations based on product and service information registered in a database provided by advertisers and companies. Next, the server receives geographical location information and user operation history transmitted from the terminal and analyzes the user's past behavior patterns.

[0405] The user's device collects audio data using the smartphone's microphone and text data through text input. This data is sent to a server, which uses an emotion recognition engine to identify the user's emotional state from the tone of voice and the context of the text. Specifically, it uses the Google Cloud Speech-to-Text speech recognition API to convert the audio data into text. Then, it analyzes the text data using the Google Cloud Natural Language API natural language processing model and detects emotions through IBM Watson's emotion recognition capabilities.

[0406] Once emotional information is identified, the server uses OpenAI's GPT-4 generative AI model to dynamically generate advertising content tailored to the user's emotions. In this process, prompts are used to generate appropriate advertisements based on the emotional state. For example, a prompt such as, "The user is feeling stressed; please recommend products that can help them relax," might be used.

[0407] The device receives the generated advertising content and displays the advertisement on the screen of the smartphone, which is the display device. Users can view this advertisement and, if interested, take action such as clicking on a link. The device records this response and sends it back to the server as feedback. The server analyzes this feedback information and continuously improves the advertising delivery algorithm.

[0408] This entire process makes it possible to provide personalized advertisements that are tailored to the user's emotional state, thereby increasing the effectiveness of the advertisements.

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The server retrieves data on products and services registered by businesses and stores it in a database. This data serves as the input information for future personalized information presentations.

[0412] Step 2:

[0413] The device collects geographical location information through the smartphone's location services and obtains usage history information based on the user's access logs. This input data is sent to the server.

[0414] Step 3:

[0415] The device collects user voice data using the smartphone's microphone and receives text data using the text input function. The input voice data is converted to text using Google Cloud Speech-to-Text and sent to the server.

[0416] Step 4:

[0417] The server receives the transmitted text data and performs text analysis using the Google Cloud Natural Language API. This analysis involves understanding the context of the text and extracting information necessary for sentiment recognition.

[0418] Step 5:

[0419] The server uses IBM Watson's emotion recognition technology to detect the user's emotional state from the analyzed text data. This process identifies the type and intensity of the emotion and passes the results to the next step.

[0420] Step 6:

[0421] The server uses OpenAI's generative AI model (GPT-4) to generate advertising content that matches the detected emotional state. The input to this process is emotional information, and the output is dynamically customized advertisements. The prompt used is "The user is feeling stressed; please recommend products that can help them relax."

[0422] Step 7:

[0423] The generated advertisement is sent from the server to the device and presented to the user on the smartphone screen. The user views the advertisement and generates a response by taking actions such as clicking or interacting with links.

[0424] Step 8:

[0425] The device records the user's response to advertisements and feeds this information back to the server. The server analyzes the received feedback information and uses it as data to improve the ad delivery algorithm.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] [Third Embodiment]

[0430] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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".

[0442] This invention provides a system for small businesses to effectively deliver personalized advertising to customers with limited resources. Embodiments thereof are described below.

[0443] The server performs central processing and receives website content and campaign information that businesses have registered in advance. This information is stored as basic data for later generation of advertising content.

[0444] The device plays a role in routinely collecting the user's location information, payment history, and application usage history, and sending this data to a server. If a user frequently visits a particular location, that location information is used to identify the user's living area.

[0445] The server analyzes the received data to recognize user behavior patterns. For example, it analyzes places users frequently visit on holidays and predicts their interest in services related to those locations. This analysis allows for an automatic understanding of user interests.

[0446] Next, the server uses a generation AI to create personalized advertising content based on the analysis results. This process utilizes information registered by the business, including, for example, announcements of new products and promotions of services. This personalized information is then configured to be delivered to the user's smartphone at the appropriate time.

[0447] User responses to delivered advertisements are recorded on the device. The device acquires data such as click-through rates and ad viewing time, and sends this data to the server as feedback. This feedback information is used to improve the ad delivery algorithm.

[0448] For example, if a user frequently visits a particular cafe, the server can deliver advertisements for the cafe's new menu items to coincide with the user's next visit. In this case, the advertisements are optimized to attract the user's interest, taking into account their visit frequency and past payment history.

[0449] This invention enables small businesses to approach customers more efficiently and accurately.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The device collects the user's location information, app usage history, and payment history. This data is sent to the server as it is collected.

[0453] Step 2:

[0454] The server stores the data received from the terminal in a database. This allows for the storage of detailed activity history for each user.

[0455] Step 3:

[0456] The server analyzes accumulated data to predict user behavior patterns and interests. For example, it may analyze the tendency for users to visit the same store multiple times.

[0457] Step 4:

[0458] The server retrieves campaign information and website content registered by businesses and uses a generation AI to create user-optimized advertising content.

[0459] Step 5:

[0460] The server sends the generated ad content to the user's device at the optimal time. For example, it can be configured to notify the user of an ad when they enter a specific geographical area.

[0461] Step 6:

[0462] The user's device receives advertisements and records how the user reacts to them (clicks, viewing time, etc.).

[0463] Step 7:

[0464] The device sends recorded user response data to the server, which receives it as feedback.

[0465] Step 8:

[0466] The server uses the feedback information to improve its ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery.

[0467] (Example 1)

[0468] 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."

[0469] For small businesses, providing effective and personalized advertising to customers with limited resources is difficult. Existing systems struggle to deliver targeted ads based on user behavior patterns and lack feedback functions to evaluate ad effectiveness. As a result, there is a challenge in accurately delivering ads that attract user interest and continuously improving those ads.

[0470] 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.

[0471] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator; means for receiving location information and usage history information transmitted from the terminal; means for analyzing the acquired information, recognizing user behavior patterns, and making personalized behavior predictions; means for generating optimized advertising content using a generation AI model based on the analysis results; means for delivering the generated content at an appropriate time according to the user's situation; and means for recording user reactions and feeding them back into the analysis to improve the advertising delivery algorithm. This makes it possible for even small businesses to achieve effective and personalized advertising delivery with limited resources, and to further improve its accuracy.

[0472] "Information registered by businesses" refers to content and campaign information provided in advance by businesses conducting commercial activities, which the system uses to generate advertising content.

[0473] "Personalized information presentation" refers to advertisements and notifications that are created individually based on the user's behavioral data and registered information, and delivered to the user.

[0474] A "terminal" is an electronic device used to collect user location information, payment history, and application usage history, and to transmit this information to a server.

[0475] "Location information" refers to information that includes geographical data indicating that a user is located in a specific place.

[0476] "Usage history information" refers to data that includes a user's past behavioral history, payment history, and application usage history.

[0477] "Behavioral patterns" are the results of analyzing the regularity, consistency, and habits that indicate a user's daily actions and tendencies.

[0478] A "generative AI model" is an artificial intelligence system that automatically generates advertising content based on user behavior patterns and interests, using prior data learning.

