system

Abstract

We provide the system. [Solution] A device for collecting customer data, A device for integrating and standardizing the data collected by the said device, A device that uses a generative model to analyze integrated data, A device for designing an advertising delivery strategy using the generative model, A device that delivers advertisements in real time, A device that measures the effectiveness of a campaign and generates improvement suggestions, A marketing system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0001] The technology of this 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] Due to the strengthening of consumer privacy regulations, the use of third-party data that has been used so far is being restricted. Also, although first-party data can be collected, the subsequent utilization methods of the data are unclear, and it is difficult to formulate an effective marketing strategy that leads to actual purchases and behaviors. For this reason, companies are required to optimize advertising costs and implement effective campaigns, but the lack of data integration and analysis capabilities to achieve this is an issue.

Means for Solving the Problems

[0005] This invention provides a means for collecting customer data, integrating and standardizing it, and then analyzing it using a generative model. This enables the maximum utilization of collected first-party data and the design of real-time advertising delivery strategies. Furthermore, it provides personalized information to users on the terminals where advertisements are delivered, measures the effectiveness of campaigns based on the results, and generates improvement suggestions for future measures. By building such a data-driven marketing system, companies can simultaneously achieve optimization of advertising spending, promotion of purchasing behavior, and improvement of the customer experience.

[0006] "Customer data" refers to data that companies collect directly from their customers, such as purchase history and communication information.

[0007] The term "device" refers to a mechanical or electronic system designed to perform a specific function.

[0008] A "generative model" is an algorithm used in machine learning to predict future data and trends based on input data.

[0009] An "advertising delivery strategy" is a plan that determines what kind of promotion to run for a specific target audience, on which media, and at what time.

[0010] "Real-time" refers to a processing method where data is processed as soon as it is generated, and the results can be obtained immediately.

[0011] A "campaign" refers to a series of activities planned and executed to achieve a specific promotional objective.

[0012] "Data-driven" refers to an approach to decision-making and strategy formulation that involves making logical and objective judgments based on data. [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] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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 is a marketing system that collects first-party data, integrates and analyzes it to optimize ad delivery. In this system, the server, terminal, and user each play a specific role.

[0035] First, the server has the capability to efficiently collect customer data held by companies. This data includes customer purchase history and communication history, and is securely and efficiently stored in a database using APIs. The collected data is unified, standardized, and integrated by the customer data platform, which handles data in different formats.

[0036] Next, the server analyzes the integrated data using a generative model. This generative model uses machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising delivery strategy is formulated for each customer. The generative model translates the data analysis results into specific advertising campaign suggestions, and personalized advertisements are designed based on this information.

[0037] In ad delivery, the device plays a crucial role. The device has the ability to deliver ads to users in real time based on instructions received from the server. In this process, the device displays more relevant ads based on geographical location information and past behavioral history. For example, if a user is near a store they frequently visit, information about special campaigns at that store can be immediately provided, stimulating their desire to purchase.

[0038] Finally, the server measures the effectiveness of the ads and campaigns implemented and generates feedback through data analysis to improve future strategies. This allows companies to quickly adjust their advertising strategies and conduct lean marketing activities.

[0039] In this way, the present invention makes it possible to realize effective marketing strategies while complying with privacy regulations.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects customer data from various corporate data sources via APIs. This data includes purchase history, communication logs, and customer profile information. The collected data is stored in temporary storage.

[0043] Step 2:

[0044] The server integrates data collected using the customer data platform. It standardizes data from different formats and sources, removes duplicate data, and generates a consistent dataset.

[0045] Step 3:

[0046] The server inputs the integrated data into a generative model for analysis. The generative model uses machine learning algorithms to predict customer purchasing trends and behavior, and determines advertising targets for each segment.

[0047] Step 4:

[0048] The server designs an advertising delivery strategy based on the analysis results of the generative model. In this process, it selects the optimal creative and channel for the target segment and develops an implementation plan.

[0049] Step 5:

[0050] The device displays ads to the user in real time, following the ad delivery plan instructed by the server. The device selects the most relevant ads, taking into account location information and the user's viewing history.

[0051] Step 6:

[0052] Users receive advertisements and campaigns displayed on their devices. If they are interested in this information, they can obtain more detailed information or coupons and then initiate a purchase.

[0053] Step 7:

[0054] The server aggregates the results of advertising campaigns and measures their effectiveness. For example, it analyzes click-through rates and conversion rates to build a feedback loop that helps improve future ad campaigns.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] Conventional information distribution systems have struggled to effectively utilize individual users' interests and behavioral history to provide optimal information tailored to each situation in real time. Furthermore, they lacked the functionality to quickly measure the results of information distribution and use that data to improve future strategies.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting information, means for integrating and standardizing said information, and means for analyzing the integrated information using a generation AI model. This enables real-time delivery of information tailored to each user's behavior and interests, and allows for efficient and continuous improvement of the information delivery strategy.

[0060] "Means of collecting information" refers to devices and methods for obtaining necessary information from databases or external information sources.

[0061] "Means for integrating and standardizing the information" refers to the process of converting collected information from different formats into a single format and compiling it while maintaining consistency.

[0062] "Analysis using generative AI models" refers to a method of predicting data trends and patterns using machine learning algorithms and deriving results from them.

[0063] "Designing an information distribution strategy" is the process of determining, based on analysis results, how, when, and where to deliver the most appropriate information to individual users.

[0064] "A means of delivering information in real time and displaying information based on location information and behavioral history" refers to a system that takes into account the user's current geographical location and past behavioral patterns to provide timely and relevant information.

[0065] "Methods for measuring the effectiveness of information distribution and generating improvement suggestions" refers to methods for evaluating the results of distributed information and indicating areas for improvement in future information distribution strategies.

[0066] To implement this invention, the server first plays the role of collecting information from various sources. For example, it retrieves necessary data from corporate databases and external public databases via an internet connection. The retrieved data is stored on the server in a secure manner using a database management system or API technology.

[0067] Next, the server performs a process to integrate and standardize the collected data. This integration uses a data platform, which converts data in different formats into a single format and performs transformation processes to ensure consistency. Specific examples include unifying date data in different formats and standardizing currency units.

[0068] Subsequently, the server analyzes the integrated data using a generative AI model. This model implements machine learning algorithms to analyze large datasets and predict customer behavior patterns and trends. The results of the analysis are used to design an information distribution strategy. From these results, the most relevant information for the user is selected. For example, if a user has frequently purchased a particular product in the past, new offers related to that product will be prepared.

[0069] Next, the terminal plays a crucial role in the information distribution stage. Based on instructions from the server, it provides information in real time, taking into account the user's location and past behavioral history. For example, if a user is in a specific area, the terminal will display promotional information for stores in that area. This allows users to receive more personalized information.

[0070] Finally, the server measures the effectiveness of the delivered information and generates feedback to improve future information delivery strategies. Effectiveness measurements include ad impressions, click-through rates, and conversion rates. By analyzing this data, companies can evaluate the effectiveness of their information strategies and use this information to develop future initiatives.

[0071] A concrete example of a prompt message is, "Based on the purchase history of online sports equipment buyers, please propose a strategy for designing the next promotional campaign." In this way, this invention makes it possible to implement an effective information strategy while complying with privacy regulations.

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

[0073] Step 1:

[0074] The server collects information from corporate databases and publicly available sources. Input is data accessible via the internet, and output is the collected raw data. Specifically, the server uses APIs to securely download customer purchase and communication history and store it in a database.

[0075] Step 2:

[0076] The server integrates and standardizes the collected raw data. The input is the raw data obtained in step 1, and the output is consistent, integrated data. The data platform is used to unify data in different formats, perform format conversions, and eliminate duplication.

[0077] Step 3:

[0078] The server analyzes the integrated data using a generation AI model. The input is the integrated data generated in step 2, and the output is the analysis results showing customer behavior patterns and purchasing trends. Specifically, it applies machine learning algorithms to predict trends based on purchase frequency and interests.

[0079] Step 4:

[0080] The server designs an information distribution strategy based on the analysis results. The input is the analysis results from step 3, and the output is an information distribution plan optimized for the user. The server determines which information to distribute and when, according to the strategy proposed by the generative AI model.

[0081] Step 5:

[0082] The terminal receives instructions from the server and displays information to the user in real time. The input is the information distribution plan determined in step 4, and the output is the specific information displayed to the user. The terminal considers the user's location and past behavior history to display appropriate information.

[0083] Step 6:

[0084] The server measures the effectiveness of information distribution and generates feedback for future strategies. The input is performance data of the distributed information (e.g., click-through rate and conversion rate), and the output is improvement suggestions. This allows companies to distribute information more efficiently in the future.

[0085] (Application Example 1)

[0086] 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."

[0087] In modern digital marketing, consumers are exposed to a vast amount of information, making it challenging to maximize the effectiveness of advertising. In particular, there is a need for methods to deliver personalized advertising based on individual user interests in real time. However, traditional methods struggle to efficiently integrate and standardize data, and to perform real-time analysis and delivery. Furthermore, ensuring privacy remains a crucial challenge.

[0088] 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.

[0089] In this invention, the server includes means for collecting customer information, means for integrating and standardizing the information collected by said means, and means for using a generative model to analyze the integrated information. This enables the real-time delivery of personalized advertisements based on location information and behavioral history, as well as the measurement of campaign effectiveness and the suggestion of improvements.

[0090] "Customer information" refers to data collected by companies, such as individual attributes, purchase history, interests, and behavioral history.

[0091] "Integration" refers to combining data of different formats and types into a single, unified dataset.

[0092] "Standardization" refers to unifying data formats and preparing them in a way that makes them easier to process and analyze.

[0093] A "generative model" is a model that uses machine learning algorithms to analyze data and make predictions or suggestions.

[0094] "Advertising planning" is the process of designing a strategy for how to deploy advertising based on specified conditions.

[0095] "Location information" refers to data that indicates the geographical location of a device or user.

[0096] "Activity history" refers to a record of actions and movements performed by a user both online and offline.

[0097] "Real-time" refers to situations where information or actions are performed almost instantly.

[0098] "Effectiveness measurement" is the analysis used to evaluate the performance of a campaign or advertisement that has been implemented.

[0099] An "improvement suggestion" is a specific proposal to improve future measures based on the measurement results.

[0100] The system implementing this invention primarily consists of three parties: a server, a terminal, and a user. The server efficiently collects, integrates, and standardizes customer information. This includes utilizing a secure database via an API. The server passes the integrated information to a generative AI model, which is used to analyze customer purchasing trends and interests. This generative AI model uses machine learning modules and forms a crucial foundation for advertising planning that drives the next steps.

[0101] The advertising plan proposed by the generative model is sent to the device. The device then uses location services and past behavioral history to deliver the most relevant ads to the user in real time. Specifically, advertising information is seamlessly notified via smartphones and smart glasses. For example, when a user approaches a particular store, they are immediately notified of special campaigns at that store.

[0102] Furthermore, the server measures the performance of delivered ads and campaigns and performs data analysis to inform future strategies. This eliminates waste in marketing activities and enables effective strategic adjustments.

[0103] As a concrete example, by notifying users who visit shopping malls near them on weekends in real time about special sales from fashion brands, it is possible to encourage them to visit the stores. This implementation is useful not only because it improves the user's purchasing experience, but also because it improves the sales effectiveness of the stores.

[0104] An example of a prompt for a generative AI model would be: "Based on the user's interests, please generate advertisements for the products and services most relevant to their current location."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server collects customer information from companies via APIs. It receives customer information such as purchase history and communication history as input and securely stores it in a database. This integrates the company's accumulated customer information within the server, preparing it for use in subsequent processing.

[0108] Step 2:

[0109] The server integrates the collected customer information and standardizes the data format. It receives customer data in different formats as input, transforms and integrates them to generate a consistent dataset. This standardized data becomes available for analysis in the generated AI models.

[0110] Step 3:

[0111] The server analyzes integrated data using a generative AI model. Using standardized customer data as input, it applies machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising plan is developed for each customer, and instructions are sent to the terminal.

[0112] Step 4:

[0113] The device delivers ads to users in real time based on the advertising plan received from the server. It uses the user's location information and past behavioral history as input, selecting and displaying appropriate ads based on this information. This ensures that users receive the most relevant ads in a timely manner.

[0114] Step 5:

[0115] The server measures the effectiveness of implemented advertising campaigns. It receives performance data from delivered ads as input and performs analysis. Based on this analysis, feedback is generated to improve future advertising strategies, enabling companies to streamline their marketing activities.

