System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting real-time word-of-mouth or feedback information from users; a generative AI engine for analyzing the collected information to identify user interests and preferences; means for automatically generating custom advertisements based on the identified interests and preferences; means for delivering the generated custom advertisements to user terminals; and means for collecting feedback from users again after delivering the advertisements to evaluate and optimize the effectiveness of the advertisements.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional ad delivery systems tend to display ads that are of little interest to users, resulting in a poor user experience. Furthermore, increasing the effectiveness of ads requires repeated hypothesis testing, which is time-consuming and labor-intensive. Furthermore, because ads are not optimized in real time, it is difficult to quickly respond to changes in user interests. The purpose of this invention is to solve these problems and provide users with a more satisfying advertising experience. [Means for solving the problem]

[0005] This invention is a system that includes the following means: First, it includes means for collecting word-of-mouth or feedback data from users in real time. Next, it uses a generation AI engine that analyzes the collected data and identifies the user's interests and preferences. It includes means for automatically generating customized advertisements based on the identified interests and preferences. It includes means for delivering the generated customized advertisements to user devices, and includes means for collecting feedback from users again after the advertisements are delivered, and evaluating and optimizing the effectiveness of the advertisements. In this way, advertisements are always optimized based on the latest user interests, making it possible to provide higher satisfaction.

[0006] "Word of mouth" is information that users share with other users about their feelings and opinions about products and services.

[0007] "Feedback" refers to information such as ratings, comments, and opinions given by users regarding services or products.

[0008] A "generative AI engine" is an artificial intelligence program that identifies users' interests and preferences based on collected data and automatically generates advertising content.

[0009] "Custom Ads" refers to personalized ads generated based on a particular user's interests and preferences.

[0010] A "user device" is an electronic device, such as a smartphone, PC, or tablet, that a user uses to access applications or websites via the Internet.

[0011] "Natural language processing" is a technology that allows computers to understand and process human language.

[0012] A "deep learning model" is a machine learning model that uses a multi-layer neural network to automatically learn features from large amounts of data and perform analysis and predictions.

[0013] "User behavioral data" refers to data about the actions a user takes after viewing an advertisement (clicks, purchases, skips, etc.).

[0014] A "marketing automation tool" is a software tool that automatically delivers, measures effectiveness, and optimizes advertising.

[0015] "Means for evaluating and optimizing effectiveness" refers to methods and tools for analyzing user feedback and behavioral data and improving advertising content and distribution strategies based on that data. [Brief explanation of the drawings]

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

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

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] System Overview

[0038] The system has the ability to automatically generate and distribute personalized ads based on user reviews and feedback. Specifically, it analyzes collected data and uses a generative AI engine to generate custom ads. The ads are then distributed to user devices, and feedback is collected again to optimize advertising effectiveness.

[0039] Server Processing

[0040] Data collection

[0041] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[0042] Data analysis

[0043] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether a user's comment is positive, negative, or neutral. Based on this information, the server can identify the user's interests and preferences.

[0044] Ad Generation

[0045] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest users.

[0046] Ad serving

[0047] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[0048] Feedback collection and optimization

[0049] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0050] Terminal handling

[0051] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[0052] User Behavior

[0053] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided.

[0054] This system generates ads based on real-time user feedback, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' interest and maximizing advertising effectiveness.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[0058] Step 2:

[0059] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[0060] Step 3:

[0061] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[0062] Step 4:

[0063] The server inputs the stored data into a natural language processing (NLP) engine to extract text and keywords, such as "lipstick" and "like."

[0064] Step 5:

[0065] The server performs sentiment analysis to determine whether a user's comments are positive, negative, or neutral, and uses this information to identify the user's interests and preferences.

[0066] Step 6:

[0067] The server then feeds the analysis results into a generative AI engine that automatically generates custom ads based on the user's interests and preferences. These ads include text and visuals such as "Try these amazing shades!"

[0068] Step 7:

[0069] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[0070] Step 8:

[0071] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[0072] Step 9:

[0073] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[0074] Step 10:

[0075] Users respond to the ads they see by clicking on them, skipping them, or making a purchase, and this behavioral data is collected by the device.

[0076] Step 11:

[0077] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[0078] Step 12:

[0079] The server analyzes the collected behavioral data to evaluate the effectiveness of advertising, for example, calculating click-through rates and conversion rates.

[0080] Step 13:

[0081] The server inputs the results of the effectiveness evaluation back into the AI ​​engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and ads with low response rates are improved.

[0082] Step 14:

[0083] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] In modern advertising delivery, it is a difficult challenge to efficiently generate and deliver personalized advertisements that match users' interests and preferences. To solve this problem, a system is needed that effectively utilizes user word-of-mouth and feedback to optimize advertisements in real time.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes means for collecting word-of-mouth or feedback data from user terminals in real time, means for analyzing the collected data using a natural language processing engine and identifying the user's interests and preferences, means for inputting prompt sentences into a generation AI engine based on the identified interests and preferences and automatically generating a customized advertisement, means for delivering the generated customized advertisement to the user terminals via a marketing automation tool, and means for collecting feedback data from users after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement.

[0089] This makes it possible to generate optimal advertisements based on users' interests and preferences in real time and deliver them efficiently.

[0090] A "user terminal" is a device operated by a user, and includes smartphones, tablets, personal computers, etc.

[0091] "Review or Feedback Data" means information posted by users through an application or website, and may be in the form of text, images, audio, or other information.

[0092] A "natural language processing engine" is a software tool that analyzes text data and performs keyword extraction and sentiment analysis, and examples include SpaCy and NLTK.

[0093] A "generative AI engine" is an artificial intelligence engine that generates custom ads based on user interests and preferences, and examples include OpenAI's GPT-4.

[0094] A "prompt sentence" is an instruction sentence input into the generative AI engine, and is specific input data for generating a custom ad.

[0095] "Custom ads" are ads automatically generated based on a user's interests and preferences, and come in the form of text, images, videos, and more.

[0096] A "marketing automation tool" is a software tool for automating advertising and marketing activities, such as HubSpot or Marketo.

[0097] "Feedback data" refers to information about a user's response to an advertisement (click, skip, purchase, etc.).

[0098] A "collection means" is a method or device for acquiring data from a user terminal.

[0099] "Means for analyzing" refers to a method or device for analyzing collected data and identifying user interests and preferences.

[0100] "Means for generating" refers to a method or device for inputting a prompt sentence into a generating AI engine based on the analysis results and generating a custom advertisement.

[0101] The "means for delivering" refers to a method or device for transmitting the generated custom advertisement to a user terminal.

[0102] The "optimization means" refers to a method or device for analyzing feedback data collected after advertisement distribution, and evaluating and improving the effectiveness of the advertisement.

[0103] This invention relates to a system that generates and distributes personalized advertisements based on word-of-mouth and feedback data collected from users. Specifically, it collects user behavior data in real time, analyzes it with a natural language processing (NLP) engine, and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback data is collected again to optimize the effectiveness of the advertisements.

[0104] Server Processing

[0105] Data collection

[0106] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user logs into a cosmetics app and posts a comment saying, "I love your new lipstick," that information is sent to the server.

[0107] Data analysis

[0108] The server analyzes the collected data using a natural language processing (NLP) engine (such as SpaCy or NLTK). This allows it to extract keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. Based on this information, it can identify the user's interests and preferences.

[0109] Ad Generation

[0110] Using the analysis results, the server inputs the data into a generative AI engine (e.g., OpenAI's GPT-4) to automatically generate custom ads tailored to the user's interests and preferences. For example, by inputting the prompt "Create an ad for a new lipstick color," the server generates ad copy such as "Try this amazing shade!"

[0111] Ad serving

[0112] The generated custom ads are delivered to the user's device via a marketing automation tool (e.g., HubSpot or Marketo). The server also considers the optimal delivery timing and frequency based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ads to be delivered at night.

[0113] Feedback collection and optimization

[0114] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click rates can be continued as they are, while ads with low responses can be changed.

[0115] Terminal handling

[0116] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[0117] User Behavior

[0118] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, and users respond to the ads. This response is fed back into the generation and distribution of the next ad, allowing the system to continue providing ads that are more relevant to the user.

[0119] This system generates advertisements based on real-time user feedback and provides a constantly optimized advertising experience, effectively delivering advertisements that capture users' interest and maximizing advertising effectiveness.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] The user enters the feedback data.

[0123] Users submit reviews and feedback on applications and websites, and this data can include text, images, and audio.

[0124] Specific behavior: A user logs into a cosmetics app and posts a comment saying, "I love your new lipstick." The comment is sent to the central server through the application server.

[0125] Input: User comments and feedback.

[0126] Output: Review data collected on the server.

[0127] Step 2:

[0128] The server analyzes the collected data using a natural language processing (NLP) engine.

[0129] The server feeds the received reviews and feedback data into an NLP engine (e.g., SpaCy or NLTK), where keyword extraction and sentiment analysis are performed.

[0130] Specific operation: The server analyzes the comment "I like the new lipstick" and extracts keywords such as "lipstick" and "like." At the same time, it uses sentiment analysis to determine whether the comment is positive.

[0131] Input: Collected review data.

[0132] Output: Keyword and sentiment analysis results.

[0133] Step 3:

[0134] The server passes the analysis results to a generative AI engine to generate custom ads.

[0135] The server inputs the analysis results of the NLP engine into a generative AI engine (e.g., OpenAI's GPT-4) and requests it to generate a custom ad.

[0136] Specific operation: The server sends the prompt "Please create an advertisement for a new lipstick color" to the AI ​​engine. The AI ​​engine generates the advertisement copy "Try this amazing shade!"

[0137] Input: Keywords and sentiment analysis results.

[0138] Output: The generated custom ad copy.

[0139] Step 4:

[0140] The server delivers the generated custom advertisement to the user terminal via a marketing automation tool.

[0141] The generated advertisement is passed to an advertisement distribution tool (e.g., HubSpot or Marketo) and sent to the user's device at the optimal time.

[0142] Specific operation: The server sets up nighttime ad distribution based on the user's behavioral history. The ad distribution tool sends the ad to the user's smartphone.

[0143] Input: Your generated custom ad copy.

[0144] Output: Advertisement delivered to user device.

[0145] Step 5:

[0146] The server collects feedback data from users after delivering the advertisements, and evaluates and optimizes the effectiveness of the advertisements.

[0147] The server collects and analyzes data such as ad click rates, purchase rates, and skip rates, and uses this information to generate the next ad.

[0148] Specific operation: When a user clicks on an ad, the data is sent to the server. The server analyzes the click data and evaluates the effectiveness of the ad. If the click rate is high, the same ad format will continue to be displayed, but if the response is low, the ad content will be changed.

[0149] Input: User feedback data.

[0150] Output: Evaluation of the effectiveness of the ad and the results reflected in the next ad generation.

[0151] The above is the specific processing flow of this system, which makes it possible to generate and distribute advertisements optimized for users in real time.

[0152] (Application example 1)

[0153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0154] Conventional ad delivery systems have difficulty accurately grasping users' interests and preferences, making it difficult to deliver ads effectively. In particular, there is a lack of a way to deliver ads optimized for individual users in a timely manner, which reduces the effectiveness of advertising.

[0155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0156] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine for analyzing the collected data and identifying user interests and preferences; means for automatically generating customized advertisements based on the identified interests and preferences and creating advertisement copy using prompt text using a generation AI model; means for delivering the generated customized advertisements to user devices at optimal times based on user behavior data; and means for collecting user feedback again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to generate personalized advertisements based on user preferences in real time and deliver them at optimal times.