[0479] "Advertising content" refers to media or messages that contain information about specific products or services and are created to attract the user's interest.

[0480] "User response" refers to behavioral data such as clicks and viewing time in response to advertisements and notifications.

[0481] An "ad delivery algorithm" is a computational method used to optimize the delivery of advertising content based on user data and responses.

[0482] This system aims to enable small businesses to effectively deliver personalized advertising with limited resources. The system analyzes users' behavioral patterns based on their location information and usage history in their daily lives, and generates advertising content using a generative AI model.

[0483] The server receives website content and campaign information registered in advance by the service provider and stores this information in a database. This information is used as basic data when generating advertisements. The device collects the user's location information using GPS functionality and also obtains payment history and application usage history. This data is necessary to understand the user's daily behavior.

[0484] The server analyzes the data sent from the terminal to recognize the user's behavior patterns. Based on these analysis results, the server uses a generative AI model to prepare prompts that create personalized advertising content. For example, a prompt could say, "Create an advertisement for an interesting new menu item at a cafe the user visits on their day off."

[0485] The generated advertising content is delivered to the device at the optimal time based on the user's location and usage history. By displaying ads on the screen based on location and time while the user is using their smartphone, a personalized advertising experience is provided.

[0486] For example, when a user is near a cafe they frequently visit, advertisements containing information about the cafe's new menu or discounts could be delivered to them in time for their next visit. In this way, advertisements optimized based on user behavior data can be delivered, enabling small businesses to attract customers more efficiently and supporting business growth.

[0487] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0488] Step 1:

[0489] The device acquires the user's daily location information using GPS functionality. The main process in this step is from the collection of location data to its transmission to the server. The input is GPS location coordinates, and the output is time-series data of these coordinates. Specifically, the device collects location information at regular intervals and temporarily stores it.

[0490] Step 2:

[0491] The terminal retrieves the user's payment history from relevant applications and digital wallets. The purpose of this step is to send the payment history data to the server. The input is a record of transactions, and the output is a historical dataset in which these are aggregated. The terminal periodically retrieves this information and automatically sends it to the server.

[0492] Step 3:

[0493] The device collects the user's application usage history. Specifically, it collects data on how frequently and for how long each application is used. The input is the application usage history log, and the output is aggregated usage statistics. The device collects this data and prepares it to be sent to the server later.

[0494] Step 4:

[0495] The server receives location information, payment history, and application usage history transmitted from the terminal. Receiving this data prepares it for analysis. The input consists of diverse user data, and the output is registration into the database. The server organizes and stores all received data according to its type.

[0496] Step 5:

[0497] The server analyzes the stored data. Specifically, it performs data processing to recognize user behavior patterns and interests. The input is the stored dataset, and the output is the behavior patterns resulting from the analysis. The server uses statistical analysis and machine learning techniques to predict user interests.

[0498] Step 6:

[0499] The server uses an AI model based on the analysis results to prepare prompt messages and generate advertising content. For example, the prompt message might be "Create an optimal cafe advertisement based on the user's behavior patterns." The input is the analyzed behavioral data, and the output is the generated advertising content. The generated content is saved for later distribution.

[0500] Step 7:

[0501] The server delivers advertising content generated according to the user's situation to the device at the appropriate time. The input is the generated advertisement and the user's real-time location information, and the output is the display of the advertisement on the device. The server adjusts the timing of ad delivery based on the user's location and time.

[0502] Step 8:

[0503] The device records how the user interacts with advertisements, such as clicks and viewing time, as response data. The input is user action information, and the output is the recorded response data. The device measures this data and prepares to send it back to the server.

[0504] Step 9:

[0505] The server receives user response data sent from the terminal and uses it to improve the ad delivery algorithm. The input is user feedback data, and the output is the updated ad delivery algorithm. The server then continuously learns from this to improve the accuracy of future ad deliveries.

[0506] (Application Example 1)

[0507] 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."

[0508] It is technically and economically challenging for small businesses to deliver effective, personalized advertising to customers with limited resources. Current large-scale advertising platforms are not sufficiently personalized, and locally-based businesses, in particular, need to deliver pinpoint, relevant information in a timely manner.

[0509] 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.

[0510] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, means for analyzing the acquired information and making personalized behavioral predictions, means for generating advertising content based on the user's interests using a generation AI, and means for delivering notifications to the user's mobile terminal in real time. This makes it possible to dynamically generate and deliver advertising content based on the user's location and interests.

[0511] "Information registered by the business operator" refers to data such as product and service details and campaign information that the business operator has registered in the system in advance in order to provide the service.

[0512] "Means for automatically generating personalized information presentations" refers to a system or algorithm that takes into account user characteristics and behavioral history to generate information and advertisements tailored to individual users.

[0513] "Location information and usage history information transmitted from the device" refers to geographical location data and records of past application usage transmitted from the user's mobile device or similar device.

[0514] "Means for analysis and personalized behavioral prediction" refers to technologies or algorithms for analyzing received data and predicting user behavior patterns.

[0515] "Methods for generating advertising content based on user interests using generative AI" refers to methods that use machine learning models or generative AI to automatically create appropriate advertising content based on the user's past behavior and interests.

[0516] "Means for delivering notifications to users' mobile devices in real time" refers to technologies or communication methods for sending information from a server to a user's mobile device in a timely manner.

[0517] The system for implementing this invention mainly includes a server, a user's mobile terminal, and a database managed by the service provider. The server has the function of holding information registered by the service provider and receiving location information and usage history information from the user's terminal. This makes it possible to predict individualized behavior based on location and activity history.

[0518] The servers run on cloud platforms such as AWS or Google Cloud and utilize generative AI models (e.g., GPT-3) to generate ad content based on user interests. These ads are personalized based on the user's past usage history and location information. The generated ads are stored in a database and delivered in real time to the user's mobile device via communication methods such as Firebase Cloud Messaging.

[0519] User responses, such as ad click-through rates and viewing time, are recorded by mobile devices and sent back to the server as feedback. The server uses this data to update and improve its behavioral prediction model.

[0520] For example, if it is determined that a user frequently visits a restaurant in a specific area, an advertisement for new menu items at that restaurant will be generated and appropriately notified during their next visit. This system allows users to receive advertisements that match their interests.

[0521] An example of a prompt message is: "Generate ads based on nearby store information and campaigns related to locations the user frequently visits. The generated ads will be based on the user's interests and past purchase history."

[0522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0523] Step 1:

[0524] The device continuously collects the user's location information and usage history information. The input is the device's GPS data and application usage history, and the output is a data stream in which this data is packetized and sent to the server.

[0525] Step 2:

[0526] The server stores the received location information and usage history information in a database. The input is location information and usage history information sent from the terminal, and the output is the storage operation into the database. During this process, the validity and integrity of the data are checked.

[0527] Step 3:

[0528] The server analyzes information in the database to identify user behavior patterns. Inputs are stored location data and usage history, and output is an update to the user behavior prediction model. The analysis is performed using an AI model to extract frequently visited locations and usage patterns.