[0116] 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.

[0117] This invention is a marketing system that optimizes ad delivery by collecting first-party data and recognizing the user's emotional state using an emotion engine. This system consists primarily of a server, a terminal, and the user.

[0118] First, the server collects customer data from multiple data sources within the company via APIs. This data includes purchase history, communication history, and data to capture the user's emotional state. Emotional data is obtained using techniques such as analyzing voice tone and facial expressions. This data is stored in a database and integrated through the customer data platform.

[0119] Next, on the server, the integrated data is analyzed by a generative model. This model utilizes machine learning algorithms to predict not only customer purchasing intent and behavioral trends, but also their emotional state based on emotional data. Based on these analysis results, an emotion engine operates to design an optimal advertising delivery strategy tailored to the user's emotions.

[0120] The device handles ad delivery. Based on the ad delivery plan received from the server, the device presents ads to the user in real time. Here, the device reflects the user's emotional state as recognized by the emotion engine and customizes the ad content and frequency accordingly. For example, when a user is feeling stressed, it displays ads suggesting products with relaxing effects, thus conducting promotions tailored to the user's emotional state.

[0121] Users can react to advertisements displayed on their devices. They can click links to learn more about ads that interest them, or use coupons provided to purchase products.

[0122] Finally, the server measures the effectiveness of the advertising campaign and generates feedback on areas for improvement to increase the success rate. This allows the system to adjust future ad delivery strategies, enabling more sophisticated targeting and personalization.

[0123] In this way, the present invention improves the accuracy of advertising and maximizes marketing effectiveness through advanced customer service combined with emotion recognition technology.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The server collects customer data from various data sources within the company using APIs. This includes purchase history, communication logs, and user sentiment data, which is obtained using voice analysis and facial recognition technology. The collected data is temporarily stored in a database.

[0127] Step 2:

[0128] The server integrates data collected using the customer data platform. It standardizes different data formats and removes duplicate data. The integrated dataset should contain information useful for understanding user behavior and emotional states.

[0129] Step 3:

[0130] The server inputs integrated data into a generative model for analysis. The generative model uses machine learning to predict customer purchasing trends and emotional states. This analysis includes reflecting emotional data in real time and determining which advertisements are effective in which situations.

[0131] Step 4:

[0132] The server uses the analysis results obtained from the generative model to enable the emotion engine to design an ad delivery strategy that is tailored to the user's emotional state. This strategy includes the content, timing, and frequency of the ads and is designed to adapt to the user's current emotions.

[0133] Step 5:

[0134] The device displays ads to the user in real time based on the ad delivery strategy provided by the server. The device selects and displays the appropriate ad content at the optimal time based on the user's location information and feedback from the sentiment engine.

[0135] Step 6:

[0136] Users receive advertisements and suggestions displayed on their devices and can click or tap on ads that interest them to view details. They can then use coupons for products they are interested in and proceed to make a purchase.

[0137] Step 7:

[0138] The server collects results after ad delivery and performs campaign effectiveness analysis. It measures ad effectiveness considering the impact of emotions and generates improvement suggestions to reflect in future ad delivery strategies. The goal is to continuously improve ad performance.

[0139] (Example 2)

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

[0141] In modern marketing, there is a demand for targeted advertising that responds to the diverse needs and emotional states of consumers. However, traditional methods have faced challenges in designing optimal advertising strategies due to insufficient analysis of collected data and inadequate personalization for individual consumers. A new system is needed to deliver more targeted advertising and increase consumer purchasing intent.

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

[0143] In this invention, the server includes means for collecting data, means for standardizing the aggregated data, and means for utilizing generative models for analysis. This enables the creation of accurate advertising strategies based on consumer sentiment and the delivery of personalized advertisements in real time.

[0144] "Means of data collection" refers to the technical processes for obtaining necessary information from various data sources.

[0145] "Methods for standardizing aggregated data" refer to methods for transforming collected data into a consistent format and preparing it in a way that facilitates analysis.

[0146] "Methods of using generative models" refer to techniques that utilize artificial intelligence and machine learning technologies to analyze data and generate patterns and predictions.

[0147] "Methods for building advertising strategies based on emotional information" refers to the process of analyzing consumers' emotional states and designing strategies to effectively deliver advertisements that correspond to those states.

[0148] A "means of presenting advertisements in real time" refers to a system that displays advertisements to consumers instantly without any time delay.

[0149] "Methods for measuring campaign effectiveness and generating improvement suggestions" refers to the process of analyzing the results of advertising activities and making suggestions for future activities based on that data.

[0150] "Behavioral information" refers to data about consumer behavior, such as consumer purchase history and website browsing history.

[0151] "Personalized advertising" refers to advertisements that are customized to the preferences and needs of each individual consumer.

[0152] "Diverse data sources" refers to different information sources, such as customer information provided by companies and data obtained from online platforms.

[0153] A "customer information platform" is a system that centrally manages and analyzes diverse customer data.

[0154] This invention is an advanced marketing system that personalizes advertisements based on the emotional state of consumers and presents them at the appropriate time. This system consists primarily of a server, terminals, and users.

[0155] The server collects consumer behavior information from various data sources via APIs. This data includes purchase history, communication history, and emotional data derived from voice tone and facial expression analysis. The server integrates this data into a database and manages it centrally using a customer information platform. In this process, voice recognition software and image analysis software are used to convert the data into a standardized format.

[0156] Using integrated data, the server employs generative AI models to analyze consumer behavior patterns and emotional states. This allows the server to build an advertising delivery strategy best suited to the customer's current emotions. The emotion engine optimizes the ad content, timing, and frequency based on the analysis results. For example, if a consumer is feeling stressed, the server will create an ad suggesting products with relaxing effects.

[0157] The device displays advertisements to consumers in real time based on the ad delivery plan received from the server. The device constantly communicates with the server, reflecting the latest sentiment data to display the most relevant advertising information.

[0158] Users can react to advertisements displayed on their devices. By clicking on an ad that interests them, they can obtain more information and even use coupons to purchase products. This improves the consumer experience and maximizes the effectiveness of advertising.

[0159] As a concrete example, if the server detects that a consumer is in a relaxed emotional state, an advertisement for a relaxing aromatherapy product will be displayed on the device. If the user clicks on the advertisement and checks the details on the product page, a coupon will be offered, which can encourage them to make a purchase.

[0160] An example of a prompt from this system is, "How can I design a model that integrates customer data and delivers the most relevant ads in real time based on the customer's emotional state?" This prompt serves as a guideline when utilizing generative AI models.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The server collects consumer behavior information from various data sources via APIs. Inputs include raw data such as purchase history, voice tone, and facial expressions. This data is analyzed using speech recognition and image analysis software, and the output is converted into a standardized format. Specifically, the server captures data in real time and immediately saves it to the database.

[0164] Step 2:

[0165] The server integrates the aggregated data into the customer information platform and prepares the dataset. The input is the standardized data set obtained in step 1. Using a unification technique, it outputs integrated information for each customer. Specifically, it unifies different data formats, performs cleanup processing, and then restores the data in the database.

[0166] Step 3:

[0167] The server uses integrated data to perform analysis with a generative AI model. The input is the integrated customer data obtained in step 2. The model predicts the customer's emotional state and behavioral patterns and outputs the analysis results. Specifically, it utilizes machine learning algorithms to perform cluster analysis and regression analysis on the data to generate prediction results.

[0168] Step 4:

[0169] The server activates an emotion engine based on the analysis results and designs user-specific ad delivery strategies. The input is the predictive analysis results from step 3. Here, strategies such as ad content and delivery frequency that take emotional states into account are obtained as output. Specifically, a template is used to design a scenario and generate a strategy document.

[0170] Step 5:

[0171] The device displays advertisements in real time based on the ad delivery plan received from the server. The input is the ad delivery plan from step 4. The goal is to instantly display the appropriate advertisement to the user, and the ad display results are output. Specifically, the advertisement is displayed to the user using the display or push notification.

[0172] Step 6:

[0173] Users can react to advertisements displayed on their devices. The input is the advertisement itself displayed on the device. The output is the user's reaction, such as clicking, purchasing, or using a coupon. Specifically, users can click a link to access detailed information and complete a purchase.

[0174] Step 7:

[0175] The server measures the effectiveness of advertising campaigns and generates feedback for future strategies. Inputs include purchase history and user response data. Based on this evaluation data, it outputs effectiveness measurement results and provides improvement suggestions. Specifically, it analyzes KPIs and generates reports based on click-through rates and conversion rates.

[0176] (Application Example 2)

[0177] 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".

[0178] Modern advertising doesn't always adequately address the diverse emotional states of users. The inability to deliver ads that resonate with users' emotions leads to insufficient advertising effectiveness. Furthermore, accurately measuring the impact of advertising on users and incorporating that into future advertising strategies is also difficult.

[0179] 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.

[0180] In this invention, the server includes means for collecting user emotional data, means for integrating and analyzing the emotional data in a standardized format, and means for using a generative model that optimizes ad delivery based on the emotional data. This enables the provision of optimal ads according to the user's emotional state, as well as accurate measurement and improvement of ad effectiveness.

[0181] "User emotional data" refers to biological or behavioral indicators that show a user's emotional state, such as information obtained from voice tone or facial expressions.

[0182] A "standardized format" refers to a state where data is converted into a consistent format, allowing for unified processing of information from different data sources.

[0183] A "generative model" is a computational model that uses statistical or machine learning algorithms to make predictions or optimizations from data.

[0184] "Real-time delivery" refers to the process of immediately presenting advertisements and services according to the user's situation.

[0185] "Advertising effectiveness" refers to measuring the degree to which an advertisement influences users and the resulting changes in their responses.

[0186] An "analysis platform" is an integrated system infrastructure used to import and analyze multiple data sets.

[0187] In this invention, the server collects user emotional data using a camera and microphone. This emotional data includes signals from voice tone and facial expressions. This data is converted into a digital format using software such as OpenCV and analyzed by an emotion recognition library. As a result of this analysis, the user's emotional state is identified, and the emotion engine utilizes a generative model to select appropriate advertisements based on that state.

[0188] The device processes the results of the emotional data analysis received from the server in real time and displays advertisements optimized for the user. These advertisements are customized according to the emotional state the user is expressing. For example, if the user is feeling stressed, advertisements for products related to relaxation will be displayed.

[0189] Users can use advertisements displayed on their devices to research details about products and services that interest them and take action to make a purchase. The server collects these responses, analyzes the effectiveness of the advertising campaign, and uses the results to inform future advertising strategies. This analysis uses advertising effectiveness measurement software, and the generated data is used to suggest improvements.

[0190] One concrete example is a scenario where the program detects a user relaxing at home at night and displays an advertisement for a relaxation music app. Another example of a prompt that utilizes a generative AI model is: "What strategy would you employ to analyze the facial expressions captured by the camera while the user is looking at their device and display optimized advertisements when the user is feeling stressed?"

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The server collects user emotion data via camera and microphone. This input includes biometric information such as voice tone and facial expressions. The data is acquired in digital format and converted to a standardized data format using libraries such as OpenCV. This provides the foundational data for emotion recognition processing.

[0194] Step 2:

[0195] The server analyzes the collected emotion data using an emotion recognition library. This data is used as input for calculations to infer the user's emotional state. Features are extracted from the emotion data, and the emotional states are labeled. The output is data representing the user's current emotional state.

[0196] Step 3:

[0197] The server uses a generative model to optimize ad delivery strategies based on analyzed emotional states. It uses the input emotional state data to calculate which ad is most effective and executes the ad selection process. In this step, ad strategies are recommended using prompts powered by the generative AI model. The output is the optimal ad suggestion to present to the user.

[0198] Step 4:

[0199] The device presents advertisements to the user in real time based on optimized advertising information obtained from the server. Inputs include ad proposals and user usage data, which are used to adjust the ad content and timing. The device displays custom messages and images on its screen, enabling real-time user interaction.

[0200] Step 5:

[0201] Users can respond to advertisements displayed on their devices and take further action on those that interest them. User input is done through methods such as touching or clicking, allowing them to navigate to purchase pages or obtain detailed information. This generates user engagement that leverages the effectiveness of the advertisements.