[0157] "User" refers to the general consumer who uses a product or service, and in particular the person who provides word-of-mouth or feedback.

[0158] "Review or Feedback Data" refers to any user feedback or evaluation information, such as text, images, or audio, posted by users on an application or website.

[0159] "Means of collection" refers to the mechanism for obtaining word-of-mouth or feedback data from user devices in real time and sending it to a server.

[0160] "Analysis means" refers to technologies used to analyze collected reviews or feedback data and identify user interests and preferences.

[0161] A "generative AI engine" refers to an artificial intelligence engine that analyzes user preferences based on collected data and generates appropriate advertisements.

[0162] A "prompt" is an input to a generative AI model, and refers to an instruction to request the generation of a specific ad copy or sentence.

[0163] "Generative AI model" refers to an artificial intelligence model that automatically generates advertising copy and related information based on a given prompt.

[0164] "Ad generation method" refers to a mechanism that automatically generates custom advertisements based on a user's interests and preferences.

[0165] "Timely delivery" refers to a system that delivers advertisements at the optimal time based on the user's behavioral history and usage patterns.

[0166] "Means of collecting feedback" refers to a system that recollects user reactions and evaluation data after advertisement delivery and sends it to a server.

[0167] "Means for evaluating and optimizing advertising effectiveness" refers to a mechanism for analyzing the effectiveness of advertising using collected feedback data and reflecting the results in the generation and distribution of the next advertisement.

[0168] "User terminal" refers to a device that can connect to the Internet and is used by a user, such as a smartphone, tablet, or PC.

[0169] System Overview

[0170] This invention is a system that automatically generates and distributes personalized advertisements based on user behavioral data and feedback data. The system analyzes collected data and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback is collected again to optimize the effectiveness of the advertisements.

[0171] Server Processing

[0172] Data collection

[0173] The server receives real-time user reviews and feedback data from users' devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment on an online shopping site saying, "These sneakers are very comfortable," that information is sent to the server.

[0174] Data analysis

[0175] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "sneakers" and "comfortable" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. This information is used to identify the user's interests and preferences.

[0176] Ad Generation

[0177] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. Specific ad copy is generated by inputting a prompt into the generative AI model. For example, in the previous example, the prompt would be, "Generate ad copy for a new product suitable for a user looking for comfortable sneakers." Using this prompt, the generative AI model would generate ad copy such as, "Our newly released sneakers will provide you with the ultimate in comfort. Click now to see the details!"

[0178] Ad serving

[0179] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[0180] Feedback collection and optimization

[0181] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0182] User terminal processing

[0183] The user device receives the advertisement and feedback request sent from the server and displays it to the user in an appropriate interface. When the user responds to the advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on an advertisement for sneakers on their smartphone, the information is immediately sent to the server and used for later analysis.

[0184] Hardware and software used

[0185] The servers are deployed on cloud platforms (e.g., AWS, Google Cloud, Azure). Natural language processing engines (e.g., Google NLP, IBM Watson) are used for analysis, generative AI engines (e.g., OpenAI GPT-4) are used for ad generation, and marketing automation tools (e.g., Mailchimp, HubSpot) are used for ad delivery.

[0186] With the above configuration, it is possible to generate personalized advertisements based on user preferences in real time and deliver them at the optimal timing.

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] The server collects word-of-mouth and feedback data from user devices in real time. Specifically, it receives text, images, and audio data posted by users on applications and websites and stores this data on a cloud server. The input is word-of-mouth and feedback data from users, and the output is the data stored on the cloud server.

[0190] Step 2:

[0191] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it extracts keywords from the text data and performs sentiment analysis to determine whether the comments are positive, negative, or neutral. The input is the reviews and feedback data stored on the cloud server, and the output is the extracted keywords and sentiment information.

[0192] Step 3:

[0193] The server inputs a prompt text based on the analysis results into the generative AI engine, which then generates a custom ad tailored to the user's interests and preferences. Specifically, a prompt text such as "Please generate advertising copy for a new product suitable for a user looking for comfortable sneakers" is generated and input into the generative AI model. The input is a prompt text based on the analysis results, and the output is the advertising copy created by the generative AI model.

[0194] Step 4:

[0195] The server delivers the generated custom ads to the user's device via a marketing automation tool. Specifically, it configures the settings to deliver ads at the optimal time based on the user's behavioral history. For example, if a user frequently uses the app at night, it delivers ads at night. The input is the generated ad copy and the user's behavioral history, and the output is the ad delivered to the user's device.

[0196] Step 5:

[0197] When a user responds to an ad (by clicking, skipping, purchasing, etc.), the device sends that data to the server. Specifically, when a user clicks on an ad, that information is immediately sent to the server and stored on the cloud server. The input is the user's response data to the ad, and the output is the response data stored on the cloud server.

[0198] Step 6:

[0199] The server analyzes the collected feedback data and evaluates the effectiveness of the ads. Specifically, it analyzes which ads were effective based on behavioral data such as click rates, skip rates, and purchase rates. The input is the feedback data stored on the cloud server, and the output is the evaluation results of the advertising effectiveness.

[0200] Step 7:

[0201] The server then performs optimization based on the evaluation results to reflect them in the next ad generation. Specifically, ads with high click-through rates are continued without any improvements, while ads with low responses are modified in content or targeting. The input is the evaluation results of the advertising effectiveness, and the output is optimization data for the next ad generation.

[0202] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0203] System Overview

[0204] This system has the ability to personalize, automatically generate, and deliver advertisements based on user reviews and feedback. It also combines an emotion engine that analyzes user emotions to achieve even more accurate ad generation and delivery. Specifically, it analyzes collected data and generates custom ads using the emotion engine and generative AI engine. The ads are then delivered to user devices, and feedback is collected again to optimize advertising effectiveness.

[0205] Server Processing

[0206] Data collection

[0207] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[0208] Data analysis

[0209] The server inputs the collected data into a natural language processing (NLP) and emotion engine to extract text and analyze user sentiment. This allows it to extract keywords such as "lipstick" and "like" and determine whether the comment is positive, negative, or neutral. This information is then used to identify the user's interests and preferences.

[0210] Ad Generation

[0211] Using the results of the analysis and sentiment analysis, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest the user.

[0212] Ad serving

[0213] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery, delivering them based on the user's emotions and behavioral history. For example, if a user frequently uses the app at night and has positive emotions at that time, the server will set the ads to be delivered at night.

[0214] Feedback collection and optimization

[0215] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the generative AI and emotion engine optimize the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0216] Terminal handling

[0217] The user device receives advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicking, skipping, etc.), the data is sent to the server. Furthermore, the user's facial expressions and behavior are detected using cameras and sensors, and sent to the emotion engine for real-time emotion analysis. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server and used for subsequent analysis.

[0218] User Behavior

[0219] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided. In addition, the user's facial expressions and behavior when viewing an ad are also sent to the emotion engine, and this is used as data for ad optimization.

[0220] This system generates ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' attention and maximizing advertising effectiveness.

[0221] The processing flow will be explained below.

[0222] Step 1:

[0223] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[0224] Step 2:

[0225] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[0226] Step 3:

[0227] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[0228] Step 4:

[0229] The server inputs the stored data into a natural language processing (NLP) engine and sentiment engine to extract text, analyze keywords, and analyze sentiment. For example, it can extract keywords such as "lipstick" and "like" and determine whether a comment is positive.

[0230] Step 5:

[0231] The server uses the analysis results of the emotion engine to determine the user's emotional status, for example, determining that the user has a positive emotion.

[0232] Step 6:

[0233] The server inputs the analysis results and emotional status into a generation AI engine, which automatically generates custom ads tailored to the user's emotions as well as their interests and preferences. Specifically, it generates ad copy such as "Try these amazing shades!"

[0234] Step 7:

[0235] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[0236] Step 8:

[0237] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[0238] Step 9:

[0239] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[0240] Step 10:

[0241] Users respond to the ads displayed to them by clicking on them, making a purchase, or skipping them, and this behavioral data is collected by the device.

[0242] Step 11:

[0243] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[0244] Step 12:

[0245] The server analyzes the collected behavioral data and evaluates the effectiveness of the advertisement, specifically calculating click-through rates and conversion rates.

[0246] Step 13:

[0247] The server inputs the results of the effectiveness evaluation into the AI ​​engine and emotion engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and the content and targeting of ads with low response rates are changed.

[0248] Step 14:

[0249] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[0250] Step 15:

[0251] The device collects measurable emotional data (such as facial expressions and behavior) from the user and sends it to a server. For example, a camera or sensor can be used to detect the user's facial expressions, and the data is used for analysis.

[0252] Step 16:

[0253] The server analyzes the collected emotional data and uses it to optimize advertising. By including emotional data from users while they are viewing ads in the analysis of advertising effectiveness, more accurate optimization becomes possible.

[0254] Example 2

[0255] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0256] Conventional ad delivery systems have had difficulty in generating and delivering ads that fully incorporate real-time user reviews and feedback. Furthermore, they have been unable to adequately optimize ads based on user sentiment, making it difficult to maximize advertising effectiveness. Furthermore, there are issues with the significant time and effort required to utilize feedback after ad delivery to improve ad content and delivery strategies.

[0257] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0258] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; means for analyzing the collected data using a natural language processing and sentiment analysis engine to identify user interests and preferences; a generation AI engine for automatically generating customized advertisements based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisements to user devices and optimizing the timing and frequency of delivery; and means for collecting feedback data from users again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to effectively generate and deliver advertisements that are always optimized based on users' real-time feedback and sentiment data, thereby maximizing advertising effectiveness.

[0259] "User" means an end user who uses a particular application or website to post reviews and feedback.

[0260] "Real-time" means that processing occurs immediately the moment the user sends the data.

[0261] "Review or Feedback Data" means data such as text, images, or audio that a user provides through an application or website.

[0262] "Natural language processing" is a technology for converting text data into a format that is easy for machines to understand and analyzing its meaning.

[0263] An "emotion analysis engine" is a system that analyzes text data and information obtained from sensors to detect user emotions.

[0264] "Interests and Preferences" refers to the interest or preference a user has in a particular product, service, or topic.

[0265] A "generative AI engine" is an engine that uses artificial intelligence technologies such as deep learning models to analyze data and automatically generate custom advertisements.

[0266] "Custom Ads" are ads that are personalized based on a particular user's interests, preferences, and emotions.

[0267] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0268] "Optimizing delivery timing and frequency" refers to the process of adjusting the delivery of advertisements at the most effective time and frequency based on user behavioral history and emotional data.

[0269] "Feedback data" refers to data about the actions users take after viewing an ad (clicks, purchases, skips, etc.).

[0270] "Advertising effectiveness evaluation and optimization" refers to the process of analyzing collected feedback data, measuring advertising performance, and improving next ad generation and distribution strategies.

[0271] This invention is a system that automatically generates and distributes personalized advertisements based on real-time user reviews and feedback. Furthermore, by combining this with an emotion engine that analyzes user emotions, it is possible to generate and distribute advertisements with even greater accuracy.

[0272] The system uses the following hardware and software:

[0273] User device: A device such as a smartphone, tablet, or computer.

[0274] Server: A central computer that collects data, analyzes, generates and delivers advertisements.

[0275] Natural Language Processing (NLP) engine: Software that performs text analysis on user data.

[0276] Sentiment analysis engine: Software that analyzes emotions from user data.