[0529] Step 4:

[0530] The server uses a generative AI model to generate advertising content based on user behavior patterns and interests. Input is data from the behavioral prediction model and information registered by the business, and output is personalized advertising content. The generated ads include campaign information but are edited to match the user's preferences.

[0531] Step 5:

[0532] The server delivers generated advertising content to the user's device in real time. The input is advertising content, and the output is in the form of a push notification to the device. Reliable delivery is ensured using Firebase Cloud Messaging.

[0533] Step 6:

[0534] The user's device records their response to received advertisements. Input is the user's activity log (ad click-through rate and viewing time), and output is feedback data sent to the server. This provides data that allows for a more accurate understanding of user interests and other factors.

[0535] Step 7:

[0536] The server analyzes feedback data to improve the behavioral prediction model and ad generation algorithm. The input is user feedback data, and the output is the updated behavioral prediction model and ad generation parameters. This continuous improvement leads to more accurate ad delivery.

[0537] 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.

[0538] This invention provides an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This enables small businesses to deliver more personalized advertisements and achieve a more nuanced approach based on user responses.

[0539] The server first acquires information and campaign data provided by the service provider and uses this to create the content that forms the basis of the advertisement. The device continues to acquire normal location information and usage history, and in addition, it collects the user's voice and text data.

[0540] The collected data is analyzed by the server, and the user's emotional state is identified using an emotion engine. The emotion engine analyzes voice tone and text context to determine the type of emotion the user is currently experiencing (e.g., joy, sadness, surprise). This emotional data is added to the analysis results and reflected in the user behavior prediction model.

[0541] Next, the server uses this emotional information to create customized advertising content adapted to the user's emotions using generative AI. For example, if the user is feeling stressed, it can suggest advertisements for relaxation services that can alleviate that stress.

[0542] Once the content is created, the server delivers the ad to the user's device at the optimal time. The user views the ad on their device and takes action as needed. The device also records the user's response to the ad, such as the time spent clicking on the ad or viewing details.

[0543] These responses are fed back to the server and used to improve the ad delivery algorithm. For example, if a user accesses the site at the end of the workday when they are stressed, the emotion engine detects this information and provides ads for products specifically designed for relaxation, making it easier to capture the user's interest.

[0544] Thus, by taking into account the user's emotional state, the present invention achieves even more precise personalization and contributes to effective marketing by businesses.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] The device collects the user's location information, app usage history, and voice and text data. In particular, it pays attention to the tone and intensity of conversations when collecting voice data, and sends appropriate data to the server.

[0548] Step 2:

[0549] The server stores location information, usage history, and voice / text data received from the terminal in a database. This allows for the recording of detailed behavioral and emotional history for each user.

[0550] Step 3:

[0551] The server analyzes the accumulated data and uses an emotion engine to identify the user's emotional state. For example, a high tone of voice is interpreted as excitement, while a low tone is interpreted as depression.

[0552] Step 4:

[0553] Based on the emotional data obtained from the emotion engine, the server updates the user behavior prediction model. During this process, the behavioral patterns are adjusted according to the user's current emotional state.

[0554] Step 5:

[0555] The server retrieves information registered by businesses and campaign details, and uses a generation AI to create personalized advertising content tailored to the user's emotional state. For example, if a user is in a somewhat unstable emotional state, it will create relaxation-related advertisements.

[0556] Step 6:

[0557] The server delivers the generated advertising content to the user's device at the most effective time, optimizing notifications based on specific time periods and location information.

[0558] Step 7:

[0559] Users receive advertisements on their devices and review their content. The device records behavioral data (clicks, time spent viewing details, etc.) about how the user reacts to the advertisements.

[0560] Step 8:

[0561] The device sends recorded user response data to the server, which receives it as feedback.

[0562] Step 9:

[0563] The server uses the feedback information to improve the ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery that incorporates emotional data.

[0564] (Example 2)

[0565] 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."

[0566] Traditional advertising delivery systems have faced the challenge of being unable to deliver advertisements tailored to the emotional state of individual users, thus failing to maximize the effectiveness of advertising. As a result, advertisements fail to attract user attention, and consequently, they do not effectively boost the sales of businesses.

[0567] 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.

[0568] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information, usage history, and emotion data transmitted from the terminal, and means for analyzing the acquired voice and text data and identifying the emotional state using an emotion engine. This enables accurate advertising delivery based on the user's emotional state.

[0569] A "business operator" is an entity that uses the system to provide advertisements or informational content, and is responsible for managing registration information within the system.

[0570] "Personalized information presentation" is the process of providing customized information and advertisements to each user, generating content that is tailored to the user's attributes and current emotional state.

[0571] A "terminal" is a device that users directly operate and use to exchange information, and it is responsible for collecting location information, usage history, voice and text data and sending it to the server.

[0572] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from their voice tone and text context, and is used to customize advertising content.

[0573] An "emotion engine" is a software module that analyzes collected data and identifies the user's emotional state from voice, text, and other sources.

[0574] A "generative AI model" is a pre-trained algorithm that has the ability to automatically generate advertising content tailored to the user's attributes and emotional state.

[0575] An "ad delivery algorithm" is a series of methods that implement a process to analyze user behavior data and emotional data to determine when and which advertisements should be delivered.

[0576] "Feedback" is the process of returning user response data to the server to help improve the accuracy and customization of the system in the future.

[0577] This invention includes an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This system has the function of generating and delivering personalized advertisements that correspond to the user's emotional state, based on information registered by the business operator.

[0578] The server acquires campaign information and product data provided by businesses and creates the basic data for advertising content. The server receives user location information, usage history, voice, and text data from the device. The device collects this data using hardware such as sensors, microphones, and text input.

[0579] The server analyzes the acquired data and uses an emotion engine to identify the user's emotional state from changes in voice tone and text content. The emotion engine used here is a software module that includes acoustic analysis and natural language processing algorithms.

[0580] Next, the server uses a generative AI model to generate advertising content that is best suited to the analyzed emotional state. The generative AI model is an algorithm pre-trained to adapt to the user's emotions. An example of a prompt is, "Generate an advertisement for a relaxation service that is appropriate when the user is feeling stressed."

[0581] Ultimately, the server delivers the generated advertisements to the user's device at the appropriate time. Users can view the advertisements on their devices and take the necessary actions. The device records the user's response and feeds this information back to the server. This feedback is used to improve the ad delivery algorithm, enhancing the accuracy of future advertisements. This enables more effective marketing that responds to the user's emotions.

[0582] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0583] Step 1:

[0584] The device collects user location information, app usage history, and voice and text data. Inputs include data from the GPS sensor, microphone, and keyboard. This data is acquired in real time and stored on the device in various formats. For example, if the user says, "I want to go to a nearby cafe," voice data is collected. As output, this data is prepared to be sent to a server.