[0202] Step 6:

[0203] The server collects user responses to ads and analyzes the effectiveness of the campaign. Using the data obtained from users as input, calculations are performed to measure the success rate and engagement level of the ads. This generates suggestions for improvement for the next advertising strategy, contributing to improved accuracy in ad delivery.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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".

[0220] This invention is a marketing system that collects first-party data, integrates and analyzes it to optimize ad delivery. In this system, the server, terminal, and user each play a specific role.

[0221] First, the server has the capability to efficiently collect customer data held by companies. This data includes customer purchase history and communication history, and is securely and efficiently stored in a database using APIs. The collected data is unified, standardized, and integrated by the customer data platform, which handles data in different formats.

[0222] Next, the server analyzes the integrated data using a generative model. This generative model uses machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising delivery strategy is formulated for each customer. The generative model translates the data analysis results into specific advertising campaign suggestions, and personalized advertisements are designed based on this information.

[0223] In ad delivery, the device plays a crucial role. The device has the ability to deliver ads to users in real time based on instructions received from the server. In this process, the device displays more relevant ads based on geographical location information and past behavioral history. For example, if a user is near a store they frequently visit, information about special campaigns at that store can be immediately provided, stimulating their desire to purchase.

[0224] Finally, the server measures the effectiveness of the ads and campaigns implemented and generates feedback through data analysis to improve future strategies. This allows companies to quickly adjust their advertising strategies and conduct lean marketing activities.

[0225] In this way, the present invention makes it possible to realize effective marketing strategies while complying with privacy regulations.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The server collects customer data from various corporate data sources via APIs. This data includes purchase history, communication logs, and customer profile information. The collected data is stored in temporary storage.

[0229] Step 2:

[0230] The server integrates data collected using the customer data platform. It standardizes data from different formats and sources, removes duplicate data, and generates a consistent dataset.

[0231] Step 3:

[0232] The server inputs the integrated data into a generative model for analysis. The generative model uses machine learning algorithms to predict customer purchasing trends and behavior, and determines advertising targets for each segment.

[0233] Step 4:

[0234] The server designs an advertising delivery strategy based on the analysis results of the generative model. In this process, it selects the optimal creative and channel for the target segment and develops an implementation plan.

[0235] Step 5:

[0236] The device displays ads to the user in real time, following the ad delivery plan instructed by the server. The device selects the most relevant ads, taking into account location information and the user's viewing history.

[0237] Step 6:

[0238] Users receive advertisements and campaigns displayed on their devices. If they are interested in this information, they can obtain more detailed information or coupons and then initiate a purchase.

[0239] Step 7:

[0240] The server aggregates the results of advertising campaigns and measures their effectiveness. For example, it analyzes click-through rates and conversion rates to build a feedback loop that helps improve future ad campaigns.

[0241] (Example 1)

[0242] 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."

[0243] Conventional information distribution systems have struggled to effectively utilize individual users' interests and behavioral history to provide optimal information tailored to each situation in real time. Furthermore, they lacked the functionality to quickly measure the results of information distribution and use that data to improve future strategies.

[0244] 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.

[0245] In this invention, the server includes means for collecting information, means for integrating and standardizing said information, and means for analyzing the integrated information using a generation AI model. This enables real-time delivery of information tailored to each user's behavior and interests, and allows for efficient and continuous improvement of the information delivery strategy.

[0246] "Means of collecting information" refers to devices and methods for obtaining necessary information from databases or external information sources.

[0247] "Means for integrating and standardizing the information" refers to the process of converting collected information from different formats into a single format and compiling it while maintaining consistency.

[0248] "Analysis using generative AI models" refers to a method of predicting data trends and patterns using machine learning algorithms and deriving results from them.

[0249] "Designing an information distribution strategy" is the process of determining, based on analysis results, how, when, and where to deliver the most appropriate information to individual users.

[0250] "A means of delivering information in real time and displaying information based on location information and behavioral history" refers to a system that takes into account the user's current geographical location and past behavioral patterns to provide timely and relevant information.

[0251] "Methods for measuring the effectiveness of information distribution and generating improvement suggestions" refers to methods for evaluating the results of distributed information and indicating areas for improvement in future information distribution strategies.

[0252] To implement this invention, the server first plays the role of collecting information from various sources. For example, it retrieves necessary data from corporate databases and external public databases via an internet connection. The retrieved data is stored on the server in a secure manner using a database management system or API technology.

[0253] Next, the server performs a process to integrate and standardize the collected data. This integration uses a data platform, which converts data in different formats into a single format and performs transformation processes to ensure consistency. Specific examples include unifying date data in different formats and standardizing currency units.

[0254] Subsequently, the server analyzes the integrated data using a generative AI model. This model implements machine learning algorithms to analyze large datasets and predict customer behavior patterns and trends. The results of the analysis are used to design an information distribution strategy. From these results, the most relevant information for the user is selected. For example, if a user has frequently purchased a particular product in the past, new offers related to that product will be prepared.

[0255] Next, the terminal plays a crucial role in the information distribution stage. Based on instructions from the server, it provides information in real time, taking into account the user's location and past behavioral history. For example, if a user is in a specific area, the terminal will display promotional information for stores in that area. This allows users to receive more personalized information.

[0256] Finally, the server measures the effectiveness of the delivered information and generates feedback to improve future information delivery strategies. Effectiveness measurements include ad impressions, click-through rates, and conversion rates. By analyzing this data, companies can evaluate the effectiveness of their information strategies and use this information to develop future initiatives.

[0257] A concrete example of a prompt message is, "Based on the purchase history of online sports equipment buyers, please propose a strategy for designing the next promotional campaign." In this way, this invention makes it possible to implement an effective information strategy while complying with privacy regulations.

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The server collects information from corporate databases and publicly available sources. Input is data accessible via the internet, and output is the collected raw data. Specifically, the server uses APIs to securely download customer purchase and communication history and store it in a database.

[0261] Step 2:

[0262] The server integrates and standardizes the collected raw data. The input is the raw data obtained in step 1, and the output is consistent, integrated data. The data platform is used to unify data in different formats, perform format conversions, and eliminate duplication.

[0263] Step 3:

[0264] The server analyzes the integrated data using a generation AI model. The input is the integrated data generated in step 2, and the output is the analysis results showing customer behavior patterns and purchasing trends. Specifically, it applies machine learning algorithms to predict trends based on purchase frequency and interests.

[0265] Step 4:

[0266] The server designs an information distribution strategy based on the analysis results. The input is the analysis results from step 3, and the output is an information distribution plan optimized for the user. The server determines which information to distribute and when, according to the strategy proposed by the generative AI model.

[0267] Step 5:

[0268] The terminal receives instructions from the server and displays information to the user in real time. The input is the information distribution plan determined in step 4, and the output is the specific information displayed to the user. The terminal considers the user's location and past behavior history to display appropriate information.

[0269] Step 6:

[0270] The server measures the effectiveness of information distribution and generates feedback for future strategies. The input is performance data of the distributed information (e.g., click-through rate and conversion rate), and the output is improvement suggestions. This allows companies to distribute information more efficiently in the future.

[0271] (Application Example 1)

[0272] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] In modern digital marketing, consumers are exposed to a vast amount of information, making it challenging to maximize the effectiveness of advertising. In particular, there is a need for methods to deliver personalized advertising based on individual user interests in real time. However, traditional methods struggle to efficiently integrate and standardize data, and to perform real-time analysis and delivery. Furthermore, ensuring privacy remains a crucial challenge.

[0274] 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.

[0275] In this invention, the server includes means for collecting customer information, means for integrating and standardizing the information collected by said means, and means for using a generative model to analyze the integrated information. This enables the real-time delivery of personalized advertisements based on location information and behavioral history, as well as the measurement of campaign effectiveness and the suggestion of improvements.

[0276] "Customer information" refers to data collected by companies, such as individual attributes, purchase history, interests, and behavioral history.

[0277] "Integration" refers to combining data of different formats and types into a single, unified dataset.

[0278] "Standardization" refers to unifying data formats and preparing them in a way that makes them easier to process and analyze.

[0279] A "generative model" is a model that uses machine learning algorithms to analyze data and make predictions or suggestions.

[0280] The "advertising plan" is the process of designing a strategy for how to deploy advertisements based on specified conditions.

[0281] "Location information" refers to data indicating the geographical location of a device or user.

[0282] "Behavior history" refers to the record of operations and movements that a user has performed online and offline.

[0283] "Real-time" refers to the fact that information and operations are carried out almost instantaneously.

[0284] "Effect measurement" is the analysis for evaluating the performance of implemented campaigns and advertisements.

[0285] "Improvement proposal" is a specific proposal for improving future measures based on the measurement results.

[0286] The system for implementing this invention is mainly composed of three parties: a server, a terminal, and a user. The server efficiently collects and integrates customer information and standardizes it. This includes the utilization of a secure database using an API. The server passes the integrated information to a generative AI model and uses it to analyze the purchasing trends and interests of customers. This generative AI model uses a machine learning module and forms an important foundation in the advertising plan that undertakes the following steps.

[0287] The advertising plan proposed by the generative model is sent to the terminal. The terminal utilizes location information services and past behavior history to deliver the most relevant advertisements to the user in real time. Specifically, it seamlessly notifies advertising information through smartphones and smart glasses. For example, when the user approaches a specific store, the special campaign information of that store is immediately notified.

[0288] Furthermore, the server measures the performance of delivered ads and campaigns and performs data analysis to inform future strategies. This eliminates waste in marketing activities and enables effective strategic adjustments.

[0289] As a concrete example, by notifying users who visit shopping malls near them on weekends in real time about special sales from fashion brands, it is possible to encourage them to visit the stores. This implementation is useful not only because it improves the user's purchasing experience, but also because it improves the sales effectiveness of the stores.

[0290] An example of a prompt for a generative AI model would be: "Based on the user's interests, please generate advertisements for the products and services most relevant to their current location."

[0291] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0292] Step 1:

[0293] The server collects customer information from companies via APIs. It receives customer information such as purchase history and communication history as input and securely stores it in a database. This integrates the company's accumulated customer information within the server, preparing it for use in subsequent processing.

[0294] Step 2:

[0295] The server integrates the collected customer information and standardizes the data format. It receives customer data in different formats as input, transforms and integrates them to generate a consistent dataset. This standardized data becomes available for analysis in the generated AI models.

[0296] Step 3:

[0297] The server analyzes integrated data using a generative AI model. Using standardized customer data as input, it applies machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising plan is developed for each customer, and instructions are sent to the terminal.

[0298] Step 4:

[0299] The device delivers ads to users in real time based on the advertising plan received from the server. It uses the user's location information and past behavioral history as input, selecting and displaying appropriate ads based on this information. This ensures that users receive the most relevant ads in a timely manner.

[0300] Step 5:

[0301] The server measures the effectiveness of implemented advertising campaigns. It receives performance data from delivered ads as input and performs analysis. Based on this analysis, feedback is generated to improve future advertising strategies, enabling companies to streamline their marketing activities.

[0302] 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.

[0303] This invention is a marketing system that optimizes ad delivery by collecting first-party data and recognizing the user's emotional state using an emotion engine. This system consists primarily of a server, a terminal, and the user.

[0304] First, the server collects customer data from multiple corporate data sources via an API. This data includes purchase history, communication history, and data for obtaining the user's emotional state. Emotional data is obtained, for example, using technologies that analyze voice tones and facial expressions. This data is stored in a database and integrated through a customer data platform.

[0305] Next, at the server, the integrated data is analyzed by a generative model. The generative model utilizes machine learning algorithms to predict not only the customer's purchase intent and behavioral tendencies but also the emotional state at that time based on the emotional data. Based on these analysis results, an emotion engine operates to design an optimal advertising delivery strategy according to the user's emotions.

[0306] The delivery of advertisements is carried out by the terminal. The terminal presents advertisements to the user in real time based on the advertising delivery plan received from the server. Here, the terminal reflects the emotional state of the user recognized by the emotion engine and customizes the content and frequency of the advertisements accordingly. As a specific example, when the user is feeling stressed, an advertisement proposing a product with a relaxing effect is displayed, and promotions are carried out according to the emotional state.

[0307] The user can respond to the advertisements displayed on the terminal. To investigate more details about an advertisement that shows interest, it is possible to click on a link or purchase a product using a coupon that is provided.

[0308] Finally, the server measures the effectiveness of the advertising campaign and generates improvement points for increasing the success rate as feedback. Thereby, the system adjusts the advertising delivery strategy for subsequent times and realizes more advanced targeting and personalization.