[0277] Generative AI engine: Software that uses deep learning models to generate custom ads.

[0278] Marketing automation tool: Software that delivers generated advertisements to user devices.

[0279] The operation of the system will be specifically described below.

[0280] Data collection

[0281] When a user posts a review or feedback on a particular application or website, for example, when a user posts a comment in a cosmetics app saying, "I love your new lipstick," that data is sent from the user's device to a server. The data may include text, images, and audio.

[0282] Data analysis

[0283] The server inputs the collected data into a natural language processing (NLP) engine. The NLP engine extracts keywords from the text data. For example, the keywords "lipstick" and "like" are extracted. Then, a sentiment analysis engine analyzes the user's comments and classifies them as positive, negative, or neutral. In this case, a positive sentiment is detected from the expression "like."

[0284] Ad Generation

[0285] The server inputs the analysis results into a generation AI engine to generate custom ads based on the user's interests and preferences. For example, to generate an ad for a new lipstick color, the message "Try these amazing shades!" is generated. This ad copy includes specific words and images that are likely to interest the user.

[0286] Example prompt sentence:

[0287] "Generate ad copy for a new cosmetic product. A user review reads, 'I love your new lipstick.'"

[0288] Ad serving

[0289] The custom ads created by the generative AI engine are delivered to users' devices via marketing automation tools. The server calculates the optimal delivery timing and frequency based on the user's behavioral history and emotional data. For example, if a user uses the app more at night and shows positive emotions, the server will set the ads to be delivered at night.

[0290] Feedback collection and optimization

[0291] After an ad is delivered, the user's post-ad behavior (click, purchase, skip, etc.) is immediately collected as data. When a user clicks on a lipstick ad on their smartphone, that information is sent to the server. The server analyzes this feedback data and evaluates the effectiveness of the ad. Based on the evaluation results, the next ad generation and delivery strategy are optimized. For example, ads with high click rates can be continued as is, while ads with low responses can be improved.

[0292] This allows us to effectively generate and deliver ads that are always optimized based on real-time user feedback and sentiment data, maximizing advertising effectiveness.

[0293] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0294] Step 1: Data collection

[0295] The server collects word-of-mouth and feedback data from user devices in real time. For example, a user posts a comment in a cosmetics app saying, "I like the new lipstick." The input is the text, image, and voice data posted by the user, and the output is the data received by the server. In this way, the server obtains the feedback data entered by the user.

[0296] Step 2: Natural Language Processing (NLP)

[0297] The server inputs the collected data into a natural language processing (NLP) engine. Specifically, it analyzes the text data of user engagement and extracts keywords. The input is the collected feedback data, and the output is the extracted keywords. For example, "lipstick" and "like" are extracted. Through this analysis, the server understands the user's interests and preferences.

[0298] Step 3: Sentiment Analysis

[0299] The server inputs the keywords obtained from the NLP engine into the sentiment analysis engine. The input is the keywords from the NLP engine, and the output is the emotional assessment result (positive, negative, neutral). For example, the keyword "I liked it" is analyzed to determine positive emotions. Based on this information, the server understands the user's emotions.

[0300] Step 4: Ad generation

[0301] The server inputs a prompt based on the analysis results into a generative AI engine, which then generates a custom ad based on the user's interests and preferences. The input is the analysis results and the prompt, and the output is the generated ad copy. Specifically, based on the comment "I love your new lipstick," the server generates a message saying "Try this great shade!". Through this generation, the server prepares a personalized ad for the user.

[0302] Step 5: Ad serving

[0303] The server uses a marketing automation tool to deliver the generated custom ads to the user's device. The input is the generated ad copy and delivery schedule data, and the output is the ad displayed on the user's device. For example, if a user uses the app more at night, the server can set it to deliver ads at night. Through this process, the server delivers ads to the user at the optimal time.

[0304] Step 6: Collect and analyze feedback

[0305] The server collects feedback data (clicks, purchases, skips, etc.) from users after delivering ads. The input is user response data, and the output is behavioral data sent to the server. For example, when a user clicks on an ad, that information is sent to the server. Based on this feedback, the server evaluates and analyzes the effectiveness of the ad.

[0306] Step 7: Optimization

[0307] The server analyzes the collected feedback data, evaluates the effectiveness of the ads, and optimizes the next ad generation and distribution strategy. The input is the ad effectiveness evaluation data, and the output is an optimized ad generation and distribution strategy. For example, ads with high click-through rates are continued as they are, while ads with low effectiveness are improved. This allows the server to make adjustments to maximize advertising contribution.

[0308] As described above, this system effectively generates and delivers ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience and maximizing advertising effectiveness.

[0309] (Application example 2)

[0310] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0311] Conventional ad delivery methods only take into account the user's interests and preferences, and have the problem of not being able to analyze user emotions in real time to optimize ad content and delivery timing. As a result, ads that capture the user's attention are not as effective as they could be, resulting in low ad click rates and purchase rates.

[0312] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine that analyzes the collected data and identifies the user's interests, preferences, and emotions; means for automatically generating a customized advertisement based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisement to the user terminal at an appropriate time based on the results of the user's emotion analysis; and means for collecting feedback from the user again after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement. This enables advanced advertisement delivery that takes user emotions into consideration, making it possible to maximize the effectiveness of advertisements that attract the user's attention.

[0313] 1. "User" means any individual or legal entity that uses the System or Application.

[0314] 2. "Reviews" refers to ratings and comments provided by users to other users about products or services based on their own experiences.

[0315] 3. "Feedback Data" refers to information such as opinions, impressions, and behavioral data provided by users.

[0316] 4. "Real-time" refers to the temporal concept of data being processed almost simultaneously at the moment it is generated.

[0317] 5. "Generative AI engine" refers to a software module that uses artificial intelligence to perform analysis and generation.

[0318] 6. "Interests and Preferences" refers to a user's interest in or preference for a particular product or service.

[0319] 7. “Sentiment Analysis” refers to the process of assessing a user’s emotional state based on collected data.

[0320] 8. "Custom Ads" refers to ads that are specifically tailored to a user's individual needs, interests, and even emotions.

[0321] 9. "Automatic generation means" refers to a system in which advertisements are automatically generated by a machine based on pre-set rules or algorithms.

[0322] 10. "Right timing" refers to the optimal time for ad delivery based on a user's behavioral history and emotional state.

[0323] 11. "Device" means the device used by a User to receive and display advertisements.

[0324] 12. "Means for evaluating and optimizing effectiveness" refers to a system for evaluating the effectiveness of delivered advertisements and making adjustments to further improve their effectiveness.

[0325] Based on these definitions, the features of the present invention and the terms thereof can be clearly understood.

[0326] System Overview

[0327] This system uses word-of-mouth and feedback data collected from users in real time, and through sentiment analysis, automatically generates and delivers custom ads based on the user's interests, preferences, and emotions. It also evaluates and optimizes the effectiveness of ads based on the feedback.

[0328] Hardware and software used

[0329] Hardware: Servers, user devices (smartphones and tablets), cameras, sensors

[0330] Software: Natural language processing engines (e.g., TextBlob), generative AI engines (e.g., the Transformers library), sentiment analysis engines, marketing automation tools

[0331] Program Processing Overview

[0332] 1. Data Collection:

[0333] When users post reviews or feedback on their smartphones or tablets, the data is sent to the server in real time, including text data, image data, and audio data.

[0334] 2. Data Analysis:

[0335] The server analyzes the collected data using a natural language processing engine (TextBlob) and a sentiment analysis engine (Transformers library), extracting keywords from the text and classifying sentiment as positive, negative, or neutral.

[0336] 3. Ad generation:

[0337] Based on the analysis results, the generative AI engine automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, if a user posts positive feedback, the ad copy will be tailored to that emotion.

[0338] 4. Advertisement Delivery:

[0339] Custom ads are delivered to users' devices at optimal times via marketing automation tools, which are determined based on users' behavioral history and emotional data.

[0340] 5. Feedback collection and optimization:

[0341] After the ad is delivered, the user's response data (clicks, skips, etc.) is sent back to the server. The server analyzes this data and evaluates the effectiveness of the ad. Based on the evaluation results, the generation AI engine and sentiment analysis engine will reflect this in the next ad generation.

[0342] Specific examples

[0343] Example 1: Generating ads in response to positive reviews

[0344] When a user posts feedback such as "I love the new lipstick," the sentiment analysis engine determines this as a positive emotion. The generative AI engine generates advertising copy such as "Perfect for you! Try our new lipstick color!" and delivers it to the user's device at the appropriate time.

[0345] Prompt Sentence Examples

[0346] "User posted feedback: 'I love my new lipstick.' Analyze it."

[0347] Example 2: Generating ads in response to negative reviews

[0348] When a user posts feedback such as "This perfume was a little too strong," the sentiment analysis engine determines this as a negative sentiment. The generative AI engine generates advertising copy such as "Great deals! Popular products at special prices!" and delivers it to the user's device at the appropriate time.

[0349] In this way, a system is realized that delivers advanced advertisements based on real-time user emotional data, maximizing advertising effectiveness.

[0350] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0351] Step 1:

[0352] Users post reviews and feedback on their smartphones or tablets. This generates text data, image data, and audio data. The user's device sends this data to the server in real time. The input is the reviews and feedback data, and the output is the data sent to the server.

[0353] Step 2:

[0354] The server inputs the received word-of-mouth and feedback data into a natural language processing engine (e.g., TextBlob) and analyzes the text data. Through analysis, keywords within the text are extracted and the user's interests and preferences are determined. The input is the word-of-mouth and feedback text data, and the output is the extracted keywords and data on interests and preferences.

[0355] Step 3:

[0356] The server inputs the extracted keywords, interests, and preference data into a sentiment analysis engine (e.g., the Transformers library) to classify the user's sentiment into positive, negative, or neutral. The input is keywords and interest and preference data, and the output is the sentiment classification result.

[0357] Step 4:

[0358] The server inputs the sentiment classification results into a generative AI engine to automatically generate custom ads based on the user's interests, preferences, and emotions. The generative AI engine uses a deep learning model to generate ad copy. The input is the sentiment classification results, and the output is the generated custom ad.

[0359] Step 5:

[0360] The server delivers the generated custom ads to user devices at the appropriate time via a marketing automation tool. The delivery timing is determined based on the user's behavioral history and emotional data. The input is the generated custom ads and delivery timing data, and the output is the delivery of the ads to the user devices.

[0361] Step 6:

[0362] The user reacts to the delivered advertisement, for example, by clicking or skipping the advertisement. This behavioral data is sent from the terminal to the server. The input is the user's behavioral data regarding the advertisement, and the output is the behavioral data sent to the server.

[0363] Step 7:

[0364] The server analyzes user behavior data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generation AI engine and sentiment analysis engine reflect them in the generation of the next advertisement. This process makes it possible to optimize the content of the advertisement and its distribution strategy. The input is user behavior data and advertisement effectiveness evaluation data, and the output is an optimized advertisement generation algorithm.

[0365] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0366] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search<url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0367] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0368] [Second embodiment]

[0369] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0370] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0371] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0372] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0373] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0374] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0375] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0376] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0377] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0378] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0379] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0380] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0381] System Overview

[0382] The system has the ability to automatically generate and distribute personalized ads based on user reviews and feedback. Specifically, it analyzes collected data and uses a generative AI engine to generate custom ads. The ads are then distributed to user devices, and feedback is collected again to optimize advertising effectiveness.