[0585] Step 2:

[0586] The server receives location information, usage history, and voice and text data transmitted from the terminal. This data itself is provided as input. The server then processes the voice data with a speech recognition engine and analyzes the context of the text data using natural language processing. This process determines the user's emotional state. For example, it analyzes background sounds in the voice and keywords in the text to determine whether the user wants to relax or is excited. The analysis results are output as the user's emotional state.

[0587] Step 3:

[0588] The server takes the analyzed emotional state as input and generates appropriate advertising content using a generative AI model. The AI ​​is activated by the prompt "Generate an advertisement for a relaxation service suitable for when the user wants to relax." The generation process optimizes content that matches the user's current emotional state and outputs it in a specific advertisement format. For example, a special offer from a relaxation service provider might be presented to the user.

[0589] Step 4:

[0590] The server delivers the generated ad content to the user's device. At this stage, an ad delivery algorithm is used to select the optimal timing and method. The inputs are the ad content generated by the AI ​​and the user's past browsing patterns. The output is the delivery of the ad to the user's device, displayed in the form of a notification or pop-up. User actions on the device, such as ad clicks, are recorded.

[0591] Step 5:

[0592] The device acquires user responses to advertisements and provides feedback to the server. Inputs include the number of clicks and ad viewing time. This data functions as an indicator of user interest and engagement. Finally, this feedback data is sent to the server and used to optimize future ad delivery. As output, the feedback data is aggregated on the server, contributing to improvements in the ad delivery algorithm.

[0593] (Application Example 2)

[0594] 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."

[0595] A challenge in modern advertising delivery systems is the lack of personalized information presentation that takes into account the user's emotional state. Traditional systems are limited to ad delivery based on location information and usage history, making it difficult to provide ads that reflect the user's psychological state.

[0596] 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.

[0597] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, emotion recognition means for analyzing voice data and text data to identify the user's emotional state, and advertisement generation means for dynamically adjusting the information content in response to the user's emotional state. This enables optimized advertisement delivery that is tailored to the user's emotional state.

[0598] "Information registered by businesses" refers to data about products and services that advertisers and companies enter into the system.

[0599] "Personalized information presentation" refers to the display of information that is tailored to the user's specific interests and emotional state.

[0600] "Means of automatic generation" refers to methods in which a system generates information using information processing technology without human intervention.

[0601] "Location information" refers to data that indicates the user's geographical location.

[0602] "Usage history information" refers to data that shows the history of operations and actions performed by a user in the past.

[0603] "Audio data" refers to data that records the voice spoken by the user.

[0604] "Text data" refers to data that represents text or messages entered by the user.

[0605] "Emotion recognition methods" refer to methods for identifying a user's emotional state through voice and text analysis.

[0606] "Advertising generation method" refers to a method of generating and providing advertising content based on the emotional state of the user.

[0607] "Ad delivery" is the process of sending generated advertisements to users' devices at the appropriate time.

[0608] To realize this invention, a system program is constructed that performs emotion recognition and advertisement generation. The server first automatically generates personalized information presentations based on product and service information registered in a database provided by advertisers and companies. Next, the server receives geographical location information and user operation history transmitted from the terminal and analyzes the user's past behavior patterns.

[0609] The user's device collects audio data using the smartphone's microphone and text data through text input. This data is sent to a server, which uses an emotion recognition engine to identify the user's emotional state from the tone of voice and the context of the text. Specifically, it uses the Google Cloud Speech-to-Text speech recognition API to convert the audio data into text. Then, it analyzes the text data using the Google Cloud Natural Language API natural language processing model and detects emotions through IBM Watson's emotion recognition capabilities.

[0610] Once emotional information is identified, the server uses OpenAI's GPT-4 generative AI model to dynamically generate advertising content tailored to the user's emotions. In this process, prompts are used to generate appropriate advertisements based on the emotional state. For example, a prompt such as, "The user is feeling stressed; please recommend products that can help them relax," might be used.

[0611] The device receives the generated advertising content and displays the advertisement on the screen of the smartphone, which is the display device. Users can view this advertisement and, if interested, take action such as clicking on a link. The device records this response and sends it back to the server as feedback. The server analyzes this feedback information and continuously improves the advertising delivery algorithm.

[0612] This entire process makes it possible to provide personalized advertisements that are tailored to the user's emotional state, thereby increasing the effectiveness of the advertisements.

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The server retrieves data on products and services registered by businesses and stores it in a database. This data serves as the input information for future personalized information presentations.

[0616] Step 2:

[0617] The device collects geographical location information through the smartphone's location services and obtains usage history information based on the user's access logs. This input data is sent to the server.

[0618] Step 3:

[0619] The device collects user voice data using the smartphone's microphone and receives text data using the text input function. The input voice data is converted to text using Google Cloud Speech-to-Text and sent to the server.

[0620] Step 4:

[0621] The server receives the transmitted text data and performs text analysis using the Google Cloud Natural Language API. This analysis involves understanding the context of the text and extracting information necessary for sentiment recognition.

[0622] Step 5:

[0623] The server uses IBM Watson's emotion recognition technology to detect the user's emotional state from the analyzed text data. This process identifies the type and intensity of the emotion and passes the results to the next step.

[0624] Step 6:

[0625] The server uses OpenAI's generative AI model (GPT-4) to generate advertising content that matches the detected emotional state. The input to this process is emotional information, and the output is dynamically customized advertisements. The prompt used is "The user is feeling stressed; please recommend products that can help them relax."

[0626] Step 7:

[0627] The generated advertisement is sent from the server to the device and presented to the user on the smartphone screen. The user views the advertisement and generates a response by taking actions such as clicking or interacting with links.

[0628] Step 8:

[0629] The device records the user's response to advertisements and feeds this information back to the server. The server analyzes the received feedback information and uses it as data to improve the ad delivery algorithm.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] [Fourth Embodiment]

[0634] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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".

[0647] This invention provides a system for small businesses to effectively deliver personalized advertising to customers with limited resources. Embodiments thereof are described below.

[0648] The server performs central processing and receives website content and campaign information that businesses have registered in advance. This information is stored as basic data for later generation of advertising content.

[0649] The device plays a role in routinely collecting the user's location information, payment history, and application usage history, and sending this data to a server. If a user frequently visits a particular location, that location information is used to identify the user's living area.

[0650] The server analyzes the received data to recognize user behavior patterns. For example, it analyzes places users frequently visit on holidays and predicts their interest in services related to those locations. This analysis allows for an automatic understanding of user interests.

[0651] Next, the server uses a generation AI to create personalized advertising content based on the analysis results. This process utilizes information registered by the business, including, for example, announcements of new products and promotions of services. This personalized information is then configured to be delivered to the user's smartphone at the appropriate time.

[0652] User responses to delivered advertisements are recorded on the device. The device acquires data such as click-through rates and ad viewing time, and sends this data to the server as feedback. This feedback information is used to improve the ad delivery algorithm.