[0309] In this way, the present invention improves the accuracy of advertisements and maximizes the marketing effect through advanced customer correspondence combined with emotion recognition technology.

[0310] The following describes the processing flow.

[0311] Step 1:

[0312] The server collects customer data from various data sources within the company using APIs. This includes purchase history, communication logs, and user sentiment data, which is obtained using voice analysis and facial recognition technology. The collected data is temporarily stored in a database.

[0313] Step 2:

[0314] The server integrates data collected using the customer data platform. It standardizes different data formats and removes duplicate data. The integrated dataset should contain information useful for understanding user behavior and emotional states.

[0315] Step 3:

[0316] The server inputs integrated data into a generative model for analysis. The generative model uses machine learning to predict customer purchasing trends and emotional states. This analysis includes reflecting emotional data in real time and determining which advertisements are effective in which situations.

[0317] Step 4:

[0318] The server uses the analysis results obtained from the generative model to enable the emotion engine to design an ad delivery strategy that is tailored to the user's emotional state. This strategy includes the content, timing, and frequency of the ads and is designed to adapt to the user's current emotions.

[0319] Step 5:

[0320] The device displays ads to the user in real time based on the ad delivery strategy provided by the server. The device selects and displays the appropriate ad content at the optimal time based on the user's location information and feedback from the sentiment engine.

[0321] Step 6:

[0322] Users receive advertisements and suggestions displayed on their devices and can click or tap on ads that interest them to view details. They can then use coupons for products they are interested in and proceed to make a purchase.

[0323] Step 7:

[0324] The server collects results after ad delivery and performs campaign effectiveness analysis. It measures ad effectiveness considering the impact of emotions and generates improvement suggestions to reflect in future ad delivery strategies. The goal is to continuously improve ad performance.

[0325] (Example 2)

[0326] 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".

[0327] In modern marketing, there is a demand for targeted advertising that responds to the diverse needs and emotional states of consumers. However, traditional methods have faced challenges in designing optimal advertising strategies due to insufficient analysis of collected data and inadequate personalization for individual consumers. A new system is needed to deliver more targeted advertising and increase consumer purchasing intent.

[0328] 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.

[0329] In this invention, the server includes means for collecting data, means for standardizing the aggregated data, and means for utilizing generative models for analysis. This enables the creation of accurate advertising strategies based on consumer sentiment and the delivery of personalized advertisements in real time.

[0330] "Means of data collection" refers to the technical processes for obtaining necessary information from various data sources.

[0331] "Methods for standardizing aggregated data" refer to methods for transforming collected data into a consistent format and preparing it in a way that facilitates analysis.

[0332] "Methods of using generative models" refer to techniques that utilize artificial intelligence and machine learning technologies to analyze data and generate patterns and predictions.

[0333] "Methods for building advertising strategies based on emotional information" refers to the process of analyzing consumers' emotional states and designing strategies to effectively deliver advertisements that correspond to those states.

[0334] A "means of presenting advertisements in real time" refers to a system that displays advertisements to consumers instantly without any time delay.

[0335] "Methods for measuring campaign effectiveness and generating improvement suggestions" refers to the process of analyzing the results of advertising activities and making suggestions for future activities based on that data.

[0336] "Behavioral information" refers to data about consumer behavior, such as consumer purchase history and website browsing history.

[0337] "Personalized advertising" refers to advertisements that are customized to the preferences and needs of each individual consumer.

[0338] "Diverse data sources" refers to different information sources, such as customer information provided by companies and data obtained from online platforms.

[0339] A "customer information platform" is a system that centrally manages and analyzes diverse customer data.

[0340] This invention is an advanced marketing system that personalizes advertisements based on the emotional state of consumers and presents them at the appropriate time. This system consists primarily of a server, terminals, and users.

[0341] The server collects consumer behavior information from various data sources via APIs. This data includes purchase history, communication history, and emotional data derived from voice tone and facial expression analysis. The server integrates this data into a database and manages it centrally using a customer information platform. In this process, voice recognition software and image analysis software are used to convert the data into a standardized format.

[0342] Using integrated data, the server employs generative AI models to analyze consumer behavior patterns and emotional states. This allows the server to build an advertising delivery strategy best suited to the customer's current emotions. The emotion engine optimizes the ad content, timing, and frequency based on the analysis results. For example, if a consumer is feeling stressed, the server will create an ad suggesting products with relaxing effects.

[0343] The device displays advertisements to consumers in real time based on the ad delivery plan received from the server. The device constantly communicates with the server, reflecting the latest sentiment data to display the most relevant advertising information.

[0344] Users can react to advertisements displayed on their devices. By clicking on an ad that interests them, they can obtain more information and even use coupons to purchase products. This improves the consumer experience and maximizes the effectiveness of advertising.

[0345] As a concrete example, if the server detects that a consumer is in a relaxed emotional state, an advertisement for a relaxing aromatherapy product will be displayed on the device. If the user clicks on the advertisement and checks the details on the product page, a coupon will be offered, which can encourage them to make a purchase.

[0346] An example of a prompt from this system is, "How can I design a model that integrates customer data and delivers the most relevant ads in real time based on the customer's emotional state?" This prompt serves as a guideline when utilizing generative AI models.

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

[0348] Step 1:

[0349] The server collects consumer behavior information from various data sources via APIs. Inputs include raw data such as purchase history, voice tone, and facial expressions. This data is analyzed using speech recognition and image analysis software, and the output is converted into a standardized format. Specifically, the server captures data in real time and immediately saves it to the database.

[0350] Step 2:

[0351] The server integrates the aggregated data into the customer information platform and prepares the dataset. The input is the standardized data set obtained in step 1. Using a unification technique, it outputs integrated information for each customer. Specifically, it unifies different data formats, performs cleanup processing, and then restores the data in the database.

[0352] Step 3:

[0353] The server uses integrated data to perform analysis with a generative AI model. The input is the integrated customer data obtained in step 2. The model predicts the customer's emotional state and behavioral patterns and outputs the analysis results. Specifically, it utilizes machine learning algorithms to perform cluster analysis and regression analysis on the data to generate prediction results.

[0354] Step 4:

[0355] The server activates an emotion engine based on the analysis results and designs user-specific ad delivery strategies. The input is the predictive analysis results from step 3. Here, strategies such as ad content and delivery frequency that take emotional states into account are obtained as output. Specifically, a template is used to design a scenario and generate a strategy document.

[0356] Step 5:

[0357] The device displays advertisements in real time based on the ad delivery plan received from the server. The input is the ad delivery plan from step 4. The goal is to instantly display the appropriate advertisement to the user, and the ad display results are output. Specifically, the advertisement is displayed to the user using the display or push notification.

[0358] Step 6:

[0359] Users can react to advertisements displayed on their devices. The input is the advertisement itself displayed on the device. The output is the user's reaction, such as clicking, purchasing, or using a coupon. Specifically, users can click a link to access detailed information and complete a purchase.

[0360] Step 7:

[0361] The server measures the effectiveness of advertising campaigns and generates feedback for future strategies. Inputs include purchase history and user response data. Based on this evaluation data, it outputs effectiveness measurement results and provides improvement suggestions. Specifically, it analyzes KPIs and generates reports based on click-through rates and conversion rates.

[0362] (Application Example 2)

[0363] 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."

[0364] Modern advertising doesn't always adequately address the diverse emotional states of users. The inability to deliver ads that resonate with users' emotions leads to insufficient advertising effectiveness. Furthermore, accurately measuring the impact of advertising on users and incorporating that into future advertising strategies is also difficult.

[0365] 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.

[0366] In this invention, the server includes means for collecting user emotional data, means for integrating and analyzing the emotional data in a standardized format, and means for using a generative model that optimizes ad delivery based on the emotional data. This enables the provision of optimal ads according to the user's emotional state, as well as accurate measurement and improvement of ad effectiveness.

[0367] "User emotional data" refers to biological or behavioral indicators that show a user's emotional state, such as information obtained from voice tone or facial expressions.

[0368] A "standardized format" refers to a state where data is converted into a consistent format, allowing for unified processing of information from different data sources.

[0369] A "generative model" is a computational model that uses statistical or machine learning algorithms to make predictions or optimizations from data.

[0370] "Real-time delivery" refers to the process of immediately presenting advertisements and services according to the user's situation.

[0371] "Advertising effectiveness" refers to measuring the degree to which an advertisement influences users and the resulting changes in their responses.

[0372] An "analysis platform" is an integrated system infrastructure used to import and analyze multiple data sets.

[0373] In this invention, the server collects user emotional data using a camera and microphone. This emotional data includes signals from voice tone and facial expressions. This data is converted into a digital format using software such as OpenCV and analyzed by an emotion recognition library. As a result of this analysis, the user's emotional state is identified, and the emotion engine utilizes a generative model to select appropriate advertisements based on that state.

[0374] The device processes the results of the emotional data analysis received from the server in real time and displays advertisements optimized for the user. These advertisements are customized according to the emotional state the user is expressing. For example, if the user is feeling stressed, advertisements for products related to relaxation will be displayed.

[0375] Users can use advertisements displayed on their devices to research details about products and services that interest them and take action to make a purchase. The server collects these responses, analyzes the effectiveness of the advertising campaign, and uses the results to inform future advertising strategies. This analysis uses advertising effectiveness measurement software, and the generated data is used to suggest improvements.

[0376] One concrete example is a scenario where the program detects a user relaxing at home at night and displays an advertisement for a relaxation music app. Another example of a prompt that utilizes a generative AI model is: "What strategy would you employ to analyze the facial expressions captured by the camera while the user is looking at their device and display optimized advertisements when the user is feeling stressed?"

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The server collects user emotion data via camera and microphone. This input includes biometric information such as voice tone and facial expressions. The data is acquired in digital format and converted to a standardized data format using libraries such as OpenCV. This provides the foundational data for emotion recognition processing.

[0380] Step 2:

[0381] The server analyzes the collected emotion data using an emotion recognition library. This data is used as input for calculations to infer the user's emotional state. Features are extracted from the emotion data, and the emotional states are labeled. The output is data representing the user's current emotional state.

[0382] Step 3:

[0383] The server uses a generative model to optimize ad delivery strategies based on analyzed emotional states. It uses the input emotional state data to calculate which ad is most effective and executes the ad selection process. In this step, ad strategies are recommended using prompts powered by the generative AI model. The output is the optimal ad suggestion to present to the user.

[0384] Step 4:

[0385] The device presents advertisements to the user in real time based on optimized advertising information obtained from the server. Inputs include ad proposals and user usage data, which are used to adjust the ad content and timing. The device displays custom messages and images on its screen, enabling real-time user interaction.

[0386] Step 5:

[0387] Users can respond to advertisements displayed on their devices and take further action on those that interest them. User input is done through methods such as touching or clicking, allowing them to navigate to purchase pages or obtain detailed information. This generates user engagement that leverages the effectiveness of the advertisements.

[0388] Step 6:

[0389] The server collects user responses to ads and analyzes the effectiveness of the campaign. Using the data obtained from users as input, calculations are performed to measure the success rate and engagement level of the ads. This generates suggestions for improvement for the next advertising strategy, contributing to improved accuracy in ad delivery.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] [Third Embodiment]

[0394] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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".

[0406] This invention is a marketing system that collects first-party data, integrates and analyzes it to optimize ad delivery. In this system, the server, terminal, and user each play a specific role.

[0407] First, the server has the capability to efficiently collect customer data held by companies. This data includes customer purchase history and communication history, and is securely and efficiently stored in a database using APIs. The collected data is unified, standardized, and integrated by the customer data platform, which handles data in different formats.

[0408] Next, the server analyzes the integrated data using a generative model. This generative model uses machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising delivery strategy is formulated for each customer. The generative model translates the data analysis results into specific advertising campaign suggestions, and personalized advertisements are designed based on this information.

[0409] In ad delivery, the device plays a crucial role. The device has the ability to deliver ads to users in real time based on instructions received from the server. In this process, the device displays more relevant ads based on geographical location information and past behavioral history. For example, if a user is near a store they frequently visit, information about special campaigns at that store can be immediately provided, stimulating their desire to purchase.

[0410] Finally, the server measures the effectiveness of the ads and campaigns implemented and generates feedback through data analysis to improve future strategies. This allows companies to quickly adjust their advertising strategies and conduct lean marketing activities.

[0411] In this way, the present invention makes it possible to realize effective marketing strategies while complying with privacy regulations.