[0383] Server Processing

[0384] Data collection

[0385] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[0386] Data analysis

[0387] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether a user's comment is positive, negative, or neutral. Based on this information, the server can identify the user's interests and preferences.

[0388] Ad Generation

[0389] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest users.

[0390] Ad serving

[0391] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[0392] Feedback collection and optimization

[0393] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0394] Terminal handling

[0395] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[0396] User Behavior

[0397] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided.

[0398] This system generates ads based on real-time user feedback, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' interest and maximizing advertising effectiveness.

[0399] The processing flow will be explained below.

[0400] Step 1:

[0401] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[0402] Step 2:

[0403] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[0404] Step 3:

[0405] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[0406] Step 4:

[0407] The server inputs the stored data into a natural language processing (NLP) engine to extract text and keywords, such as "lipstick" and "like."

[0408] Step 5:

[0409] The server performs sentiment analysis to determine whether a user's comments are positive, negative, or neutral, and uses this information to identify the user's interests and preferences.

[0410] Step 6:

[0411] The server then feeds the analysis results into a generative AI engine that automatically generates custom ads based on the user's interests and preferences. These ads include text and visuals such as "Try these amazing shades!"

[0412] Step 7:

[0413] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[0414] Step 8:

[0415] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[0416] Step 9:

[0417] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[0418] Step 10:

[0419] Users respond to the ads they see by clicking on them, skipping them, or making a purchase, and this behavioral data is collected by the device.

[0420] Step 11:

[0421] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[0422] Step 12:

[0423] The server analyzes the collected behavioral data to evaluate the effectiveness of advertising, for example, calculating click-through rates and conversion rates.

[0424] Step 13:

[0425] The server inputs the results of the effectiveness evaluation back into the AI ​​engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and ads with low response rates are improved.

[0426] Step 14:

[0427] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[0428] Example 1

[0429] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0430] In modern advertising delivery, it is a difficult challenge to efficiently generate and deliver personalized advertisements that match users' interests and preferences. To solve this problem, a system is needed that effectively utilizes user word-of-mouth and feedback to optimize advertisements in real time.

[0431] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0432] In this invention, the server includes means for collecting word-of-mouth or feedback data from user terminals in real time, means for analyzing the collected data using a natural language processing engine and identifying the user's interests and preferences, means for inputting prompt sentences into a generation AI engine based on the identified interests and preferences and automatically generating a customized advertisement, means for delivering the generated customized advertisement to the user terminals via a marketing automation tool, and means for collecting feedback data from users after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement.

[0433] This makes it possible to generate optimal advertisements based on users' interests and preferences in real time and deliver them efficiently.

[0434] A "user terminal" is a device operated by a user, and includes smartphones, tablets, personal computers, etc.

[0435] "Review or Feedback Data" means information posted by users through an application or website, and may be in the form of text, images, audio, or other information.

[0436] A "natural language processing engine" is a software tool that analyzes text data and performs keyword extraction and sentiment analysis, and examples include SpaCy and NLTK.

[0437] A "generative AI engine" is an artificial intelligence engine that generates custom ads based on user interests and preferences, and examples include OpenAI's GPT-4.

[0438] A "prompt sentence" is an instruction sentence input into the generative AI engine, and is specific input data for generating a custom ad.

[0439] "Custom ads" are ads automatically generated based on a user's interests and preferences, and come in the form of text, images, videos, and more.

[0440] A "marketing automation tool" is a software tool for automating advertising and marketing activities, such as HubSpot or Marketo.

[0441] "Feedback data" refers to information about a user's response to an advertisement (click, skip, purchase, etc.).

[0442] A "collection means" is a method or device for acquiring data from a user terminal.

[0443] "Means for analyzing" refers to a method or device for analyzing collected data and identifying user interests and preferences.

[0444] "Means for generating" refers to a method or device for inputting a prompt sentence into a generating AI engine based on the analysis results and generating a custom advertisement.

[0445] The "means for delivering" refers to a method or device for transmitting the generated custom advertisement to a user terminal.

[0446] The "optimization means" refers to a method or device for analyzing feedback data collected after advertisement distribution, and evaluating and improving the effectiveness of the advertisement.

[0447] This invention relates to a system that generates and distributes personalized advertisements based on word-of-mouth and feedback data collected from users. Specifically, it collects user behavior data in real time, analyzes it with a natural language processing (NLP) engine, and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback data is collected again to optimize the effectiveness of the advertisements.

[0448] Server Processing

[0449] Data collection

[0450] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user logs into a cosmetics app and posts a comment saying, "I love your new lipstick," that information is sent to the server.

[0451] Data analysis

[0452] The server analyzes the collected data using a natural language processing (NLP) engine (such as SpaCy or NLTK). This allows it to extract keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. Based on this information, it can identify the user's interests and preferences.

[0453] Ad Generation

[0454] Using the analysis results, the server inputs the data into a generative AI engine (e.g., OpenAI's GPT-4) to automatically generate custom ads tailored to the user's interests and preferences. For example, by inputting the prompt "Create an ad for a new lipstick color," the server generates ad copy such as "Try this amazing shade!"

[0455] Ad serving

[0456] The generated custom ads are delivered to the user's device via a marketing automation tool (e.g., HubSpot or Marketo). The server also considers the optimal delivery timing and frequency based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ads to be delivered at night.

[0457] Feedback collection and optimization

[0458] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click rates can be continued as they are, while ads with low responses can be changed.

[0459] Terminal handling

[0460] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[0461] User Behavior

[0462] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, and users respond to the ads. This response is fed back into the generation and distribution of the next ad, allowing the system to continue providing ads that are more relevant to the user.

[0463] This system generates advertisements based on real-time user feedback and provides a constantly optimized advertising experience, effectively delivering advertisements that capture users' interest and maximizing advertising effectiveness.

[0464] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0465] Step 1:

[0466] The user enters the feedback data.

[0467] Users submit reviews and feedback on applications and websites, and this data can include text, images, and audio.

[0468] Specific behavior: A user logs into a cosmetics app and posts a comment saying, "I love your new lipstick." The comment is sent to the central server through the application server.

[0469] Input: User comments and feedback.

[0470] Output: Review data collected on the server.

[0471] Step 2:

[0472] The server analyzes the collected data using a natural language processing (NLP) engine.

[0473] The server feeds the received reviews and feedback data into an NLP engine (e.g., SpaCy or NLTK), where keyword extraction and sentiment analysis are performed.

[0474] Specific operation: The server analyzes the comment "I like the new lipstick" and extracts keywords such as "lipstick" and "like." At the same time, it uses sentiment analysis to determine whether the comment is positive.

[0475] Input: Collected review data.

[0476] Output: Keyword and sentiment analysis results.

[0477] Step 3:

[0478] The server passes the analysis results to a generative AI engine to generate custom ads.

[0479] The server inputs the analysis results of the NLP engine into a generative AI engine (e.g., OpenAI's GPT-4) and requests it to generate a custom ad.

[0480] Specific operation: The server sends the prompt "Please create an advertisement for a new lipstick color" to the AI ​​engine. The AI ​​engine generates the advertisement copy "Try this amazing shade!"

[0481] Input: Keywords and sentiment analysis results.

[0482] Output: The generated custom ad copy.

[0483] Step 4:

[0484] The server delivers the generated custom advertisement to the user terminal via a marketing automation tool.

[0485] The generated advertisement is passed to an advertisement distribution tool (e.g., HubSpot or Marketo) and sent to the user's device at the optimal time.

[0486] Specific operation: The server sets up nighttime ad distribution based on the user's behavioral history. The ad distribution tool sends the ad to the user's smartphone.

[0487] Input: Your generated custom ad copy.

[0488] Output: Advertisement delivered to user device.

[0489] Step 5:

[0490] The server collects feedback data from users after delivering the advertisements, and evaluates and optimizes the effectiveness of the advertisements.

[0491] The server collects and analyzes data such as ad click rates, purchase rates, and skip rates, and uses this information to generate the next ad.

[0492] Specific operation: When a user clicks on an ad, the data is sent to the server. The server analyzes the click data and evaluates the effectiveness of the ad. If the click rate is high, the same ad format will continue to be displayed, but if the response is low, the ad content will be changed.

[0493] Input: User feedback data.

[0494] Output: Evaluation of the effectiveness of the ad and the results reflected in the next ad generation.

[0495] The above is the specific processing flow of this system, which makes it possible to generate and distribute advertisements optimized for users in real time.

[0496] (Application example 1)

[0497] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0498] Conventional ad delivery systems have difficulty accurately grasping users' interests and preferences, making it difficult to deliver ads effectively. In particular, there is a lack of a way to deliver ads optimized for individual users in a timely manner, which reduces the effectiveness of advertising.

[0499] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0500] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine for analyzing the collected data and identifying user interests and preferences; means for automatically generating customized advertisements based on the identified interests and preferences and creating advertisement copy using prompt text using a generation AI model; means for delivering the generated customized advertisements to user devices at optimal times based on user behavior data; and means for collecting user feedback again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to generate personalized advertisements based on user preferences in real time and deliver them at optimal times.

[0501] "User" refers to the general consumer who uses a product or service, and in particular the person who provides word-of-mouth or feedback.

[0502] "Review or Feedback Data" refers to any user feedback or evaluation information, such as text, images, or audio, posted by users on an application or website.

[0503] "Means of collection" refers to the mechanism for obtaining word-of-mouth or feedback data from user devices in real time and sending it to a server.

[0504] "Analysis means" refers to technologies used to analyze collected reviews or feedback data and identify user interests and preferences.

[0505] A "generative AI engine" refers to an artificial intelligence engine that analyzes user preferences based on collected data and generates appropriate advertisements.

[0506] A "prompt" is an input to a generative AI model, and refers to an instruction to request the generation of a specific ad copy or sentence.

[0507] "Generative AI model" refers to an artificial intelligence model that automatically generates advertising copy and related information based on a given prompt.

[0508] "Ad generation method" refers to a mechanism that automatically generates custom advertisements based on a user's interests and preferences.

[0509] "Timely delivery" refers to a system that delivers advertisements at the optimal time based on the user's behavioral history and usage patterns.

[0510] "Means of collecting feedback" refers to a system that recollects user reactions and evaluation data after advertisement delivery and sends it to a server.

[0511] "Means for evaluating and optimizing advertising effectiveness" refers to a mechanism for analyzing the effectiveness of advertising using collected feedback data and reflecting the results in the generation and distribution of the next advertisement.

[0512] "User terminal" refers to a device that can connect to the Internet and is used by a user, such as a smartphone, tablet, or PC.

[0513] System Overview

[0514] This invention is a system that automatically generates and distributes personalized advertisements based on user behavioral data and feedback data. The system analyzes collected data and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback is collected again to optimize the effectiveness of the advertisements.

[0515] Server Processing

[0516] Data collection

[0517] The server receives real-time user reviews and feedback data from users' devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment on an online shopping site saying, "These sneakers are very comfortable," that information is sent to the server.

[0518] Data analysis

[0519] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "sneakers" and "comfortable" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. This information is used to identify the user's interests and preferences.

[0520] Ad Generation

[0521] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. Specific ad copy is generated by inputting a prompt into the generative AI model. For example, in the previous example, the prompt would be, "Generate ad copy for a new product suitable for a user looking for comfortable sneakers." Using this prompt, the generative AI model would generate ad copy such as, "Our newly released sneakers will provide you with the ultimate in comfort. Click now to see the details!"