[0653] For example, if a user frequently visits a particular cafe, the server can deliver advertisements for the cafe's new menu items to coincide with the user's next visit. In this case, the advertisements are optimized to attract the user's interest, taking into account their visit frequency and past payment history.

[0654] This invention enables small businesses to approach customers more efficiently and accurately.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] The device collects the user's location information, app usage history, and payment history. This data is sent to the server as it is collected.

[0658] Step 2:

[0659] The server stores the data received from the terminal in a database. This allows for the storage of detailed activity history for each user.

[0660] Step 3:

[0661] The server analyzes accumulated data to predict user behavior patterns and interests. For example, it may analyze the tendency for users to visit the same store multiple times.

[0662] Step 4:

[0663] The server retrieves campaign information and website content registered by businesses and uses a generation AI to create user-optimized advertising content.

[0664] Step 5:

[0665] The server sends the generated ad content to the user's device at the optimal time. For example, it can be configured to notify the user of an ad when they enter a specific geographical area.

[0666] Step 6:

[0667] The user's device receives advertisements and records how the user reacts to them (clicks, viewing time, etc.).

[0668] Step 7:

[0669] The device sends recorded user response data to the server, which receives it as feedback.

[0670] Step 8:

[0671] The server uses the feedback information to improve its ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery.

[0672] (Example 1)

[0673] 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".

[0674] For small businesses, providing effective and personalized advertising to customers with limited resources is difficult. Existing systems struggle to deliver targeted ads based on user behavior patterns and lack feedback functions to evaluate ad effectiveness. As a result, there is a challenge in accurately delivering ads that attract user interest and continuously improving those ads.

[0675] 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.

[0676] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator; means for receiving location information and usage history information transmitted from the terminal; means for analyzing the acquired information, recognizing user behavior patterns, and making personalized behavior predictions; means for generating optimized advertising content using a generation AI model based on the analysis results; means for delivering the generated content at an appropriate time according to the user's situation; and means for recording user reactions and feeding them back into the analysis to improve the advertising delivery algorithm. This makes it possible for even small businesses to achieve effective and personalized advertising delivery with limited resources, and to further improve its accuracy.

[0677] "Information registered by businesses" refers to content and campaign information provided in advance by businesses conducting commercial activities, which the system uses to generate advertising content.

[0678] "Personalized information presentation" refers to advertisements and notifications that are created individually based on the user's behavioral data and registered information, and delivered to the user.

[0679] A "terminal" is an electronic device used to collect user location information, payment history, and application usage history, and to transmit this information to a server.

[0680] "Location information" refers to information that includes geographical data indicating that a user is located in a specific place.

[0681] "Usage history information" refers to data that includes a user's past behavioral history, payment history, and application usage history.

[0682] "Behavioral patterns" are the results of analyzing the regularity, consistency, and habits that indicate a user's daily actions and tendencies.

[0683] A "generative AI model" is an artificial intelligence system that automatically generates advertising content based on user behavior patterns and interests, using prior data learning.

[0684] "Advertising content" refers to media or messages that contain information about specific products or services and are created to attract the user's interest.

[0685] "User response" refers to behavioral data such as clicks and viewing time in response to advertisements and notifications.

[0686] An "ad delivery algorithm" is a computational method used to optimize the delivery of advertising content based on user data and responses.

[0687] This system aims to enable small businesses to effectively deliver personalized advertising with limited resources. The system analyzes users' behavioral patterns based on their location information and usage history in their daily lives, and generates advertising content using a generative AI model.

[0688] The server receives website content and campaign information registered in advance by the service provider and stores this information in a database. This information is used as basic data when generating advertisements. The device collects the user's location information using GPS functionality and also obtains payment history and application usage history. This data is necessary to understand the user's daily behavior.

[0689] The server analyzes the data sent from the terminal to recognize the user's behavior patterns. Based on these analysis results, the server uses a generative AI model to prepare prompts that create personalized advertising content. For example, a prompt could say, "Create an advertisement for an interesting new menu item at a cafe the user visits on their day off."

[0690] The generated advertising content is delivered to the device at the optimal time based on the user's location and usage history. By displaying ads on the screen based on location and time while the user is using their smartphone, a personalized advertising experience is provided.

[0691] For example, when a user is near a cafe they frequently visit, advertisements containing information about the cafe's new menu or discounts could be delivered to them in time for their next visit. In this way, advertisements optimized based on user behavior data can be delivered, enabling small businesses to attract customers more efficiently and supporting business growth.

[0692] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0693] Step 1:

[0694] The device acquires the user's daily location information using GPS functionality. The main process in this step is from the collection of location data to its transmission to the server. The input is GPS location coordinates, and the output is time-series data of these coordinates. Specifically, the device collects location information at regular intervals and temporarily stores it.

[0695] Step 2:

[0696] The terminal retrieves the user's payment history from relevant applications and digital wallets. The purpose of this step is to send the payment history data to the server. The input is a record of transactions, and the output is a historical dataset in which these are aggregated. The terminal periodically retrieves this information and automatically sends it to the server.

[0697] Step 3:

[0698] The device collects the user's application usage history. Specifically, it collects data on how frequently and for how long each application is used. The input is the application usage history log, and the output is aggregated usage statistics. The device collects this data and prepares it to be sent to the server later.

[0699] Step 4:

[0700] The server receives location information, payment history, and application usage history transmitted from the terminal. Receiving this data prepares it for analysis. The input consists of diverse user data, and the output is registration into the database. The server organizes and stores all received data according to its type.

[0701] Step 5:

[0702] The server analyzes the stored data. Specifically, it performs data processing to recognize user behavior patterns and interests. The input is the stored dataset, and the output is the behavior patterns resulting from the analysis. The server uses statistical analysis and machine learning techniques to predict user interests.

[0703] Step 6:

[0704] The server uses an AI model based on the analysis results to prepare prompt messages and generate advertising content. For example, the prompt message might be "Create an optimal cafe advertisement based on the user's behavior patterns." The input is the analyzed behavioral data, and the output is the generated advertising content. The generated content is saved for later distribution.

[0705] Step 7:

[0706] The server delivers advertising content generated according to the user's situation to the device at the appropriate time. The input is the generated advertisement and the user's real-time location information, and the output is the display of the advertisement on the device. The server adjusts the timing of ad delivery based on the user's location and time.

[0707] Step 8:

[0708] The device records how the user interacts with advertisements, such as clicks and viewing time, as response data. The input is user action information, and the output is the recorded response data. The device measures this data and prepares to send it back to the server.

[0709] Step 9:

[0710] The server receives user response data sent from the terminal and uses it to improve the ad delivery algorithm. The input is user feedback data, and the output is the updated ad delivery algorithm. The server then continuously learns from this to improve the accuracy of future ad deliveries.

[0711] (Application Example 1)

[0712] 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".

[0713] It is technically and economically challenging for small businesses to deliver effective, personalized advertising to customers with limited resources. Current large-scale advertising platforms are not sufficiently personalized, and locally-based businesses, in particular, need to deliver pinpoint, relevant information in a timely manner.