[0412] The following describes the processing flow.

[0413] Step 1:

[0414] The server collects customer data from various corporate data sources via APIs. This data includes purchase history, communication logs, and customer profile information. The collected data is stored in temporary storage.

[0415] Step 2:

[0416] The server integrates data collected using the customer data platform. It standardizes data from different formats and sources, removes duplicate data, and generates a consistent dataset.

[0417] Step 3:

[0418] The server inputs the integrated data into a generative model for analysis. The generative model uses machine learning algorithms to predict customer purchasing trends and behavior, and determines advertising targets for each segment.

[0419] Step 4:

[0420] The server designs an advertising delivery strategy based on the analysis results of the generative model. In this process, it selects the optimal creative and channel for the target segment and develops an implementation plan.

[0421] Step 5:

[0422] The device displays ads to the user in real time, following the ad delivery plan instructed by the server. The device selects the most relevant ads, taking into account location information and the user's viewing history.

[0423] Step 6:

[0424] Users receive advertisements and campaigns displayed on their devices. If they are interested in this information, they can obtain more detailed information or coupons and then initiate a purchase.

[0425] Step 7:

[0426] The server aggregates the results of advertising campaigns and measures their effectiveness. For example, it analyzes click-through rates and conversion rates to build a feedback loop that helps improve future ad campaigns.

[0427] (Example 1)

[0428] 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."

[0429] Conventional information distribution systems have struggled to effectively utilize individual users' interests and behavioral history to provide optimal information tailored to each situation in real time. Furthermore, they lacked the functionality to quickly measure the results of information distribution and use that data to improve future strategies.

[0430] 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.

[0431] In this invention, the server includes means for collecting information, means for integrating and standardizing said information, and means for analyzing the integrated information using a generation AI model. This enables real-time delivery of information tailored to each user's behavior and interests, and allows for efficient and continuous improvement of the information delivery strategy.

[0432] "Means of collecting information" refers to devices and methods for obtaining necessary information from databases or external information sources.

[0433] "Means for integrating and standardizing the information" refers to the process of converting collected information from different formats into a single format and compiling it while maintaining consistency.

[0434] "Analysis using generative AI models" refers to a method of predicting data trends and patterns using machine learning algorithms and deriving results from them.

[0435] "Designing an information distribution strategy" is the process of determining, based on analysis results, how, when, and where to deliver the most appropriate information to individual users.

[0436] "A means of delivering information in real time and displaying information based on location information and behavioral history" refers to a system that takes into account the user's current geographical location and past behavioral patterns to provide timely and relevant information.

[0437] "Methods for measuring the effectiveness of information distribution and generating improvement suggestions" refers to methods for evaluating the results of distributed information and indicating areas for improvement in future information distribution strategies.

[0438] To implement this invention, the server first plays the role of collecting information from various sources. For example, it retrieves necessary data from corporate databases and external public databases via an internet connection. The retrieved data is stored on the server in a secure manner using a database management system or API technology.

[0439] Next, the server performs a process to integrate and standardize the collected data. This integration uses a data platform, which converts data in different formats into a single format and performs transformation processes to ensure consistency. Specific examples include unifying date data in different formats and standardizing currency units.

[0440] Subsequently, the server analyzes the integrated data using a generative AI model. This model implements machine learning algorithms to analyze large datasets and predict customer behavior patterns and trends. The results of the analysis are used to design an information distribution strategy. From these results, the most relevant information for the user is selected. For example, if a user has frequently purchased a particular product in the past, new offers related to that product will be prepared.

[0441] Next, the terminal plays a crucial role in the information distribution stage. Based on instructions from the server, it provides information in real time, taking into account the user's location and past behavioral history. For example, if a user is in a specific area, the terminal will display promotional information for stores in that area. This allows users to receive more personalized information.

[0442] Finally, the server measures the effectiveness of the delivered information and generates feedback to improve future information delivery strategies. Effectiveness measurements include ad impressions, click-through rates, and conversion rates. By analyzing this data, companies can evaluate the effectiveness of their information strategies and use this information to develop future initiatives.

[0443] A concrete example of a prompt message is, "Based on the purchase history of online sports equipment buyers, please propose a strategy for designing the next promotional campaign." In this way, this invention makes it possible to implement an effective information strategy while complying with privacy regulations.

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

[0445] Step 1:

[0446] The server collects information from corporate databases and publicly available sources. Input is data accessible via the internet, and output is the collected raw data. Specifically, the server uses APIs to securely download customer purchase and communication history and store it in a database.

[0447] Step 2:

[0448] The server integrates and standardizes the collected raw data. The input is the raw data obtained in step 1, and the output is consistent, integrated data. The data platform is used to unify data in different formats, perform format conversions, and eliminate duplication.

[0449] Step 3:

[0450] The server analyzes the integrated data using a generation AI model. The input is the integrated data generated in step 2, and the output is the analysis results showing customer behavior patterns and purchasing trends. Specifically, it applies machine learning algorithms to predict trends based on purchase frequency and interests.

[0451] Step 4:

[0452] The server designs an information distribution strategy based on the analysis results. The input is the analysis results from step 3, and the output is an information distribution plan optimized for the user. The server determines which information to distribute and when, according to the strategy proposed by the generative AI model.

[0453] Step 5:

[0454] The terminal receives instructions from the server and displays information to the user in real time. The input is the information distribution plan determined in step 4, and the output is the specific information displayed to the user. The terminal considers the user's location and past behavior history to display appropriate information.

[0455] Step 6:

[0456] The server measures the effectiveness of information distribution and generates feedback for future strategies. The input is performance data of the distributed information (e.g., click-through rate and conversion rate), and the output is improvement suggestions. This allows companies to distribute information more efficiently in the future.

[0457] (Application Example 1)

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

[0459] In modern digital marketing, consumers are exposed to a vast amount of information, making it challenging to maximize the effectiveness of advertising. In particular, there is a need for methods to deliver personalized advertising based on individual user interests in real time. However, traditional methods struggle to efficiently integrate and standardize data, and to perform real-time analysis and delivery. Furthermore, ensuring privacy remains a crucial challenge.

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

[0461] In this invention, the server includes means for collecting customer information, means for integrating and standardizing the information collected by said means, and means for using a generative model to analyze the integrated information. This enables the real-time delivery of personalized advertisements based on location information and behavioral history, as well as the measurement of campaign effectiveness and the suggestion of improvements.

[0462] "Customer information" refers to data collected by companies, such as individual attributes, purchase history, interests, and behavioral history.

[0463] "Integration" refers to combining data of different formats and types into a single, unified dataset.

[0464] "Standardization" refers to unifying data formats and preparing them in a way that makes them easier to process and analyze.

[0465] A "generative model" is a model that uses machine learning algorithms to analyze data and make predictions or suggestions.

[0466] "Advertising planning" is the process of designing a strategy for how to deploy advertising based on specified conditions.

[0467] "Location information" refers to data that indicates the geographical location of a device or user.

[0468] "Activity history" refers to a record of actions and movements performed by a user both online and offline.

[0469] "Real-time" refers to situations where information or actions are performed almost instantly.

[0470] "Effectiveness measurement" is the analysis used to evaluate the performance of a campaign or advertisement that has been implemented.

[0471] An "improvement suggestion" is a specific proposal to improve future measures based on the measurement results.

[0472] The system implementing this invention primarily consists of three parties: a server, a terminal, and a user. The server efficiently collects, integrates, and standardizes customer information. This includes utilizing a secure database via an API. The server passes the integrated information to a generative AI model, which is used to analyze customer purchasing trends and interests. This generative AI model uses machine learning modules and forms a crucial foundation for advertising planning that drives the next steps.

[0473] The advertising plan proposed by the generative model is sent to the device. The device then uses location services and past behavioral history to deliver the most relevant ads to the user in real time. Specifically, advertising information is seamlessly notified via smartphones and smart glasses. For example, when a user approaches a particular store, they are immediately notified of special campaigns at that store.

[0474] Furthermore, the server measures the performance of delivered ads and campaigns and performs data analysis to inform future strategies. This eliminates waste in marketing activities and enables effective strategic adjustments.

[0475] As a concrete example, by notifying users who visit shopping malls near them on weekends in real time about special sales from fashion brands, it is possible to encourage them to visit the stores. This implementation is useful not only because it improves the user's purchasing experience, but also because it improves the sales effectiveness of the stores.

[0476] An example of a prompt for a generative AI model would be: "Based on the user's interests, please generate advertisements for the products and services most relevant to their current location."

[0477] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0478] Step 1:

[0479] The server collects customer information from companies via APIs. It receives customer information such as purchase history and communication history as input and securely stores it in a database. This integrates the company's accumulated customer information within the server, preparing it for use in subsequent processing.

[0480] Step 2:

[0481] The server integrates the collected customer information and standardizes the data format. It receives customer data in different formats as input, transforms and integrates them to generate a consistent dataset. This standardized data becomes available for analysis in the generated AI models.

[0482] Step 3:

[0483] The server analyzes integrated data using a generative AI model. Using standardized customer data as input, it applies machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising plan is developed for each customer, and instructions are sent to the terminal.

[0484] Step 4:

[0485] The device delivers ads to users in real time based on the advertising plan received from the server. It uses the user's location information and past behavioral history as input, selecting and displaying appropriate ads based on this information. This ensures that users receive the most relevant ads in a timely manner.

[0486] Step 5:

[0487] The server measures the effectiveness of implemented advertising campaigns. It receives performance data from delivered ads as input and performs analysis. Based on this analysis, feedback is generated to improve future advertising strategies, enabling companies to streamline their marketing activities.

[0488] 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.

[0489] This invention is a marketing system that optimizes ad delivery by collecting first-party data and recognizing the user's emotional state using an emotion engine. This system consists primarily of a server, a terminal, and the user.

[0490] First, the server collects customer data from multiple data sources within the company via APIs. This data includes purchase history, communication history, and data to capture the user's emotional state. Emotional data is obtained using techniques such as analyzing voice tone and facial expressions. This data is stored in a database and integrated through the customer data platform.

[0491] Next, on the server, the integrated data is analyzed by a generative model. This model utilizes machine learning algorithms to predict not only customer purchasing intent and behavioral trends, but also their emotional state based on emotional data. Based on these analysis results, an emotion engine operates to design an optimal advertising delivery strategy tailored to the user's emotions.

[0492] The device handles ad delivery. Based on the ad delivery plan received from the server, the device presents ads to the user in real time. Here, the device reflects the user's emotional state as recognized by the emotion engine and customizes the ad content and frequency accordingly. For example, when a user is feeling stressed, it displays ads suggesting products with relaxing effects, thus conducting promotions tailored to the user's emotional state.

[0493] Users can react to advertisements displayed on their devices. They can click links to learn more about ads that interest them, or use coupons provided to purchase products.

[0494] Finally, the server measures the effectiveness of the advertising campaign and generates feedback on areas for improvement to increase the success rate. This allows the system to adjust future ad delivery strategies, enabling more sophisticated targeting and personalization.

[0495] In this way, the present invention improves the accuracy of advertising and maximizes marketing effectiveness through advanced customer service combined with emotion recognition technology.

[0496] The following describes the processing flow.

[0497] Step 1:

[0498] The server collects customer data from various data sources within the company using APIs. This includes purchase history, communication logs, and user sentiment data, which is obtained using voice analysis and facial recognition technology. The collected data is temporarily stored in a database.

[0499] Step 2:

[0500] The server integrates data collected using the customer data platform. It standardizes different data formats and removes duplicate data. The integrated dataset should contain information useful for understanding user behavior and emotional states.

[0501] Step 3:

[0502] The server inputs integrated data into a generative model for analysis. The generative model uses machine learning to predict customer purchasing trends and emotional states. This analysis includes reflecting emotional data in real time and determining which advertisements are effective in which situations.

[0503] Step 4:

[0504] The server uses the analysis results obtained from the generative model to enable the emotion engine to design an ad delivery strategy that is tailored to the user's emotional state. This strategy includes the content, timing, and frequency of the ads and is designed to adapt to the user's current emotions.

[0505] Step 5:

[0506] The device displays ads to the user in real time based on the ad delivery strategy provided by the server. The device selects and displays the appropriate ad content at the optimal time based on the user's location information and feedback from the sentiment engine.

[0507] Step 6:

[0508] Users receive advertisements and suggestions displayed on their devices and can click or tap on ads that interest them to view details. They can then use coupons for products they are interested in and proceed to make a purchase.