[0522] Ad serving

[0523] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[0524] Feedback collection and optimization

[0525] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0526] User terminal processing

[0527] The user device receives the advertisement and feedback request sent from the server and displays it to the user in an appropriate interface. When the user responds to the advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on an advertisement for sneakers on their smartphone, the information is immediately sent to the server and used for later analysis.

[0528] Hardware and software used

[0529] The servers are deployed on cloud platforms (e.g., AWS, Google Cloud, Azure). Natural language processing engines (e.g., Google NLP, IBM Watson) are used for analysis, generative AI engines (e.g., OpenAI GPT-4) are used for ad generation, and marketing automation tools (e.g., Mailchimp, HubSpot) are used for ad delivery.

[0530] With the above configuration, it is possible to generate personalized advertisements based on user preferences in real time and deliver them at the optimal timing.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] The server collects word-of-mouth and feedback data from user devices in real time. Specifically, it receives text, images, and audio data posted by users on applications and websites and stores this data on a cloud server. The input is word-of-mouth and feedback data from users, and the output is the data stored on the cloud server.

[0534] Step 2:

[0535] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it extracts keywords from the text data and performs sentiment analysis to determine whether the comments are positive, negative, or neutral. The input is the reviews and feedback data stored on the cloud server, and the output is the extracted keywords and sentiment information.

[0536] Step 3:

[0537] The server inputs a prompt text based on the analysis results into the generative AI engine, which then generates a custom ad tailored to the user's interests and preferences. Specifically, a prompt text such as "Please generate advertising copy for a new product suitable for a user looking for comfortable sneakers" is generated and input into the generative AI model. The input is a prompt text based on the analysis results, and the output is the advertising copy created by the generative AI model.

[0538] Step 4:

[0539] The server delivers the generated custom ads to the user's device via a marketing automation tool. Specifically, it configures the settings to deliver ads at the optimal time based on the user's behavioral history. For example, if a user frequently uses the app at night, it delivers ads at night. The input is the generated ad copy and the user's behavioral history, and the output is the ad delivered to the user's device.

[0540] Step 5:

[0541] When a user responds to an ad (by clicking, skipping, purchasing, etc.), the device sends that data to the server. Specifically, when a user clicks on an ad, that information is immediately sent to the server and stored on the cloud server. The input is the user's response data to the ad, and the output is the response data stored on the cloud server.

[0542] Step 6:

[0543] The server analyzes the collected feedback data and evaluates the effectiveness of the ads. Specifically, it analyzes which ads were effective based on behavioral data such as click rates, skip rates, and purchase rates. The input is the feedback data stored on the cloud server, and the output is the evaluation results of the advertising effectiveness.

[0544] Step 7:

[0545] The server then performs optimization based on the evaluation results to reflect them in the next ad generation. Specifically, ads with high click-through rates are continued without any improvements, while ads with low responses are modified in content or targeting. The input is the evaluation results of the advertising effectiveness, and the output is optimization data for the next ad generation.

[0546] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0547] System Overview

[0548] This system has the ability to personalize, automatically generate, and deliver advertisements based on user reviews and feedback. It also combines an emotion engine that analyzes user emotions to achieve even more accurate ad generation and delivery. Specifically, it analyzes collected data and generates custom ads using the emotion engine and generative AI engine. The ads are then delivered to user devices, and feedback is collected again to optimize advertising effectiveness.

[0549] Server Processing

[0550] Data collection

[0551] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[0552] Data analysis

[0553] The server inputs the collected data into a natural language processing (NLP) and emotion engine to extract text and analyze user sentiment. This allows it to extract keywords such as "lipstick" and "like" and determine whether the comment is positive, negative, or neutral. This information is then used to identify the user's interests and preferences.

[0554] Ad Generation

[0555] Using the results of the analysis and sentiment analysis, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest the user.

[0556] Ad serving

[0557] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery, delivering them based on the user's emotions and behavioral history. For example, if a user frequently uses the app at night and has positive emotions at that time, the server will set the ads to be delivered at night.

[0558] Feedback collection and optimization

[0559] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the generative AI and emotion engine optimize the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0560] Terminal handling

[0561] The user device receives advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicking, skipping, etc.), the data is sent to the server. Furthermore, the user's facial expressions and behavior are detected using cameras and sensors, and sent to the emotion engine for real-time emotion analysis. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server and used for subsequent analysis.

[0562] User Behavior

[0563] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided. In addition, the user's facial expressions and behavior when viewing an ad are also sent to the emotion engine, and this is used as data for ad optimization.

[0564] This system generates ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' attention and maximizing advertising effectiveness.

[0565] The processing flow will be explained below.

[0566] Step 1:

[0567] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[0568] Step 2:

[0569] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[0570] Step 3:

[0571] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[0572] Step 4:

[0573] The server inputs the stored data into a natural language processing (NLP) engine and sentiment engine to extract text, analyze keywords, and analyze sentiment. For example, it can extract keywords such as "lipstick" and "like" and determine whether a comment is positive.

[0574] Step 5:

[0575] The server uses the analysis results of the emotion engine to determine the user's emotional status, for example, determining that the user has a positive emotion.

[0576] Step 6:

[0577] The server inputs the analysis results and emotional status into a generation AI engine, which automatically generates custom ads tailored to the user's emotions as well as their interests and preferences. Specifically, it generates ad copy such as "Try these amazing shades!"

[0578] Step 7:

[0579] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[0580] Step 8:

[0581] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[0582] Step 9:

[0583] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[0584] Step 10:

[0585] Users respond to the ads displayed to them by clicking on them, making a purchase, or skipping them, and this behavioral data is collected by the device.

[0586] Step 11:

[0587] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[0588] Step 12:

[0589] The server analyzes the collected behavioral data and evaluates the effectiveness of the advertisement, specifically calculating click-through rates and conversion rates.

[0590] Step 13:

[0591] The server inputs the results of the effectiveness evaluation into the AI ​​engine and emotion engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and the content and targeting of ads with low response rates are changed.

[0592] Step 14:

[0593] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[0594] Step 15:

[0595] The device collects measurable emotional data (such as facial expressions and behavior) from the user and sends it to a server. For example, a camera or sensor can be used to detect the user's facial expressions, and the data is used for analysis.

[0596] Step 16:

[0597] The server analyzes the collected emotional data and uses it to optimize advertising. By including emotional data from users while they are viewing ads in the analysis of advertising effectiveness, more accurate optimization becomes possible.

[0598] Example 2

[0599] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0600] Conventional ad delivery systems have had difficulty in generating and delivering ads that fully incorporate real-time user reviews and feedback. Furthermore, they have been unable to adequately optimize ads based on user sentiment, making it difficult to maximize advertising effectiveness. Furthermore, there are issues with the significant time and effort required to utilize feedback after ad delivery to improve ad content and delivery strategies.

[0601] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0602] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; means for analyzing the collected data using a natural language processing and sentiment analysis engine to identify user interests and preferences; a generation AI engine for automatically generating customized advertisements based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisements to user devices and optimizing the timing and frequency of delivery; and means for collecting feedback data from users again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to effectively generate and deliver advertisements that are always optimized based on users' real-time feedback and sentiment data, thereby maximizing advertising effectiveness.

[0603] "User" means an end user who uses a particular application or website to post reviews and feedback.

[0604] "Real-time" means that processing occurs immediately the moment the user sends the data.

[0605] "Review or Feedback Data" means data such as text, images, or audio that a user provides through an application or website.

[0606] "Natural language processing" is a technology for converting text data into a format that is easy for machines to understand and analyzing its meaning.

[0607] An "emotion analysis engine" is a system that analyzes text data and information obtained from sensors to detect user emotions.

[0608] "Interests and Preferences" refers to the interest or preference a user has in a particular product, service, or topic.

[0609] A "generative AI engine" is an engine that uses artificial intelligence technologies such as deep learning models to analyze data and automatically generate custom advertisements.

[0610] "Custom Ads" are ads that are personalized based on a particular user's interests, preferences, and emotions.

[0611] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0612] "Optimizing delivery timing and frequency" refers to the process of adjusting the delivery of advertisements at the most effective time and frequency based on user behavioral history and emotional data.

[0613] "Feedback data" refers to data about the actions users take after viewing an ad (clicks, purchases, skips, etc.).

[0614] "Advertising effectiveness evaluation and optimization" refers to the process of analyzing collected feedback data, measuring advertising performance, and improving next ad generation and distribution strategies.

[0615] This invention is a system that automatically generates and distributes personalized advertisements based on real-time user reviews and feedback. Furthermore, by combining this with an emotion engine that analyzes user emotions, it is possible to generate and distribute advertisements with even greater accuracy.

[0616] The system uses the following hardware and software:

[0617] User device: A device such as a smartphone, tablet, or computer.

[0618] Server: A central computer that collects data, analyzes, generates and delivers advertisements.

[0619] Natural Language Processing (NLP) engine: Software that performs text analysis on user data.

[0620] Sentiment analysis engine: Software that analyzes emotions from user data.

[0621] Generative AI engine: Software that uses deep learning models to generate custom ads.

[0622] Marketing automation tool: Software that delivers generated advertisements to user devices.

[0623] The operation of the system will be specifically described below.

[0624] Data collection

[0625] When a user posts a review or feedback on a particular application or website, for example, when a user posts a comment in a cosmetics app saying, "I love your new lipstick," that data is sent from the user's device to a server. The data may include text, images, and audio.

[0626] Data analysis

[0627] The server inputs the collected data into a natural language processing (NLP) engine. The NLP engine extracts keywords from the text data. For example, the keywords "lipstick" and "like" are extracted. Then, a sentiment analysis engine analyzes the user's comments and classifies them as positive, negative, or neutral. In this case, a positive sentiment is detected from the expression "like."

[0628] Ad Generation

[0629] The server inputs the analysis results into a generation AI engine to generate custom ads based on the user's interests and preferences. For example, to generate an ad for a new lipstick color, the message "Try these amazing shades!" is generated. This ad copy includes specific words and images that are likely to interest the user.

[0630] Example prompt sentence:

[0631] "Generate ad copy for a new cosmetic product. A user review reads, 'I love your new lipstick.'"

[0632] Ad serving

[0633] The custom ads created by the generative AI engine are delivered to users' devices via marketing automation tools. The server calculates the optimal delivery timing and frequency based on the user's behavioral history and emotional data. For example, if a user uses the app more at night and shows positive emotions, the server will set the ads to be delivered at night.

[0634] Feedback collection and optimization

[0635] After an ad is delivered, the user's post-ad behavior (click, purchase, skip, etc.) is immediately collected as data. When a user clicks on a lipstick ad on their smartphone, that information is sent to the server. The server analyzes this feedback data and evaluates the effectiveness of the ad. Based on the evaluation results, the next ad generation and delivery strategy are optimized. For example, ads with high click rates can be continued as is, while ads with low responses can be improved.

[0636] This allows us to effectively generate and deliver ads that are always optimized based on real-time user feedback and sentiment data, maximizing advertising effectiveness.

[0637] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0638] Step 1: Data collection

[0639] The server collects word-of-mouth and feedback data from user devices in real time. For example, a user posts a comment in a cosmetics app saying, "I like the new lipstick." The input is the text, image, and voice data posted by the user, and the output is the data received by the server. In this way, the server obtains the feedback data entered by the user.

[0640] Step 2: Natural Language Processing (NLP)

[0641] The server inputs the collected data into a natural language processing (NLP) engine. Specifically, it analyzes the text data of user engagement and extracts keywords. The input is the collected feedback data, and the output is the extracted keywords. For example, "lipstick" and "like" are extracted. Through this analysis, the server understands the user's interests and preferences.