[0714] 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.

[0715] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, means for analyzing the acquired information and making personalized behavioral predictions, means for generating advertising content based on the user's interests using a generation AI, and means for delivering notifications to the user's mobile terminal in real time. This makes it possible to dynamically generate and deliver advertising content based on the user's location and interests.

[0716] "Information registered by the business operator" refers to data such as product and service details and campaign information that the business operator has registered in the system in advance in order to provide the service.

[0717] "Means for automatically generating personalized information presentations" refers to a system or algorithm that takes into account user characteristics and behavioral history to generate information and advertisements tailored to individual users.

[0718] "Location information and usage history information transmitted from the device" refers to geographical location data and records of past application usage transmitted from the user's mobile device or similar device.

[0719] "Means for analysis and personalized behavioral prediction" refers to technologies or algorithms for analyzing received data and predicting user behavior patterns.

[0720] "Methods for generating advertising content based on user interests using generative AI" refers to methods that use machine learning models or generative AI to automatically create appropriate advertising content based on the user's past behavior and interests.

[0721] "Means for delivering notifications to users' mobile devices in real time" refers to technologies or communication methods for sending information from a server to a user's mobile device in a timely manner.

[0722] The system for implementing this invention mainly includes a server, a user's mobile terminal, and a database managed by the service provider. The server has the function of holding information registered by the service provider and receiving location information and usage history information from the user's terminal. This makes it possible to predict individualized behavior based on location and activity history.

[0723] The servers run on cloud platforms such as AWS or Google Cloud and utilize generative AI models (e.g., GPT-3) to generate ad content based on user interests. These ads are personalized based on the user's past usage history and location information. The generated ads are stored in a database and delivered in real time to the user's mobile device via communication methods such as Firebase Cloud Messaging.

[0724] User responses, such as ad click-through rates and viewing time, are recorded by mobile devices and sent back to the server as feedback. The server uses this data to update and improve its behavioral prediction model.

[0725] For example, if it is determined that a user frequently visits a restaurant in a specific area, an advertisement for new menu items at that restaurant will be generated and appropriately notified during their next visit. This system allows users to receive advertisements that match their interests.

[0726] An example of a prompt message is: "Generate ads based on nearby store information and campaigns related to locations the user frequently visits. The generated ads will be based on the user's interests and past purchase history."

[0727] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0728] Step 1:

[0729] The device continuously collects the user's location information and usage history information. The input is the device's GPS data and application usage history, and the output is a data stream in which this data is packetized and sent to the server.

[0730] Step 2:

[0731] The server stores the received location information and usage history information in a database. The input is location information and usage history information sent from the terminal, and the output is the storage operation into the database. During this process, the validity and integrity of the data are checked.

[0732] Step 3:

[0733] The server analyzes information in the database to identify user behavior patterns. Inputs are stored location data and usage history, and output is an update to the user behavior prediction model. The analysis is performed using an AI model to extract frequently visited locations and usage patterns.

[0734] Step 4:

[0735] The server uses a generative AI model to generate advertising content based on user behavior patterns and interests. Input is data from the behavioral prediction model and information registered by the business, and output is personalized advertising content. The generated ads include campaign information but are edited to match the user's preferences.

[0736] Step 5:

[0737] The server delivers generated advertising content to the user's device in real time. The input is advertising content, and the output is in the form of a push notification to the device. Reliable delivery is ensured using Firebase Cloud Messaging.

[0738] Step 6:

[0739] The user's device records their response to received advertisements. Input is the user's activity log (ad click-through rate and viewing time), and output is feedback data sent to the server. This provides data that allows for a more accurate understanding of user interests and other factors.

[0740] Step 7:

[0741] The server analyzes feedback data to improve the behavioral prediction model and ad generation algorithm. The input is user feedback data, and the output is the updated behavioral prediction model and ad generation parameters. This continuous improvement leads to more accurate ad delivery.

[0742] 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.

[0743] This invention provides an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This enables small businesses to deliver more personalized advertisements and achieve a more nuanced approach based on user responses.

[0744] The server first acquires information and campaign data provided by the service provider and uses this to create the content that forms the basis of the advertisement. The device continues to acquire normal location information and usage history, and in addition, it collects the user's voice and text data.

[0745] The collected data is analyzed by the server, and the user's emotional state is identified using an emotion engine. The emotion engine analyzes voice tone and text context to determine the type of emotion the user is currently experiencing (e.g., joy, sadness, surprise). This emotional data is added to the analysis results and reflected in the user behavior prediction model.

[0746] Next, the server uses this emotional information to create customized advertising content adapted to the user's emotions using generative AI. For example, if the user is feeling stressed, it can suggest advertisements for relaxation services that can alleviate that stress.

[0747] Once the content is created, the server delivers the ad to the user's device at the optimal time. The user views the ad on their device and takes action as needed. The device also records the user's response to the ad, such as the time spent clicking on the ad or viewing details.

[0748] These responses are fed back to the server and used to improve the ad delivery algorithm. For example, if a user accesses the site at the end of the workday when they are stressed, the emotion engine detects this information and provides ads for products specifically designed for relaxation, making it easier to capture the user's interest.

[0749] Thus, by taking into account the user's emotional state, the present invention achieves even more precise personalization and contributes to effective marketing by businesses.

[0750] The following describes the processing flow.

[0751] Step 1:

[0752] The device collects the user's location information, app usage history, and voice and text data. In particular, it pays attention to the tone and intensity of conversations when collecting voice data, and sends appropriate data to the server.

[0753] Step 2:

[0754] The server stores location information, usage history, and voice / text data received from the terminal in a database. This allows for the recording of detailed behavioral and emotional history for each user.

[0755] Step 3:

[0756] The server analyzes the accumulated data and uses an emotion engine to identify the user's emotional state. For example, a high tone of voice is interpreted as excitement, while a low tone is interpreted as depression.

[0757] Step 4:

[0758] Based on the emotional data obtained from the emotion engine, the server updates the user behavior prediction model. During this process, the behavioral patterns are adjusted according to the user's current emotional state.

[0759] Step 5:

[0760] The server retrieves information registered by businesses and campaign details, and uses a generation AI to create personalized advertising content tailored to the user's emotional state. For example, if a user is in a somewhat unstable emotional state, it will create relaxation-related advertisements.

[0761] Step 6:

[0762] The server delivers the generated advertising content to the user's device at the most effective time, optimizing notifications based on specific time periods and location information.

[0763] Step 7:

[0764] Users receive advertisements on their devices and review their content. The device records behavioral data (clicks, time spent viewing details, etc.) about how the user reacts to the advertisements.

[0765] Step 8:

[0766] The device sends recorded user response data to the server, which receives it as feedback.

[0767] Step 9:

[0768] The server uses the feedback information to improve the ad delivery algorithm and utilize it for future ad deliveries. This enables more accurate ad delivery that incorporates emotional data.