[0509] Step 7:

[0510] The server collects results after ad delivery and performs campaign effectiveness analysis. It measures ad effectiveness considering the impact of emotions and generates improvement suggestions to reflect in future ad delivery strategies. The goal is to continuously improve ad performance.

[0511] (Example 2)

[0512] 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."

[0513] In modern marketing, there is a demand for targeted advertising that responds to the diverse needs and emotional states of consumers. However, traditional methods have faced challenges in designing optimal advertising strategies due to insufficient analysis of collected data and inadequate personalization for individual consumers. A new system is needed to deliver more targeted advertising and increase consumer purchasing intent.

[0514] 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.

[0515] In this invention, the server includes means for collecting data, means for standardizing the aggregated data, and means for utilizing generative models for analysis. This enables the creation of accurate advertising strategies based on consumer sentiment and the delivery of personalized advertisements in real time.

[0516] "Means of data collection" refers to the technical processes for obtaining necessary information from various data sources.

[0517] "Methods for standardizing aggregated data" refer to methods for transforming collected data into a consistent format and preparing it in a way that facilitates analysis.

[0518] "Methods of using generative models" refer to techniques that utilize artificial intelligence and machine learning technologies to analyze data and generate patterns and predictions.

[0519] "Methods for building advertising strategies based on emotional information" refers to the process of analyzing consumers' emotional states and designing strategies to effectively deliver advertisements that correspond to those states.

[0520] A "means of presenting advertisements in real time" refers to a system that displays advertisements to consumers instantly without any time delay.

[0521] "Methods for measuring campaign effectiveness and generating improvement suggestions" refers to the process of analyzing the results of advertising activities and making suggestions for future activities based on that data.

[0522] "Behavioral information" refers to data about consumer behavior, such as consumer purchase history and website browsing history.

[0523] "Personalized advertising" refers to advertisements that are customized to the preferences and needs of each individual consumer.

[0524] "Diverse data sources" refers to different information sources, such as customer information provided by companies and data obtained from online platforms.

[0525] A "customer information platform" is a system that centrally manages and analyzes diverse customer data.

[0526] This invention is an advanced marketing system that personalizes advertisements based on the emotional state of consumers and presents them at the appropriate time. This system consists primarily of a server, terminals, and users.

[0527] The server collects consumer behavior information from various data sources via APIs. This data includes purchase history, communication history, and emotional data derived from voice tone and facial expression analysis. The server integrates this data into a database and manages it centrally using a customer information platform. In this process, voice recognition software and image analysis software are used to convert the data into a standardized format.

[0528] Using integrated data, the server employs generative AI models to analyze consumer behavior patterns and emotional states. This allows the server to build an advertising delivery strategy best suited to the customer's current emotions. The emotion engine optimizes the ad content, timing, and frequency based on the analysis results. For example, if a consumer is feeling stressed, the server will create an ad suggesting products with relaxing effects.

[0529] The device displays advertisements to consumers in real time based on the ad delivery plan received from the server. The device constantly communicates with the server, reflecting the latest sentiment data to display the most relevant advertising information.

[0530] Users can react to advertisements displayed on their devices. By clicking on an ad that interests them, they can obtain more information and even use coupons to purchase products. This improves the consumer experience and maximizes the effectiveness of advertising.

[0531] As a concrete example, if the server detects that a consumer is in a relaxed emotional state, an advertisement for a relaxing aromatherapy product will be displayed on the device. If the user clicks on the advertisement and checks the details on the product page, a coupon will be offered, which can encourage them to make a purchase.

[0532] An example of a prompt from this system is, "How can I design a model that integrates customer data and delivers the most relevant ads in real time based on the customer's emotional state?" This prompt serves as a guideline when utilizing generative AI models.

[0533] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0534] Step 1:

[0535] The server collects consumer behavior information from various data sources via APIs. Inputs include raw data such as purchase history, voice tone, and facial expressions. This data is analyzed using speech recognition and image analysis software, and the output is converted into a standardized format. Specifically, the server captures data in real time and immediately saves it to the database.

[0536] Step 2:

[0537] The server integrates the aggregated data into the customer information platform and prepares the dataset. The input is the standardized data set obtained in step 1. Using a unification technique, it outputs integrated information for each customer. Specifically, it unifies different data formats, performs cleanup processing, and then restores the data in the database.

[0538] Step 3:

[0539] The server uses integrated data to perform analysis with a generative AI model. The input is the integrated customer data obtained in step 2. The model predicts the customer's emotional state and behavioral patterns and outputs the analysis results. Specifically, it utilizes machine learning algorithms to perform cluster analysis and regression analysis on the data to generate prediction results.

[0540] Step 4:

[0541] The server activates an emotion engine based on the analysis results and designs user-specific ad delivery strategies. The input is the predictive analysis results from step 3. Here, strategies such as ad content and delivery frequency that take emotional states into account are obtained as output. Specifically, a template is used to design a scenario and generate a strategy document.

[0542] Step 5:

[0543] The device displays advertisements in real time based on the ad delivery plan received from the server. The input is the ad delivery plan from step 4. The goal is to instantly display the appropriate advertisement to the user, and the ad display results are output. Specifically, the advertisement is displayed to the user using the display or push notification.

[0544] Step 6:

[0545] Users can react to advertisements displayed on their devices. The input is the advertisement itself displayed on the device. The output is the user's reaction, such as clicking, purchasing, or using a coupon. Specifically, users can click a link to access detailed information and complete a purchase.

[0546] Step 7:

[0547] The server measures the effectiveness of advertising campaigns and generates feedback for future strategies. Inputs include purchase history and user response data. Based on this evaluation data, it outputs effectiveness measurement results and provides improvement suggestions. Specifically, it analyzes KPIs and generates reports based on click-through rates and conversion rates.

[0548] (Application Example 2)

[0549] 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."

[0550] Modern advertising doesn't always adequately address the diverse emotional states of users. The inability to deliver ads that resonate with users' emotions leads to insufficient advertising effectiveness. Furthermore, accurately measuring the impact of advertising on users and incorporating that into future advertising strategies is also difficult.

[0551] 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.

[0552] In this invention, the server includes means for collecting user emotional data, means for integrating and analyzing the emotional data in a standardized format, and means for using a generative model that optimizes ad delivery based on the emotional data. This enables the provision of optimal ads according to the user's emotional state, as well as accurate measurement and improvement of ad effectiveness.

[0553] "User emotional data" refers to biological or behavioral indicators that show a user's emotional state, such as information obtained from voice tone or facial expressions.

[0554] A "standardized format" refers to a state where data is converted into a consistent format, allowing for unified processing of information from different data sources.

[0555] A "generative model" is a computational model that uses statistical or machine learning algorithms to make predictions or optimizations from data.

[0556] "Real-time delivery" refers to the process of immediately presenting advertisements and services according to the user's situation.

[0557] "Advertising effectiveness" refers to measuring the degree to which an advertisement influences users and the resulting changes in their responses.

[0558] An "analysis platform" is an integrated system infrastructure used to import and analyze multiple data sets.

[0559] In this invention, the server collects user emotional data using a camera and microphone. This emotional data includes signals from voice tone and facial expressions. This data is converted into a digital format using software such as OpenCV and analyzed by an emotion recognition library. As a result of this analysis, the user's emotional state is identified, and the emotion engine utilizes a generative model to select appropriate advertisements based on that state.

[0560] The device processes the results of the emotional data analysis received from the server in real time and displays advertisements optimized for the user. These advertisements are customized according to the emotional state the user is expressing. For example, if the user is feeling stressed, advertisements for products related to relaxation will be displayed.

[0561] Users can use advertisements displayed on their devices to research details about products and services that interest them and take action to make a purchase. The server collects these responses, analyzes the effectiveness of the advertising campaign, and uses the results to inform future advertising strategies. This analysis uses advertising effectiveness measurement software, and the generated data is used to suggest improvements.

[0562] One concrete example is a scenario where the program detects a user relaxing at home at night and displays an advertisement for a relaxation music app. Another example of a prompt that utilizes a generative AI model is: "What strategy would you employ to analyze the facial expressions captured by the camera while the user is looking at their device and display optimized advertisements when the user is feeling stressed?"

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

[0564] Step 1:

[0565] The server collects user emotion data via camera and microphone. This input includes biometric information such as voice tone and facial expressions. The data is acquired in digital format and converted to a standardized data format using libraries such as OpenCV. This provides the foundational data for emotion recognition processing.

[0566] Step 2:

[0567] The server analyzes the collected emotion data using an emotion recognition library. This data is used as input for calculations to infer the user's emotional state. Features are extracted from the emotion data, and the emotional states are labeled. The output is data representing the user's current emotional state.

[0568] Step 3:

[0569] The server uses a generative model to optimize ad delivery strategies based on analyzed emotional states. It uses the input emotional state data to calculate which ad is most effective and executes the ad selection process. In this step, ad strategies are recommended using prompts powered by the generative AI model. The output is the optimal ad suggestion to present to the user.

[0570] Step 4:

[0571] The device presents advertisements to the user in real time based on optimized advertising information obtained from the server. Inputs include ad proposals and user usage data, which are used to adjust the ad content and timing. The device displays custom messages and images on its screen, enabling real-time user interaction.

[0572] Step 5:

[0573] Users can respond to advertisements displayed on their devices and take further action on those that interest them. User input is done through methods such as touching or clicking, allowing them to navigate to purchase pages or obtain detailed information. This generates user engagement that leverages the effectiveness of the advertisements.

[0574] Step 6:

[0575] The server collects user responses to ads and analyzes the effectiveness of the campaign. Using the data obtained from users as input, calculations are performed to measure the success rate and engagement level of the ads. This generates suggestions for improvement for the next advertising strategy, contributing to improved accuracy in ad delivery.

[0576] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0577] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0578] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0579] [Fourth Embodiment]

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

[0581] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0582] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0583] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0584] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0585] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0586] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0587] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0588] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0589] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0590] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0591] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0592] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0593] This invention is a marketing system that collects first-party data, integrates and analyzes it to optimize ad delivery. In this system, the server, terminal, and user each play a specific role.

[0594] First, the server has the capability to efficiently collect customer data held by companies. This data includes customer purchase history and communication history, and is securely and efficiently stored in a database using APIs. The collected data is unified, standardized, and integrated by the customer data platform, which handles data in different formats.

[0595] Next, the server analyzes the integrated data using a generative model. This generative model uses machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising delivery strategy is formulated for each customer. The generative model translates the data analysis results into specific advertising campaign suggestions, and personalized advertisements are designed based on this information.

[0596] In ad delivery, the device plays a crucial role. The device has the ability to deliver ads to users in real time based on instructions received from the server. In this process, the device displays more relevant ads based on geographical location information and past behavioral history. For example, if a user is near a store they frequently visit, information about special campaigns at that store can be immediately provided, stimulating their desire to purchase.

[0597] Finally, the server measures the effectiveness of the ads and campaigns implemented and generates feedback through data analysis to improve future strategies. This allows companies to quickly adjust their advertising strategies and conduct lean marketing activities.

[0598] In this way, the present invention makes it possible to realize effective marketing strategies while complying with privacy regulations.

[0599] The following describes the processing flow.

[0600] Step 1:

[0601] The server collects customer data from various corporate data sources via APIs. This data includes purchase history, communication logs, and customer profile information. The collected data is stored in temporary storage.

[0602] Step 2:

[0603] The server integrates data collected using the customer data platform. It standardizes data from different formats and sources, removes duplicate data, and generates a consistent dataset.

[0604] Step 3:

[0605] The server inputs the integrated data into a generative model for analysis. The generative model uses machine learning algorithms to predict customer purchasing trends and behavior, and determines advertising targets for each segment.

[0606] Step 4:

[0607] The server designs an advertising delivery strategy based on the analysis results of the generative model. In this process, it selects the optimal creative and channel for the target segment and develops an implementation plan.

[0608] Step 5:

[0609] The device displays ads to the user in real time, following the ad delivery plan instructed by the server. The device selects the most relevant ads, taking into account location information and the user's viewing history.

[0610] Step 6:

[0611] Users receive advertisements and campaigns displayed on their devices. If they are interested in this information, they can obtain more detailed information or coupons and then initiate a purchase.

[0612] Step 7:

[0613] The server aggregates the results of advertising campaigns and measures their effectiveness. For example, it analyzes click-through rates and conversion rates to build a feedback loop that helps improve future ad campaigns.