[0642] Step 3: Sentiment Analysis

[0643] The server inputs the keywords obtained from the NLP engine into the sentiment analysis engine. The input is the keywords from the NLP engine, and the output is the emotional assessment result (positive, negative, neutral). For example, the keyword "I liked it" is analyzed to determine positive emotions. Based on this information, the server understands the user's emotions.

[0644] Step 4: Ad generation

[0645] The server inputs a prompt based on the analysis results into a generative AI engine, which then generates a custom ad based on the user's interests and preferences. The input is the analysis results and the prompt, and the output is the generated ad copy. Specifically, based on the comment "I love your new lipstick," the server generates a message saying "Try this great shade!". Through this generation, the server prepares a personalized ad for the user.

[0646] Step 5: Ad serving

[0647] The server uses a marketing automation tool to deliver the generated custom ads to the user's device. The input is the generated ad copy and delivery schedule data, and the output is the ad displayed on the user's device. For example, if a user uses the app more at night, the server can set it to deliver ads at night. Through this process, the server delivers ads to the user at the optimal time.

[0648] Step 6: Collect and analyze feedback

[0649] The server collects feedback data (clicks, purchases, skips, etc.) from users after delivering ads. The input is user response data, and the output is behavioral data sent to the server. For example, when a user clicks on an ad, that information is sent to the server. Based on this feedback, the server evaluates and analyzes the effectiveness of the ad.

[0650] Step 7: Optimization

[0651] The server analyzes the collected feedback data, evaluates the effectiveness of the ads, and optimizes the next ad generation and distribution strategy. The input is the ad effectiveness evaluation data, and the output is an optimized ad generation and distribution strategy. For example, ads with high click-through rates are continued as they are, while ads with low effectiveness are improved. This allows the server to make adjustments to maximize advertising contribution.

[0652] As described above, this system effectively generates and delivers ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience and maximizing advertising effectiveness.

[0653] (Application example 2)

[0654] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0655] Conventional ad delivery methods only take into account the user's interests and preferences, and have the problem of not being able to analyze user emotions in real time to optimize ad content and delivery timing. As a result, ads that capture the user's attention are not as effective as they could be, resulting in low ad click rates and purchase rates.

[0656] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine that analyzes the collected data and identifies the user's interests, preferences, and emotions; means for automatically generating a customized advertisement based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisement to the user terminal at an appropriate time based on the results of the user's emotion analysis; and means for collecting feedback from the user again after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement. This enables advanced advertisement delivery that takes user emotions into consideration, making it possible to maximize the effectiveness of advertisements that attract the user's attention.

[0657] 1. "User" means any individual or legal entity that uses the System or Application.

[0658] 2. "Reviews" refers to ratings and comments provided by users to other users about products or services based on their own experiences.

[0659] 3. "Feedback Data" refers to information such as opinions, impressions, and behavioral data provided by users.

[0660] 4. "Real-time" refers to the temporal concept of data being processed almost simultaneously at the moment it is generated.

[0661] 5. "Generative AI engine" refers to a software module that uses artificial intelligence to perform analysis and generation.

[0662] 6. "Interests and Preferences" refers to a user's interest in or preference for a particular product or service.

[0663] 7. “Sentiment Analysis” refers to the process of assessing a user’s emotional state based on collected data.

[0664] 8. "Custom Ads" refers to ads that are specifically tailored to a user's individual needs, interests, and even emotions.

[0665] 9. "Automatic generation means" refers to a system in which advertisements are automatically generated by a machine based on pre-set rules or algorithms.

[0666] 10. "Right timing" refers to the optimal time for ad delivery based on a user's behavioral history and emotional state.

[0667] 11. "Device" means the device used by a User to receive and display advertisements.

[0668] 12. "Means for evaluating and optimizing effectiveness" refers to a system for evaluating the effectiveness of delivered advertisements and making adjustments to further improve their effectiveness.

[0669] Based on these definitions, the features of the present invention and the terms thereof can be clearly understood.

[0670] System Overview

[0671] This system uses word-of-mouth and feedback data collected from users in real time, and through sentiment analysis, automatically generates and delivers custom ads based on the user's interests, preferences, and emotions. It also evaluates and optimizes the effectiveness of ads based on the feedback.

[0672] Hardware and software used

[0673] Hardware: Servers, user devices (smartphones and tablets), cameras, sensors

[0674] Software: Natural language processing engines (e.g., TextBlob), generative AI engines (e.g., the Transformers library), sentiment analysis engines, marketing automation tools

[0675] Program Processing Overview

[0676] 1. Data Collection:

[0677] When users post reviews or feedback on their smartphones or tablets, the data is sent to the server in real time, including text data, image data, and audio data.

[0678] 2. Data Analysis:

[0679] The server analyzes the collected data using a natural language processing engine (TextBlob) and a sentiment analysis engine (Transformers library), extracting keywords from the text and classifying sentiment as positive, negative, or neutral.

[0680] 3. Ad generation:

[0681] Based on the analysis results, the generative AI engine automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, if a user posts positive feedback, the ad copy will be tailored to that emotion.

[0682] 4. Advertisement Delivery:

[0683] Custom ads are delivered to users' devices at optimal times via marketing automation tools, which are determined based on users' behavioral history and emotional data.

[0684] 5. Feedback collection and optimization:

[0685] After the ad is delivered, the user's response data (clicks, skips, etc.) is sent back to the server. The server analyzes this data and evaluates the effectiveness of the ad. Based on the evaluation results, the generation AI engine and sentiment analysis engine will reflect this in the next ad generation.

[0686] Specific examples

[0687] Example 1: Generating ads in response to positive reviews

[0688] When a user posts feedback such as "I love the new lipstick," the sentiment analysis engine determines this as a positive emotion. The generative AI engine generates advertising copy such as "Perfect for you! Try our new lipstick color!" and delivers it to the user's device at the appropriate time.

[0689] Prompt Sentence Examples

[0690] "User posted feedback: 'I love my new lipstick.' Analyze it."

[0691] Example 2: Generating ads in response to negative reviews

[0692] When a user posts feedback such as "This perfume was a little too strong," the sentiment analysis engine determines this as a negative sentiment. The generative AI engine generates advertising copy such as "Great deals! Popular products at special prices!" and delivers it to the user's device at the appropriate time.

[0693] In this way, a system is realized that delivers advanced advertisements based on real-time user emotional data, maximizing advertising effectiveness.

[0694] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0695] Step 1:

[0696] Users post reviews and feedback on their smartphones or tablets. This generates text data, image data, and audio data. The user's device sends this data to the server in real time. The input is the reviews and feedback data, and the output is the data sent to the server.

[0697] Step 2:

[0698] The server inputs the received word-of-mouth and feedback data into a natural language processing engine (e.g., TextBlob) and analyzes the text data. Through analysis, keywords within the text are extracted and the user's interests and preferences are determined. The input is the word-of-mouth and feedback text data, and the output is the extracted keywords and data on interests and preferences.

[0699] Step 3:

[0700] The server inputs the extracted keywords, interests, and preference data into a sentiment analysis engine (e.g., the Transformers library) to classify the user's sentiment into positive, negative, or neutral. The input is keywords and interest and preference data, and the output is the sentiment classification result.

[0701] Step 4:

[0702] The server inputs the sentiment classification results into a generative AI engine to automatically generate custom ads based on the user's interests, preferences, and emotions. The generative AI engine uses a deep learning model to generate ad copy. The input is the sentiment classification results, and the output is the generated custom ad.

[0703] Step 5:

[0704] The server delivers the generated custom ads to user devices at the appropriate time via a marketing automation tool. The delivery timing is determined based on the user's behavioral history and emotional data. The input is the generated custom ads and delivery timing data, and the output is the delivery of the ads to the user devices.

[0705] Step 6:

[0706] The user reacts to the delivered advertisement, for example, by clicking or skipping the advertisement. This behavioral data is sent from the terminal to the server. The input is the user's behavioral data regarding the advertisement, and the output is the behavioral data sent to the server.

[0707] Step 7:

[0708] The server analyzes user behavior data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generation AI engine and sentiment analysis engine reflect them in the generation of the next advertisement. This process makes it possible to optimize the content of the advertisement and its distribution strategy. The input is user behavior data and advertisement effectiveness evaluation data, and the output is an optimized advertisement generation algorithm.

[0709] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0710] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0711] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0712] [Third embodiment]

[0713] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0714] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0715] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0716] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0717] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0718] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0719] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0720] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0721] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0722] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0723] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0724] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0725] System Overview

[0726] The system has the ability to automatically generate and distribute personalized ads based on user reviews and feedback. Specifically, it analyzes collected data and uses a generative AI engine to generate custom ads. The ads are then distributed to user devices, and feedback is collected again to optimize advertising effectiveness.

[0727] Server Processing

[0728] Data collection

[0729] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[0730] Data analysis

[0731] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether a user's comment is positive, negative, or neutral. Based on this information, the server can identify the user's interests and preferences.

[0732] Ad Generation

[0733] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest users.

[0734] Ad serving

[0735] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[0736] Feedback collection and optimization

[0737] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0738] Terminal handling

[0739] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[0740] User Behavior

[0741] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided.

[0742] This system generates ads based on real-time user feedback, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' interest and maximizing advertising effectiveness.

[0743] The processing flow will be explained below.

[0744] Step 1:

[0745] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[0746] Step 2:

[0747] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[0748] Step 3:

[0749] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[0750] Step 4:

[0751] The server inputs the stored data into a natural language processing (NLP) engine to extract text and keywords, such as "lipstick" and "like."

[0752] Step 5:

[0753] The server performs sentiment analysis to determine whether a user's comments are positive, negative, or neutral, and uses this information to identify the user's interests and preferences.

[0754] Step 6:

[0755] The server then feeds the analysis results into a generative AI engine that automatically generates custom ads based on the user's interests and preferences. These ads include text and visuals such as "Try these amazing shades!"

[0756] Step 7:

[0757] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[0758] Step 8:

[0759] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[0760] Step 9:

[0761] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[0762] Step 10:

[0763] Users respond to the ads they see by clicking on them, skipping them, or making a purchase, and this behavioral data is collected by the device.

[0764] Step 11:

[0765] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[0766] Step 12:

[0767] The server analyzes the collected behavioral data to evaluate the effectiveness of advertising, for example, calculating click-through rates and conversion rates.

[0768] Step 13:

[0769] The server inputs the results of the effectiveness evaluation back into the AI ​​engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and ads with low response rates are improved.

[0770] Step 14:

[0771] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[0772] Example 1

[0773] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0774] In modern advertising delivery, it is a difficult challenge to efficiently generate and deliver personalized advertisements that match users' interests and preferences. To solve this problem, a system is needed that effectively utilizes user word-of-mouth and feedback to optimize advertisements in real time.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0776] In this invention, the server includes means for collecting word-of-mouth or feedback data from user terminals in real time, means for analyzing the collected data using a natural language processing engine and identifying the user's interests and preferences, means for inputting prompt sentences into a generation AI engine based on the identified interests and preferences and automatically generating a customized advertisement, means for delivering the generated customized advertisement to the user terminals via a marketing automation tool, and means for collecting feedback data from users after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement.

[0777] This makes it possible to generate optimal advertisements based on users' interests and preferences in real time and deliver them efficiently.