[0769] (Example 2)

[0770] 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".

[0771] Traditional advertising delivery systems have faced the challenge of being unable to deliver advertisements tailored to the emotional state of individual users, thus failing to maximize the effectiveness of advertising. As a result, advertisements fail to attract user attention, and consequently, they do not effectively boost the sales of businesses.

[0772] 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.

[0773] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information, usage history, and emotion data transmitted from the terminal, and means for analyzing the acquired voice and text data and identifying the emotional state using an emotion engine. This enables accurate advertising delivery based on the user's emotional state.

[0774] A "business operator" is an entity that uses the system to provide advertisements or informational content, and is responsible for managing registration information within the system.

[0775] "Personalized information presentation" is the process of providing customized information and advertisements to each user, generating content that is tailored to the user's attributes and current emotional state.

[0776] A "terminal" is a device that users directly operate and use to exchange information, and it is responsible for collecting location information, usage history, voice and text data and sending it to the server.

[0777] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from their voice tone and text context, and is used to customize advertising content.

[0778] An "emotion engine" is a software module that analyzes collected data and identifies the user's emotional state from voice, text, and other sources.

[0779] A "generative AI model" is a pre-trained algorithm that has the ability to automatically generate advertising content tailored to the user's attributes and emotional state.

[0780] An "ad delivery algorithm" is a series of methods that implement a process to analyze user behavior data and emotional data to determine when and which advertisements should be delivered.

[0781] "Feedback" is the process of returning user response data to the server to help improve the accuracy and customization of the system in the future.

[0782] This invention includes an advertising delivery system that incorporates an emotion engine that recognizes user emotions. This system has the function of generating and delivering personalized advertisements that correspond to the user's emotional state, based on information registered by the business operator.

[0783] The server acquires campaign information and product data provided by businesses and creates the basic data for advertising content. The server receives user location information, usage history, voice, and text data from the device. The device collects this data using hardware such as sensors, microphones, and text input.

[0784] The server analyzes the acquired data and uses an emotion engine to identify the user's emotional state from changes in voice tone and text content. The emotion engine used here is a software module that includes acoustic analysis and natural language processing algorithms.

[0785] Next, the server uses a generative AI model to generate advertising content that is best suited to the analyzed emotional state. The generative AI model is an algorithm pre-trained to adapt to the user's emotions. An example of a prompt is, "Generate an advertisement for a relaxation service that is appropriate when the user is feeling stressed."

[0786] Ultimately, the server delivers the generated advertisements to the user's device at the appropriate time. Users can view the advertisements on their devices and take the necessary actions. The device records the user's response and feeds this information back to the server. This feedback is used to improve the ad delivery algorithm, enhancing the accuracy of future advertisements. This enables more effective marketing that responds to the user's emotions.

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] The device collects user location information, app usage history, and voice and text data. Inputs include data from the GPS sensor, microphone, and keyboard. This data is acquired in real time and stored on the device in various formats. For example, if the user says, "I want to go to a nearby cafe," voice data is collected. As output, this data is prepared to be sent to a server.

[0790] Step 2:

[0791] The server receives location information, usage history, and voice and text data transmitted from the terminal. This data itself is provided as input. The server then processes the voice data with a speech recognition engine and analyzes the context of the text data using natural language processing. This process determines the user's emotional state. For example, it analyzes background sounds in the voice and keywords in the text to determine whether the user wants to relax or is excited. The analysis results are output as the user's emotional state.

[0792] Step 3:

[0793] The server takes the analyzed emotional state as input and generates appropriate advertising content using a generative AI model. The AI ​​is activated by the prompt "Generate an advertisement for a relaxation service suitable for when the user wants to relax." The generation process optimizes content that matches the user's current emotional state and outputs it in a specific advertisement format. For example, a special offer from a relaxation service provider might be presented to the user.

[0794] Step 4:

[0795] The server delivers the generated ad content to the user's device. At this stage, an ad delivery algorithm is used to select the optimal timing and method. The inputs are the ad content generated by the AI ​​and the user's past browsing patterns. The output is the delivery of the ad to the user's device, displayed in the form of a notification or pop-up. User actions on the device, such as ad clicks, are recorded.

[0796] Step 5:

[0797] The device acquires user responses to advertisements and provides feedback to the server. Inputs include the number of clicks and ad viewing time. This data functions as an indicator of user interest and engagement. Finally, this feedback data is sent to the server and used to optimize future ad delivery. As output, the feedback data is aggregated on the server, contributing to improvements in the ad delivery algorithm.

[0798] (Application Example 2)

[0799] 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".

[0800] A challenge in modern advertising delivery systems is the lack of personalized information presentation that takes into account the user's emotional state. Traditional systems are limited to ad delivery based on location information and usage history, making it difficult to provide ads that reflect the user's psychological state.

[0801] 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.

[0802] In this invention, the server includes means for automatically generating personalized information presentations based on information registered by the business operator, means for receiving location information and usage history information transmitted from the terminal, emotion recognition means for analyzing voice data and text data to identify the user's emotional state, and advertisement generation means for dynamically adjusting the information content in response to the user's emotional state. This enables optimized advertisement delivery that is tailored to the user's emotional state.

[0803] "Information registered by businesses" refers to data about products and services that advertisers and companies enter into the system.

[0804] "Personalized information presentation" refers to the display of information that is tailored to the user's specific interests and emotional state.

[0805] "Means of automatic generation" refers to methods in which a system generates information using information processing technology without human intervention.

[0806] "Location information" refers to data that indicates the user's geographical location.

[0807] "Usage history information" refers to data that shows the history of operations and actions performed by a user in the past.

[0808] "Audio data" refers to data that records the voice spoken by the user.

[0809] "Text data" refers to data that represents text or messages entered by the user.

[0810] "Emotion recognition methods" refer to methods for identifying a user's emotional state through voice and text analysis.

[0811] "Advertising generation method" refers to a method of generating and providing advertising content based on the emotional state of the user.

[0812] "Ad delivery" is the process of sending generated advertisements to users' devices at the appropriate time.

[0813] To realize this invention, a system program is constructed that performs emotion recognition and advertisement generation. The server first automatically generates personalized information presentations based on product and service information registered in a database provided by advertisers and companies. Next, the server receives geographical location information and user operation history transmitted from the terminal and analyzes the user's past behavior patterns.

[0814] The user's device collects audio data using the smartphone's microphone and text data through text input. This data is sent to a server, which uses an emotion recognition engine to identify the user's emotional state from the tone of voice and the context of the text. Specifically, it uses the Google Cloud Speech-to-Text speech recognition API to convert the audio data into text. Then, it analyzes the text data using the Google Cloud Natural Language API natural language processing model and detects emotions through IBM Watson's emotion recognition capabilities.