[0614] (Example 1)

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

[0616] Conventional information distribution systems have struggled to effectively utilize individual users' interests and behavioral history to provide optimal information tailored to each situation in real time. Furthermore, they lacked the functionality to quickly measure the results of information distribution and use that data to improve future strategies.

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

[0618] In this invention, the server includes means for collecting information, means for integrating and standardizing said information, and means for analyzing the integrated information using a generation AI model. This enables real-time delivery of information tailored to each user's behavior and interests, and allows for efficient and continuous improvement of the information delivery strategy.

[0619] "Means of collecting information" refers to devices and methods for obtaining necessary information from databases or external information sources.

[0620] "Means for integrating and standardizing the information" refers to the process of converting collected information from different formats into a single format and compiling it while maintaining consistency.

[0621] "Analysis using generative AI models" refers to a method of predicting data trends and patterns using machine learning algorithms and deriving results from them.

[0622] "Designing an information distribution strategy" is the process of determining, based on analysis results, how, when, and where to deliver the most appropriate information to individual users.

[0623] "A means of delivering information in real time and displaying information based on location information and behavioral history" refers to a system that takes into account the user's current geographical location and past behavioral patterns to provide timely and relevant information.

[0624] "Methods for measuring the effectiveness of information distribution and generating improvement suggestions" refers to methods for evaluating the results of distributed information and indicating areas for improvement in future information distribution strategies.

[0625] To implement this invention, the server first plays the role of collecting information from various sources. For example, it retrieves necessary data from corporate databases and external public databases via an internet connection. The retrieved data is stored on the server in a secure manner using a database management system or API technology.

[0626] Next, the server performs a process to integrate and standardize the collected data. This integration uses a data platform, which converts data in different formats into a single format and performs transformation processes to ensure consistency. Specific examples include unifying date data in different formats and standardizing currency units.

[0627] Subsequently, the server analyzes the integrated data using a generative AI model. This model implements machine learning algorithms to analyze large datasets and predict customer behavior patterns and trends. The results of the analysis are used to design an information distribution strategy. From these results, the most relevant information for the user is selected. For example, if a user has frequently purchased a particular product in the past, new offers related to that product will be prepared.

[0628] Next, the terminal plays a crucial role in the information distribution stage. Based on instructions from the server, it provides information in real time, taking into account the user's location and past behavioral history. For example, if a user is in a specific area, the terminal will display promotional information for stores in that area. This allows users to receive more personalized information.

[0629] Finally, the server measures the effectiveness of the delivered information and generates feedback to improve future information delivery strategies. Effectiveness measurements include ad impressions, click-through rates, and conversion rates. By analyzing this data, companies can evaluate the effectiveness of their information strategies and use this information to develop future initiatives.

[0630] A concrete example of a prompt message is, "Based on the purchase history of online sports equipment buyers, please propose a strategy for designing the next promotional campaign." In this way, this invention makes it possible to implement an effective information strategy while complying with privacy regulations.

[0631] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0632] Step 1:

[0633] The server collects information from corporate databases and publicly available sources. Input is data accessible via the internet, and output is the collected raw data. Specifically, the server uses APIs to securely download customer purchase and communication history and store it in a database.

[0634] Step 2:

[0635] The server integrates and standardizes the collected raw data. The input is the raw data obtained in step 1, and the output is consistent, integrated data. The data platform is used to unify data in different formats, perform format conversions, and eliminate duplication.

[0636] Step 3:

[0637] The server analyzes the integrated data using a generation AI model. The input is the integrated data generated in step 2, and the output is the analysis results showing customer behavior patterns and purchasing trends. Specifically, it applies machine learning algorithms to predict trends based on purchase frequency and interests.

[0638] Step 4:

[0639] The server designs an information distribution strategy based on the analysis results. The input is the analysis results from step 3, and the output is an information distribution plan optimized for the user. The server determines which information to distribute and when, according to the strategy proposed by the generative AI model.

[0640] Step 5:

[0641] The terminal receives instructions from the server and displays information to the user in real time. The input is the information distribution plan determined in step 4, and the output is the specific information displayed to the user. The terminal considers the user's location and past behavior history to display appropriate information.

[0642] Step 6:

[0643] The server measures the effectiveness of information distribution and generates feedback for future strategies. The input is performance data of the distributed information (e.g., click-through rate and conversion rate), and the output is improvement suggestions. This allows companies to distribute information more efficiently in the future.

[0644] (Application Example 1)

[0645] 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".

[0646] In modern digital marketing, consumers are exposed to a vast amount of information, making it challenging to maximize the effectiveness of advertising. In particular, there is a need for methods to deliver personalized advertising based on individual user interests in real time. However, traditional methods struggle to efficiently integrate and standardize data, and to perform real-time analysis and delivery. Furthermore, ensuring privacy remains a crucial challenge.

[0647] 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.

[0648] In this invention, the server includes means for collecting customer information, means for integrating and standardizing the information collected by said means, and means for using a generative model to analyze the integrated information. This enables the real-time delivery of personalized advertisements based on location information and behavioral history, as well as the measurement of campaign effectiveness and the suggestion of improvements.

[0649] "Customer information" refers to data collected by companies, such as individual attributes, purchase history, interests, and behavioral history.

[0650] "Integration" refers to combining data of different formats and types into a single, unified dataset.

[0651] "Standardization" refers to unifying data formats and preparing them in a way that makes them easier to process and analyze.

[0652] A "generative model" is a model that uses machine learning algorithms to analyze data and make predictions or suggestions.

[0653] "Advertising planning" is the process of designing a strategy for how to deploy advertising based on specified conditions.

[0654] "Location information" refers to data that indicates the geographical location of a device or user.

[0655] "Activity history" refers to a record of actions and movements performed by a user both online and offline.

[0656] "Real-time" refers to situations where information or actions are performed almost instantly.

[0657] "Effectiveness measurement" is the analysis used to evaluate the performance of a campaign or advertisement that has been implemented.

[0658] An "improvement suggestion" is a specific proposal to improve future measures based on the measurement results.

[0659] The system implementing this invention primarily consists of three parties: a server, a terminal, and a user. The server efficiently collects, integrates, and standardizes customer information. This includes utilizing a secure database via an API. The server passes the integrated information to a generative AI model, which is used to analyze customer purchasing trends and interests. This generative AI model uses machine learning modules and forms a crucial foundation for advertising planning that drives the next steps.

[0660] The advertising plan proposed by the generative model is sent to the device. The device then uses location services and past behavioral history to deliver the most relevant ads to the user in real time. Specifically, advertising information is seamlessly notified via smartphones and smart glasses. For example, when a user approaches a particular store, they are immediately notified of special campaigns at that store.

[0661] Furthermore, the server measures the performance of delivered ads and campaigns and performs data analysis to inform future strategies. This eliminates waste in marketing activities and enables effective strategic adjustments.

[0662] As a concrete example, by notifying users who visit shopping malls near them on weekends in real time about special sales from fashion brands, it is possible to encourage them to visit the stores. This implementation is useful not only because it improves the user's purchasing experience, but also because it improves the sales effectiveness of the stores.

[0663] An example of a prompt for a generative AI model would be: "Based on the user's interests, please generate advertisements for the products and services most relevant to their current location."

[0664] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0665] Step 1:

[0666] The server collects customer information from companies via APIs. It receives customer information such as purchase history and communication history as input and securely stores it in a database. This integrates the company's accumulated customer information within the server, preparing it for use in subsequent processing.

[0667] Step 2:

[0668] The server integrates the collected customer information and standardizes the data format. It receives customer data in different formats as input, transforms and integrates them to generate a consistent dataset. This standardized data becomes available for analysis in the generated AI models.

[0669] Step 3:

[0670] The server analyzes integrated data using a generative AI model. Using standardized customer data as input, it applies machine learning algorithms to predict customer purchasing trends and interests. Based on this analysis, an optimal advertising plan is developed for each customer, and instructions are sent to the terminal.

[0671] Step 4:

[0672] The device delivers ads to users in real time based on the advertising plan received from the server. It uses the user's location information and past behavioral history as input, selecting and displaying appropriate ads based on this information. This ensures that users receive the most relevant ads in a timely manner.

[0673] Step 5:

[0674] The server measures the effectiveness of implemented advertising campaigns. It receives performance data from delivered ads as input and performs analysis. Based on this analysis, feedback is generated to improve future advertising strategies, enabling companies to streamline their marketing activities.

[0675] 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.

[0676] This invention is a marketing system that optimizes ad delivery by collecting first-party data and recognizing the user's emotional state using an emotion engine. This system consists primarily of a server, a terminal, and the user.

[0677] First, the server collects customer data from multiple data sources within the company via APIs. This data includes purchase history, communication history, and data to capture the user's emotional state. Emotional data is obtained using techniques such as analyzing voice tone and facial expressions. This data is stored in a database and integrated through the customer data platform.

[0678] Next, on the server, the integrated data is analyzed by a generative model. This model utilizes machine learning algorithms to predict not only customer purchasing intent and behavioral trends, but also their emotional state based on emotional data. Based on these analysis results, an emotion engine operates to design an optimal advertising delivery strategy tailored to the user's emotions.

[0679] The device handles ad delivery. Based on the ad delivery plan received from the server, the device presents ads to the user in real time. Here, the device reflects the user's emotional state as recognized by the emotion engine and customizes the ad content and frequency accordingly. For example, when a user is feeling stressed, it displays ads suggesting products with relaxing effects, thus conducting promotions tailored to the user's emotional state.

[0680] Users can react to advertisements displayed on their devices. They can click links to learn more about ads that interest them, or use coupons provided to purchase products.

[0681] Finally, the server measures the effectiveness of the advertising campaign and generates feedback on areas for improvement to increase the success rate. This allows the system to adjust future ad delivery strategies, enabling more sophisticated targeting and personalization.

[0682] In this way, the present invention improves the accuracy of advertising and maximizes marketing effectiveness through advanced customer service combined with emotion recognition technology.

[0683] The following describes the processing flow.

[0684] Step 1:

[0685] The server collects customer data from various data sources within the company using APIs. This includes purchase history, communication logs, and user sentiment data, which is obtained using voice analysis and facial recognition technology. The collected data is temporarily stored in a database.

[0686] Step 2:

[0687] The server integrates data collected using the customer data platform. It standardizes different data formats and removes duplicate data. The integrated dataset should contain information useful for understanding user behavior and emotional states.

[0688] Step 3:

[0689] The server inputs integrated data into a generative model for analysis. The generative model uses machine learning to predict customer purchasing trends and emotional states. This analysis includes reflecting emotional data in real time and determining which advertisements are effective in which situations.

[0690] Step 4:

[0691] The server uses the analysis results obtained from the generative model to enable the emotion engine to design an ad delivery strategy that is tailored to the user's emotional state. This strategy includes the content, timing, and frequency of the ads and is designed to adapt to the user's current emotions.

[0692] Step 5:

[0693] The device displays ads to the user in real time based on the ad delivery strategy provided by the server. The device selects and displays the appropriate ad content at the optimal time based on the user's location information and feedback from the sentiment engine.

[0694] Step 6:

[0695] Users receive advertisements and suggestions displayed on their devices and can click or tap on ads that interest them to view details. They can then use coupons for products they are interested in and proceed to make a purchase.

[0696] Step 7:

[0697] The server collects results after ad delivery and performs campaign effectiveness analysis. It measures ad effectiveness considering the impact of emotions and generates improvement suggestions to reflect in future ad delivery strategies. The goal is to continuously improve ad performance.

[0698] (Example 2)

[0699] 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".

[0700] In modern marketing, there is a demand for targeted advertising that responds to the diverse needs and emotional states of consumers. However, traditional methods have faced challenges in designing optimal advertising strategies due to insufficient analysis of collected data and inadequate personalization for individual consumers. A new system is needed to deliver more targeted advertising and increase consumer purchasing intent.

[0701] 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.

[0702] In this invention, the server includes means for collecting data, means for standardizing the aggregated data, and means for utilizing generative models for analysis. This enables the creation of accurate advertising strategies based on consumer sentiment and the delivery of personalized advertisements in real time.

[0703] "Means of data collection" refers to the technical processes for obtaining necessary information from various data sources.

[0704] "Methods for standardizing aggregated data" refer to methods for transforming collected data into a consistent format and preparing it in a way that facilitates analysis.