[0778] A "user terminal" is a device operated by a user, and includes smartphones, tablets, personal computers, etc.

[0779] "Review or Feedback Data" means information posted by users through an application or website, and may be in the form of text, images, audio, or other information.

[0780] A "natural language processing engine" is a software tool that analyzes text data and performs keyword extraction and sentiment analysis, and examples include SpaCy and NLTK.

[0781] A "generative AI engine" is an artificial intelligence engine that generates custom ads based on user interests and preferences, and examples include OpenAI's GPT-4.

[0782] A "prompt sentence" is an instruction sentence input into the generative AI engine, and is specific input data for generating a custom ad.

[0783] "Custom ads" are ads automatically generated based on a user's interests and preferences, and come in the form of text, images, videos, and more.

[0784] A "marketing automation tool" is a software tool for automating advertising and marketing activities, such as HubSpot or Marketo.

[0785] "Feedback data" refers to information about a user's response to an advertisement (click, skip, purchase, etc.).

[0786] A "collection means" is a method or device for acquiring data from a user terminal.

[0787] "Means for analyzing" refers to a method or device for analyzing collected data and identifying user interests and preferences.

[0788] "Means for generating" refers to a method or device for inputting a prompt sentence into a generating AI engine based on the analysis results and generating a custom advertisement.

[0789] The "means for delivering" refers to a method or device for transmitting the generated custom advertisement to a user terminal.

[0790] The "optimization means" refers to a method or device for analyzing feedback data collected after advertisement distribution, and evaluating and improving the effectiveness of the advertisement.

[0791] This invention relates to a system that generates and distributes personalized advertisements based on word-of-mouth and feedback data collected from users. Specifically, it collects user behavior data in real time, analyzes it with a natural language processing (NLP) engine, and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback data is collected again to optimize the effectiveness of the advertisements.

[0792] Server Processing

[0793] Data collection

[0794] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user logs into a cosmetics app and posts a comment saying, "I love your new lipstick," that information is sent to the server.

[0795] Data analysis

[0796] The server analyzes the collected data using a natural language processing (NLP) engine (such as SpaCy or NLTK). This allows it to extract keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. Based on this information, it can identify the user's interests and preferences.

[0797] Ad Generation

[0798] Using the analysis results, the server inputs the data into a generative AI engine (e.g., OpenAI's GPT-4) to automatically generate custom ads tailored to the user's interests and preferences. For example, by inputting the prompt "Create an ad for a new lipstick color," the server generates ad copy such as "Try this amazing shade!"

[0799] Ad serving

[0800] The generated custom ads are delivered to the user's device via a marketing automation tool (e.g., HubSpot or Marketo). The server also considers the optimal delivery timing and frequency based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ads to be delivered at night.

[0801] Feedback collection and optimization

[0802] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click rates can be continued as they are, while ads with low responses can be changed.

[0803] Terminal handling

[0804] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[0805] User Behavior

[0806] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, and users respond to the ads. This response is fed back into the generation and distribution of the next ad, allowing the system to continue providing ads that are more relevant to the user.

[0807] This system generates advertisements based on real-time user feedback and provides a constantly optimized advertising experience, effectively delivering advertisements that capture users' interest and maximizing advertising effectiveness.

[0808] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0809] Step 1:

[0810] The user enters the feedback data.

[0811] Users submit reviews and feedback on applications and websites, and this data can include text, images, and audio.

[0812] Specific behavior: A user logs into a cosmetics app and posts a comment saying, "I love your new lipstick." The comment is sent to the central server through the application server.

[0813] Input: User comments and feedback.

[0814] Output: Review data collected on the server.

[0815] Step 2:

[0816] The server analyzes the collected data using a natural language processing (NLP) engine.

[0817] The server feeds the received reviews and feedback data into an NLP engine (e.g., SpaCy or NLTK), where keyword extraction and sentiment analysis are performed.

[0818] Specific operation: The server analyzes the comment "I like the new lipstick" and extracts keywords such as "lipstick" and "like." At the same time, it uses sentiment analysis to determine whether the comment is positive.

[0819] Input: Collected review data.

[0820] Output: Keyword and sentiment analysis results.

[0821] Step 3:

[0822] The server passes the analysis results to a generative AI engine to generate custom ads.

[0823] The server inputs the analysis results of the NLP engine into a generative AI engine (e.g., OpenAI's GPT-4) and requests it to generate a custom ad.

[0824] Specific operation: The server sends the prompt "Please create an advertisement for a new lipstick color" to the AI ​​engine. The AI ​​engine generates the advertisement copy "Try this amazing shade!"

[0825] Input: Keywords and sentiment analysis results.

[0826] Output: The generated custom ad copy.

[0827] Step 4:

[0828] The server delivers the generated custom advertisement to the user terminal via a marketing automation tool.

[0829] The generated advertisement is passed to an advertisement distribution tool (e.g., HubSpot or Marketo) and sent to the user's device at the optimal time.

[0830] Specific operation: The server sets up nighttime ad distribution based on the user's behavioral history. The ad distribution tool sends the ad to the user's smartphone.

[0831] Input: Your generated custom ad copy.

[0832] Output: Advertisement delivered to user device.

[0833] Step 5:

[0834] The server collects feedback data from users after delivering the advertisements, and evaluates and optimizes the effectiveness of the advertisements.

[0835] The server collects and analyzes data such as ad click rates, purchase rates, and skip rates, and uses this information to generate the next ad.

[0836] Specific operation: When a user clicks on an ad, the data is sent to the server. The server analyzes the click data and evaluates the effectiveness of the ad. If the click rate is high, the same ad format will continue to be displayed, but if the response is low, the ad content will be changed.

[0837] Input: User feedback data.

[0838] Output: Evaluation of the effectiveness of the ad and the results reflected in the next ad generation.

[0839] The above is the specific processing flow of this system, which makes it possible to generate and distribute advertisements optimized for users in real time.

[0840] (Application example 1)

[0841] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0842] Conventional ad delivery systems have difficulty accurately grasping users' interests and preferences, making it difficult to deliver ads effectively. In particular, there is a lack of a way to deliver ads optimized for individual users in a timely manner, which reduces the effectiveness of advertising.

[0843] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0844] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine for analyzing the collected data and identifying user interests and preferences; means for automatically generating customized advertisements based on the identified interests and preferences and creating advertisement copy using prompt text using a generation AI model; means for delivering the generated customized advertisements to user devices at optimal times based on user behavior data; and means for collecting user feedback again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to generate personalized advertisements based on user preferences in real time and deliver them at optimal times.

[0845] "User" refers to the general consumer who uses a product or service, and in particular the person who provides word-of-mouth or feedback.

[0846] "Review or Feedback Data" refers to any user feedback or evaluation information, such as text, images, or audio, posted by users on an application or website.

[0847] "Means of collection" refers to the mechanism for obtaining word-of-mouth or feedback data from user devices in real time and sending it to a server.

[0848] "Analysis means" refers to technologies used to analyze collected reviews or feedback data and identify user interests and preferences.

[0849] A "generative AI engine" refers to an artificial intelligence engine that analyzes user preferences based on collected data and generates appropriate advertisements.

[0850] A "prompt" is an input to a generative AI model, and refers to an instruction to request the generation of a specific ad copy or sentence.

[0851] "Generative AI model" refers to an artificial intelligence model that automatically generates advertising copy and related information based on a given prompt.

[0852] "Ad generation method" refers to a mechanism that automatically generates custom advertisements based on a user's interests and preferences.

[0853] "Timely delivery" refers to a system that delivers advertisements at the optimal time based on the user's behavioral history and usage patterns.

[0854] "Means of collecting feedback" refers to a system that recollects user reactions and evaluation data after advertisement delivery and sends it to a server.

[0855] "Means for evaluating and optimizing advertising effectiveness" refers to a mechanism for analyzing the effectiveness of advertising using collected feedback data and reflecting the results in the generation and distribution of the next advertisement.

[0856] "User terminal" refers to a device that can connect to the Internet and is used by a user, such as a smartphone, tablet, or PC.

[0857] System Overview

[0858] This invention is a system that automatically generates and distributes personalized advertisements based on user behavioral data and feedback data. The system analyzes collected data and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback is collected again to optimize the effectiveness of the advertisements.

[0859] Server Processing

[0860] Data collection

[0861] The server receives real-time user reviews and feedback data from users' devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment on an online shopping site saying, "These sneakers are very comfortable," that information is sent to the server.

[0862] Data analysis

[0863] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "sneakers" and "comfortable" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. This information is used to identify the user's interests and preferences.

[0864] Ad Generation

[0865] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. Specific ad copy is generated by inputting a prompt into the generative AI model. For example, in the previous example, the prompt would be, "Generate ad copy for a new product suitable for a user looking for comfortable sneakers." Using this prompt, the generative AI model would generate ad copy such as, "Our newly released sneakers will provide you with the ultimate in comfort. Click now to see the details!"

[0866] Ad serving

[0867] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[0868] Feedback collection and optimization

[0869] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0870] User terminal processing

[0871] The user device receives the advertisement and feedback request sent from the server and displays it to the user in an appropriate interface. When the user responds to the advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on an advertisement for sneakers on their smartphone, the information is immediately sent to the server and used for later analysis.

[0872] Hardware and software used

[0873] The servers are deployed on cloud platforms (e.g., AWS, Google Cloud, Azure). Natural language processing engines (e.g., Google NLP, IBM Watson) are used for analysis, generative AI engines (e.g., OpenAI GPT-4) are used for ad generation, and marketing automation tools (e.g., Mailchimp, HubSpot) are used for ad delivery.

[0874] With the above configuration, it is possible to generate personalized advertisements based on user preferences in real time and deliver them at the optimal timing.

[0875] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0876] Step 1:

[0877] The server collects word-of-mouth and feedback data from user devices in real time. Specifically, it receives text, images, and audio data posted by users on applications and websites and stores this data on a cloud server. The input is word-of-mouth and feedback data from users, and the output is the data stored on the cloud server.

[0878] Step 2:

[0879] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it extracts keywords from the text data and performs sentiment analysis to determine whether the comments are positive, negative, or neutral. The input is the reviews and feedback data stored on the cloud server, and the output is the extracted keywords and sentiment information.

[0880] Step 3:

[0881] The server inputs a prompt text based on the analysis results into the generative AI engine, which then generates a custom ad tailored to the user's interests and preferences. Specifically, a prompt text such as "Please generate advertising copy for a new product suitable for a user looking for comfortable sneakers" is generated and input into the generative AI model. The input is a prompt text based on the analysis results, and the output is the advertising copy created by the generative AI model.

[0882] Step 4:

[0883] The server delivers the generated custom ads to the user's device via a marketing automation tool. Specifically, it configures the settings to deliver ads at the optimal time based on the user's behavioral history. For example, if a user frequently uses the app at night, it delivers ads at night. The input is the generated ad copy and the user's behavioral history, and the output is the ad delivered to the user's device.

[0884] Step 5:

[0885] When a user responds to an ad (by clicking, skipping, purchasing, etc.), the device sends that data to the server. Specifically, when a user clicks on an ad, that information is immediately sent to the server and stored on the cloud server. The input is the user's response data to the ad, and the output is the response data stored on the cloud server.

[0886] Step 6:

[0887] The server analyzes the collected feedback data and evaluates the effectiveness of the ads. Specifically, it analyzes which ads were effective based on behavioral data such as click rates, skip rates, and purchase rates. The input is the feedback data stored on the cloud server, and the output is the evaluation results of the advertising effectiveness.