[0815] Once emotional information is identified, the server uses OpenAI's GPT-4 generative AI model to dynamically generate advertising content tailored to the user's emotions. In this process, prompts are used to generate appropriate advertisements based on the emotional state. For example, a prompt such as, "The user is feeling stressed; please recommend products that can help them relax," might be used.

[0816] The device receives the generated advertising content and displays the advertisement on the screen of the smartphone, which is the display device. Users can view this advertisement and, if interested, take action such as clicking on a link. The device records this response and sends it back to the server as feedback. The server analyzes this feedback information and continuously improves the advertising delivery algorithm.

[0817] This entire process makes it possible to provide personalized advertisements that are tailored to the user's emotional state, thereby increasing the effectiveness of the advertisements.

[0818] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0819] Step 1:

[0820] The server retrieves data on products and services registered by businesses and stores it in a database. This data serves as the input information for future personalized information presentations.

[0821] Step 2:

[0822] The device collects geographical location information through the smartphone's location services and obtains usage history information based on the user's access logs. This input data is sent to the server.

[0823] Step 3:

[0824] The device collects user voice data using the smartphone's microphone and receives text data using the text input function. The input voice data is converted to text using Google Cloud Speech-to-Text and sent to the server.

[0825] Step 4:

[0826] The server receives the transmitted text data and performs text analysis using the Google Cloud Natural Language API. This analysis involves understanding the context of the text and extracting information necessary for sentiment recognition.

[0827] Step 5:

[0828] The server uses IBM Watson's emotion recognition technology to detect the user's emotional state from the analyzed text data. This process identifies the type and intensity of the emotion and passes the results to the next step.

[0829] Step 6:

[0830] The server uses OpenAI's generative AI model (GPT-4) to generate advertising content that matches the detected emotional state. The input to this process is emotional information, and the output is dynamically customized advertisements. The prompt used is "The user is feeling stressed; please recommend products that can help them relax."

[0831] Step 7:

[0832] The generated advertisement is sent from the server to the device and presented to the user on the smartphone screen. The user views the advertisement and generates a response by taking actions such as clicking or interacting with links.

[0833] Step 8:

[0834] The device records the user's response to advertisements and feeds this information back to the server. The server analyzes the received feedback information and uses it as data to improve the ad delivery algorithm.

[0835] 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.

[0836] 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.

[0837] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0838] 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.

[0839] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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."

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0856] The following is further disclosed regarding the embodiments described above.

[0857] (Claim 1)

[0858] A means of automatically generating personalized information presentations based on information registered by businesses,

[0859] A means for receiving location information and usage history information transmitted from a terminal,

[0860] A means of analyzing acquired information and making personalized behavioral predictions,

[0861] A means of delivering relevant notifications at the appropriate time based on the analysis results,

[0862] A means of recording user reactions and feeding them back into analysis,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, characterized by comprising means for learning a behavior prediction model based on data analysis.

[0866] (Claim 3)

[0867] The system according to claim 1, characterized in that it has means for generating dynamically updated content based on new information provided by a business operator.

[0868] "Example 1"

[0869] (Claim 1)

[0870] A means of automatically generating personalized information presentations based on information registered by businesses,

[0871] A means for receiving location information and usage history information transmitted from a terminal,

[0872] A means for analyzing acquired information, recognizing user behavior patterns, and making personalized behavioral predictions,

[0873] A means of generating optimized advertising content using a generation AI model based on analysis results,

[0874] A means of delivering generated content at the appropriate time according to the user's situation,

[0875] A means of recording user responses and feeding them back into analysis to improve ad delivery algorithms,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, characterized by comprising means for learning a behavioral prediction model based on data analysis and improving the accuracy of ad delivery.

[0879] (Claim 3)

[0880] The system according to claim 1, characterized in that it has means for generating dynamically updated content based on new information provided by a business operator and optimizing it to attract user interest using a generation AI model.

[0881] "Application Example 1"

[0882] (Claim 1)

[0883] A means of automatically generating personalized information presentations based on information registered by businesses,

[0884] A means for receiving location information and usage history information transmitted from a terminal,

[0885] A means of analyzing acquired information and making personalized behavioral predictions,

[0886] A means of delivering relevant notifications at the appropriate time based on the analysis results,

[0887] A means of recording user reactions and feeding them back into analysis,

[0888] A method for generating advertising content based on user interests using generative AI,

[0889] A means of delivering notifications to users' mobile devices in real time,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, comprising means for learning a behavioral prediction model based on data analysis, and means for dynamically generating content based on the user's location and interests.

[0893] (Claim 3)

[0894] The system according to claim 1, which has means for generating dynamically updated content based on new information provided by a business operator, and further means for delivering personalized special offer information for a specific region based on the user's location and past behavioral history.

[0895] "Example 2 of combining an emotion engine"

[0896] (Claim 1)

[0897] A means of automatically generating personalized information presentations based on information registered by businesses,

[0898] A means for receiving location information, usage history, and sentiment data transmitted from a terminal,

[0899] A means for analyzing acquired audio and text data and identifying emotional states using an emotion engine,

[0900] A means for generating customized content adapted to the user's emotions using a generative AI model based on the analysis results,

[0901] A means for delivering the generated content to the user's device at the appropriate time,

[0902] A means of recording user responses to advertisements and providing feedback to improve ad delivery algorithms,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, characterized by comprising means for learning and updating an action prediction model based on acquired data.

[0906] (Claim 3)

[0907] The system according to claim 1, characterized in that it has means for generating dynamically updated advertising content based on new information provided by the business operator.

[0908] "Application example 2 when combining with an emotional engine"

[0909] (Claim 1)

[0910] A means of automatically generating personalized information presentations based on information registered by businesses,

[0911] A means for receiving location information and usage history information transmitted from a terminal,

[0912] A means of analyzing acquired information and making personalized behavioral predictions,

[0913] A means of delivering relevant notifications at the appropriate time based on the analysis results,

[0914] An emotion recognition means that analyzes voice data and text data to identify the user's emotional state,

[0915] An advertising generation method that dynamically adjusts the information content in response to the user's emotional state,

[0916] Means for transmitting the generated advertisement to a display device,

[0917] A means of recording user reactions and feeding them back into analysis,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, characterized by comprising means for learning a behavioral prediction model and an emotion prediction model based on data analysis.

[0921] (Claim 3)

[0922] The system according to claim 1, characterized in that it has means for generating dynamically updated content based on new information provided by a business operator and optimizing it according to emotion recognition. [Explanation of Symbols]

[0923] 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 automatically generating personalized information presentations based on information registered by businesses, A means for receiving location information and usage history information transmitted from a terminal, A means of analyzing acquired information and making personalized behavioral predictions, A means of delivering relevant notifications at the appropriate time based on the analysis results, A means of recording user reactions and feeding them back into analysis, A system that includes this.

2. The system according to claim 1, characterized in that it includes means for learning a behavior prediction model based on data analysis.

3. The system according to claim 1, characterized in that it has means for generating dynamically updated content based on new information provided by a business operator.

Images