[0705] "Methods of using generative models" refer to techniques that utilize artificial intelligence and machine learning technologies to analyze data and generate patterns and predictions.

[0706] "Methods for building advertising strategies based on emotional information" refers to the process of analyzing consumers' emotional states and designing strategies to effectively deliver advertisements that correspond to those states.

[0707] A "means of presenting advertisements in real time" refers to a system that displays advertisements to consumers instantly without any time delay.

[0708] "Methods for measuring campaign effectiveness and generating improvement suggestions" refers to the process of analyzing the results of advertising activities and making suggestions for future activities based on that data.

[0709] "Behavioral information" refers to data about consumer behavior, such as consumer purchase history and website browsing history.

[0710] "Personalized advertising" refers to advertisements that are customized to the preferences and needs of each individual consumer.

[0711] "Diverse data sources" refers to different information sources, such as customer information provided by companies and data obtained from online platforms.

[0712] A "customer information platform" is a system that centrally manages and analyzes diverse customer data.

[0713] This invention is an advanced marketing system that personalizes advertisements based on the emotional state of consumers and presents them at the appropriate time. This system consists primarily of a server, terminals, and users.

[0714] The server collects consumer behavior information from various data sources via APIs. This data includes purchase history, communication history, and emotional data derived from voice tone and facial expression analysis. The server integrates this data into a database and manages it centrally using a customer information platform. In this process, voice recognition software and image analysis software are used to convert the data into a standardized format.

[0715] Using integrated data, the server employs generative AI models to analyze consumer behavior patterns and emotional states. This allows the server to build an advertising delivery strategy best suited to the customer's current emotions. The emotion engine optimizes the ad content, timing, and frequency based on the analysis results. For example, if a consumer is feeling stressed, the server will create an ad suggesting products with relaxing effects.

[0716] The device displays advertisements to consumers in real time based on the ad delivery plan received from the server. The device constantly communicates with the server, reflecting the latest sentiment data to display the most relevant advertising information.

[0717] Users can react to advertisements displayed on their devices. By clicking on an ad that interests them, they can obtain more information and even use coupons to purchase products. This improves the consumer experience and maximizes the effectiveness of advertising.

[0718] As a concrete example, if the server detects that a consumer is in a relaxed emotional state, an advertisement for a relaxing aromatherapy product will be displayed on the device. If the user clicks on the advertisement and checks the details on the product page, a coupon will be offered, which can encourage them to make a purchase.

[0719] An example of a prompt from this system is, "How can I design a model that integrates customer data and delivers the most relevant ads in real time based on the customer's emotional state?" This prompt serves as a guideline when utilizing generative AI models.

[0720] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0721] Step 1:

[0722] The server collects consumer behavior information from various data sources via APIs. Inputs include raw data such as purchase history, voice tone, and facial expressions. This data is analyzed using speech recognition and image analysis software, and the output is converted into a standardized format. Specifically, the server captures data in real time and immediately saves it to the database.

[0723] Step 2:

[0724] The server integrates the aggregated data into the customer information platform and prepares the dataset. The input is the standardized data set obtained in step 1. Using a unification technique, it outputs integrated information for each customer. Specifically, it unifies different data formats, performs cleanup processing, and then restores the data in the database.

[0725] Step 3:

[0726] The server uses integrated data to perform analysis with a generative AI model. The input is the integrated customer data obtained in step 2. The model predicts the customer's emotional state and behavioral patterns and outputs the analysis results. Specifically, it utilizes machine learning algorithms to perform cluster analysis and regression analysis on the data to generate prediction results.

[0727] Step 4:

[0728] The server activates an emotion engine based on the analysis results and designs user-specific ad delivery strategies. The input is the predictive analysis results from step 3. Here, strategies such as ad content and delivery frequency that take emotional states into account are obtained as output. Specifically, a template is used to design a scenario and generate a strategy document.

[0729] Step 5:

[0730] The device displays advertisements in real time based on the ad delivery plan received from the server. The input is the ad delivery plan from step 4. The goal is to instantly display the appropriate advertisement to the user, and the ad display results are output. Specifically, the advertisement is displayed to the user using the display or push notification.

[0731] Step 6:

[0732] Users can react to advertisements displayed on their devices. The input is the advertisement itself displayed on the device. The output is the user's reaction, such as clicking, purchasing, or using a coupon. Specifically, users can click a link to access detailed information and complete a purchase.

[0733] Step 7:

[0734] The server measures the effectiveness of advertising campaigns and generates feedback for future strategies. Inputs include purchase history and user response data. Based on this evaluation data, it outputs effectiveness measurement results and provides improvement suggestions. Specifically, it analyzes KPIs and generates reports based on click-through rates and conversion rates.

[0735] (Application Example 2)

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

[0737] Modern advertising doesn't always adequately address the diverse emotional states of users. The inability to deliver ads that resonate with users' emotions leads to insufficient advertising effectiveness. Furthermore, accurately measuring the impact of advertising on users and incorporating that into future advertising strategies is also difficult.

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

[0739] In this invention, the server includes means for collecting user emotional data, means for integrating and analyzing the emotional data in a standardized format, and means for using a generative model that optimizes ad delivery based on the emotional data. This enables the provision of optimal ads according to the user's emotional state, as well as accurate measurement and improvement of ad effectiveness.

[0740] "User emotional data" refers to biological or behavioral indicators that show a user's emotional state, such as information obtained from voice tone or facial expressions.

[0741] A "standardized format" refers to a state where data is converted into a consistent format, allowing for unified processing of information from different data sources.

[0742] A "generative model" is a computational model that uses statistical or machine learning algorithms to make predictions or optimizations from data.

[0743] "Real-time delivery" refers to the process of immediately presenting advertisements and services according to the user's situation.

[0744] "Advertising effectiveness" refers to measuring the degree to which an advertisement influences users and the resulting changes in their responses.

[0745] An "analysis platform" is an integrated system infrastructure used to import and analyze multiple data sets.

[0746] In this invention, the server collects user emotional data using a camera and microphone. This emotional data includes signals from voice tone and facial expressions. This data is converted into a digital format using software such as OpenCV and analyzed by an emotion recognition library. As a result of this analysis, the user's emotional state is identified, and the emotion engine utilizes a generative model to select appropriate advertisements based on that state.

[0747] The device processes the results of the emotional data analysis received from the server in real time and displays advertisements optimized for the user. These advertisements are customized according to the emotional state the user is expressing. For example, if the user is feeling stressed, advertisements for products related to relaxation will be displayed.

[0748] Users can use advertisements displayed on their devices to research details about products and services that interest them and take action to make a purchase. The server collects these responses, analyzes the effectiveness of the advertising campaign, and uses the results to inform future advertising strategies. This analysis uses advertising effectiveness measurement software, and the generated data is used to suggest improvements.

[0749] One concrete example is a scenario where the program detects a user relaxing at home at night and displays an advertisement for a relaxation music app. Another example of a prompt that utilizes a generative AI model is: "What strategy would you employ to analyze the facial expressions captured by the camera while the user is looking at their device and display optimized advertisements when the user is feeling stressed?"

[0750] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0751] Step 1:

[0752] The server collects user emotion data via camera and microphone. This input includes biometric information such as voice tone and facial expressions. The data is acquired in digital format and converted to a standardized data format using libraries such as OpenCV. This provides the foundational data for emotion recognition processing.

[0753] Step 2:

[0754] The server analyzes the collected emotion data using an emotion recognition library. This data is used as input for calculations to infer the user's emotional state. Features are extracted from the emotion data, and the emotional states are labeled. The output is data representing the user's current emotional state.

[0755] Step 3:

[0756] The server uses a generative model to optimize ad delivery strategies based on analyzed emotional states. It uses the input emotional state data to calculate which ad is most effective and executes the ad selection process. In this step, ad strategies are recommended using prompts powered by the generative AI model. The output is the optimal ad suggestion to present to the user.

[0757] Step 4:

[0758] The device presents advertisements to the user in real time based on optimized advertising information obtained from the server. Inputs include ad proposals and user usage data, which are used to adjust the ad content and timing. The device displays custom messages and images on its screen, enabling real-time user interaction.

[0759] Step 5:

[0760] Users can respond to advertisements displayed on their devices and take further action on those that interest them. User input is done through methods such as touching or clicking, allowing them to navigate to purchase pages or obtain detailed information. This generates user engagement that leverages the effectiveness of the advertisements.

[0761] Step 6:

[0762] The server collects user responses to ads and analyzes the effectiveness of the campaign. Using the data obtained from users as input, calculations are performed to measure the success rate and engagement level of the ads. This generates suggestions for improvement for the next advertising strategy, contributing to improved accuracy in ad delivery.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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."

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] The following is further disclosed regarding the embodiments described above.

[0785] (Claim 1)

[0786] A device for collecting customer data,

[0787] A device for integrating and standardizing the data collected by the said device,

[0788] A device that uses a generative model to analyze integrated data,

[0789] A device for designing an advertising delivery strategy using the generative model,

[0790] A device that delivers advertisements in real time,

[0791] A device that measures the effectiveness of a campaign and generates improvement suggestions,

[0792] A marketing system that includes this.

[0793] (Claim 2)

[0794] A marketing system according to claim 1, comprising means for collecting customer behavior data and delivering personalized advertisements based on said data.

[0795] (Claim 3)

[0796] The marketing system according to claim 1, comprising means for integrating data collected from multiple data sources using a customer data platform.

[0797] "Example 1"

[0798] (Claim 1)

[0799] Means of collecting information,

[0800] Means for integrating and standardizing the information,

[0801] A means of analyzing integrated information using a generation AI model,

[0802] A means of designing an information distribution strategy based on the analysis results,

[0803] A means of delivering information in real time and displaying information based on location information and activity history,

[0804] A means of measuring the effectiveness of information distribution and generating improvement suggestions,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, which collects operational information and delivers personalized information based on said data.

[0808] (Claim 3)

[0809] The system according to claim 1, which integrates information collected from multiple sources using an information data platform.

[0810] "Application Example 1"

[0811] (Claim 1)

[0812] Means of collecting customer information,

[0813] A means for integrating and standardizing the information collected by the said means,

[0814] A means of using a generative model to analyze integrated information,

[0815] A means for designing an advertising plan using the generative model,

[0816] A means of delivering advertisements in real time based on the user's location information and behavioral history,

[0817] A means of measuring the effectiveness of a campaign and generating improvement suggestions,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, which collects customer location information and behavioral history and displays personalized advertisements in real time based on said information.

[0821] (Claim 3)

[0822] The system according to claim 1, comprising means for integrating information collected from multiple sources using a customer data platform.

[0823] "Example 2 of combining an emotion engine"

[0824] (Claim 1)

[0825] Means of collecting data,

[0826] Means for standardizing aggregated data,

[0827] Methods for using generative models for analysis,

[0828] A means of building advertising strategies based on emotional information,

[0829] A means of presenting advertisements in real time,

[0830] A means of measuring the effectiveness of a campaign and generating improvement suggestions,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, comprising means for collecting behavioral information and delivering personalized advertisements based on said information.

[0834] (Claim 3)

[0835] The system according to claim 1, comprising means for integrating information obtained from diverse data sources using a customer information platform.

[0836] "Application example 2 when combining with an emotional engine"

[0837] (Claim 1)

[0838] Means of collecting user sentiment data,

[0839] A means for integrating the emotional data and analyzing it in a standardized format,

[0840] A method using a generative model that optimizes ad delivery based on sentiment data,

[0841] A means of delivering advertisements in real time according to the user's emotional state,

[0842] A means to measure the effectiveness of advertising displays and generate suggestions for improving the next advertising strategy,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, which can analyze a user's emotional state and provide personalized advertisements based on that state.

[0846] (Claim 3)

[0847] The system according to claim 1, comprising means for collecting emotional data from multiple sensor devices and integrating the data using a single analysis platform. [Explanation of Symbols]

[0848] 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 device for collecting customer data, A device for integrating and standardizing the data collected by the said device, A device that uses a generative model to analyze integrated data, A device for designing an advertising delivery strategy using the generative model, A device that delivers advertisements in real time, A device that measures the effectiveness of a campaign and generates improvement suggestions, A marketing system that includes this.

2. The marketing system according to claim 1, comprising means for collecting customer behavior data and delivering personalized advertisements based on said data.

3. The marketing system according to claim 1, comprising means for integrating data collected from multiple data sources using a customer data platform.

Images