[0888] Step 7:

[0889] The server then performs optimization based on the evaluation results to reflect them in the next ad generation. Specifically, ads with high click-through rates are continued without any improvements, while ads with low responses are modified in content or targeting. The input is the evaluation results of the advertising effectiveness, and the output is optimization data for the next ad generation.

[0890] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0891] System Overview

[0892] This system has the ability to personalize, automatically generate, and deliver advertisements based on user reviews and feedback. It also combines an emotion engine that analyzes user emotions to achieve even more accurate ad generation and delivery. Specifically, it analyzes collected data and generates custom ads using the emotion engine and generative AI engine. The ads are then delivered to user devices, and feedback is collected again to optimize advertising effectiveness.

[0893] Server Processing

[0894] Data collection

[0895] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[0896] Data analysis

[0897] The server inputs the collected data into a natural language processing (NLP) and emotion engine to extract text and analyze user sentiment. This allows it to extract keywords such as "lipstick" and "like" and determine whether the comment is positive, negative, or neutral. This information is then used to identify the user's interests and preferences.

[0898] Ad Generation

[0899] Using the results of the analysis and sentiment analysis, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest the user.

[0900] Ad serving

[0901] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery, delivering them based on the user's emotions and behavioral history. For example, if a user frequently uses the app at night and has positive emotions at that time, the server will set the ads to be delivered at night.

[0902] Feedback collection and optimization

[0903] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the generative AI and emotion engine optimize the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[0904] Terminal handling

[0905] The user device receives advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicking, skipping, etc.), the data is sent to the server. Furthermore, the user's facial expressions and behavior are detected using cameras and sensors, and sent to the emotion engine for real-time emotion analysis. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server and used for subsequent analysis.

[0906] User Behavior

[0907] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided. In addition, the user's facial expressions and behavior when viewing an ad are also sent to the emotion engine, and this is used as data for ad optimization.

[0908] This system generates ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' attention and maximizing advertising effectiveness.

[0909] The processing flow will be explained below.

[0910] Step 1:

[0911] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[0912] Step 2:

[0913] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[0914] Step 3:

[0915] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[0916] Step 4:

[0917] The server inputs the stored data into a natural language processing (NLP) engine and sentiment engine to extract text, analyze keywords, and analyze sentiment. For example, it can extract keywords such as "lipstick" and "like" and determine whether a comment is positive.

[0918] Step 5:

[0919] The server uses the analysis results of the emotion engine to determine the user's emotional status, for example, determining that the user has a positive emotion.

[0920] Step 6:

[0921] The server inputs the analysis results and emotional status into a generation AI engine, which automatically generates custom ads tailored to the user's emotions as well as their interests and preferences. Specifically, it generates ad copy such as "Try these amazing shades!"

[0922] Step 7:

[0923] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[0924] Step 8:

[0925] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[0926] Step 9:

[0927] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[0928] Step 10:

[0929] Users respond to the ads displayed to them by clicking on them, making a purchase, or skipping them, and this behavioral data is collected by the device.

[0930] Step 11:

[0931] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[0932] Step 12:

[0933] The server analyzes the collected behavioral data and evaluates the effectiveness of the advertisement, specifically calculating click-through rates and conversion rates.

[0934] Step 13:

[0935] The server inputs the results of the effectiveness evaluation into the AI ​​engine and emotion engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and the content and targeting of ads with low response rates are changed.

[0936] Step 14:

[0937] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[0938] Step 15:

[0939] The device collects measurable emotional data (such as facial expressions and behavior) from the user and sends it to a server. For example, a camera or sensor can be used to detect the user's facial expressions, and the data is used for analysis.

[0940] Step 16:

[0941] The server analyzes the collected emotional data and uses it to optimize advertising. By including emotional data from users while they are viewing ads in the analysis of advertising effectiveness, more accurate optimization becomes possible.

[0942] Example 2

[0943] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0944] Conventional ad delivery systems have had difficulty in generating and delivering ads that fully incorporate real-time user reviews and feedback. Furthermore, they have been unable to adequately optimize ads based on user sentiment, making it difficult to maximize advertising effectiveness. Furthermore, there are issues with the significant time and effort required to utilize feedback after ad delivery to improve ad content and delivery strategies.

[0945] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0946] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; means for analyzing the collected data using a natural language processing and sentiment analysis engine to identify user interests and preferences; a generation AI engine for automatically generating customized advertisements based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisements to user devices and optimizing the timing and frequency of delivery; and means for collecting feedback data from users again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to effectively generate and deliver advertisements that are always optimized based on users' real-time feedback and sentiment data, thereby maximizing advertising effectiveness.

[0947] "User" means an end user who uses a particular application or website to post reviews and feedback.

[0948] "Real-time" means that processing occurs immediately the moment the user sends the data.

[0949] "Review or Feedback Data" means data such as text, images, or audio that a user provides through an application or website.

[0950] "Natural language processing" is a technology for converting text data into a format that is easy for machines to understand and analyzing its meaning.

[0951] An "emotion analysis engine" is a system that analyzes text data and information obtained from sensors to detect user emotions.

[0952] "Interests and Preferences" refers to the interest or preference a user has in a particular product, service, or topic.

[0953] A "generative AI engine" is an engine that uses artificial intelligence technologies such as deep learning models to analyze data and automatically generate custom advertisements.

[0954] "Custom Ads" are ads that are personalized based on a particular user's interests, preferences, and emotions.

[0955] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0956] "Optimizing delivery timing and frequency" refers to the process of adjusting the delivery of advertisements at the most effective time and frequency based on user behavioral history and emotional data.

[0957] "Feedback data" refers to data about the actions users take after viewing an ad (clicks, purchases, skips, etc.).

[0958] "Advertising effectiveness evaluation and optimization" refers to the process of analyzing collected feedback data, measuring advertising performance, and improving next ad generation and distribution strategies.

[0959] This invention is a system that automatically generates and distributes personalized advertisements based on real-time user reviews and feedback. Furthermore, by combining this with an emotion engine that analyzes user emotions, it is possible to generate and distribute advertisements with even greater accuracy.

[0960] The system uses the following hardware and software:

[0961] User device: A device such as a smartphone, tablet, or computer.

[0962] Server: A central computer that collects data, analyzes, generates and delivers advertisements.

[0963] Natural Language Processing (NLP) engine: Software that performs text analysis on user data.

[0964] Sentiment analysis engine: Software that analyzes emotions from user data.

[0965] Generative AI engine: Software that uses deep learning models to generate custom ads.

[0966] Marketing automation tool: Software that delivers generated advertisements to user devices.

[0967] The operation of the system will be specifically described below.

[0968] Data collection

[0969] When a user posts a review or feedback on a particular application or website, for example, when a user posts a comment in a cosmetics app saying, "I love your new lipstick," that data is sent from the user's device to a server. The data may include text, images, and audio.

[0970] Data analysis

[0971] The server inputs the collected data into a natural language processing (NLP) engine. The NLP engine extracts keywords from the text data. For example, the keywords "lipstick" and "like" are extracted. Then, a sentiment analysis engine analyzes the user's comments and classifies them as positive, negative, or neutral. In this case, a positive sentiment is detected from the expression "like."

[0972] Ad Generation

[0973] The server inputs the analysis results into a generation AI engine to generate custom ads based on the user's interests and preferences. For example, to generate an ad for a new lipstick color, the message "Try these amazing shades!" is generated. This ad copy includes specific words and images that are likely to interest the user.

[0974] Example prompt sentence:

[0975] "Generate ad copy for a new cosmetic product. A user review reads, 'I love your new lipstick.'"

[0976] Ad serving

[0977] The custom ads created by the generative AI engine are delivered to users' devices via marketing automation tools. The server calculates the optimal delivery timing and frequency based on the user's behavioral history and emotional data. For example, if a user uses the app more at night and shows positive emotions, the server will set the ads to be delivered at night.

[0978] Feedback collection and optimization

[0979] After an ad is delivered, the user's post-ad behavior (click, purchase, skip, etc.) is immediately collected as data. When a user clicks on a lipstick ad on their smartphone, that information is sent to the server. The server analyzes this feedback data and evaluates the effectiveness of the ad. Based on the evaluation results, the next ad generation and delivery strategy are optimized. For example, ads with high click rates can be continued as is, while ads with low responses can be improved.

[0980] This allows us to effectively generate and deliver ads that are always optimized based on real-time user feedback and sentiment data, maximizing advertising effectiveness.

[0981] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0982] Step 1: Data collection

[0983] The server collects word-of-mouth and feedback data from user devices in real time. For example, a user posts a comment in a cosmetics app saying, "I like the new lipstick." The input is the text, image, and voice data posted by the user, and the output is the data received by the server. In this way, the server obtains the feedback data entered by the user.

[0984] Step 2: Natural Language Processing (NLP)

[0985] The server inputs the collected data into a natural language processing (NLP) engine. Specifically, it analyzes the text data of user engagement and extracts keywords. The input is the collected feedback data, and the output is the extracted keywords. For example, "lipstick" and "like" are extracted. Through this analysis, the server understands the user's interests and preferences.

[0986] Step 3: Sentiment Analysis

[0987] The server inputs the keywords obtained from the NLP engine into the sentiment analysis engine. The input is the keywords from the NLP engine, and the output is the emotional assessment result (positive, negative, neutral). For example, the keyword "I liked it" is analyzed to determine positive emotions. Based on this information, the server understands the user's emotions.

[0988] Step 4: Ad generation

[0989] The server inputs a prompt based on the analysis results into a generative AI engine, which then generates a custom ad based on the user's interests and preferences. The input is the analysis results and the prompt, and the output is the generated ad copy. Specifically, based on the comment "I love your new lipstick," the server generates a message saying "Try this great shade!". Through this generation, the server prepares a personalized ad for the user.

[0990] Step 5: Ad serving

[0991] The server uses a marketing automation tool to deliver the generated custom ads to the user's device. The input is the generated ad copy and delivery schedule data, and the output is the ad displayed on the user's device. For example, if a user uses the app more at night, the server can set it to deliver ads at night. Through this process, the server delivers ads to the user at the optimal time.

[0992] Step 6: Collect and analyze feedback

[0993] The server collects feedback data (clicks, purchases, skips, etc.) from users after delivering ads. The input is user response data, and the output is behavioral data sent to the server. For example, when a user clicks on an ad, that information is sent to the server. Based on this feedback, the server evaluates and analyzes the effectiveness of the ad.

[0994] Step 7: Optimization

[0995] The server analyzes the collected feedback data, evaluates the effectiveness of the ads, and optimizes the next ad generation and distribution strategy. The input is the ad effectiveness evaluation data, and the output is an optimized ad generation and distribution strategy. For example, ads with high click-through rates are continued as they are, while ads with low effectiveness are improved. This allows the server to make adjustments to maximize advertising contribution.

[0996] As described above, this system effectively generates and delivers ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience and maximizing advertising effectiveness.

[0997] (Application example 2)

[0998] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0999] Conventional ad delivery methods only take into account the user's interests and preferences, and have the problem of not being able to analyze user emotions in real time to optimize ad content and delivery timing. As a result, ads that capture the user's attention are not as effective as they could be, resulting in low ad click rates and purchase rates.

[1000] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine that analyzes the collected data and identifies the user's interests, preferences, and emotions; means for automatically generating a customized advertisement based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisement to the user terminal at an appropriate time based on the results of the user's emotion analysis; and means for collecting feedback from the user again after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement. This enables advanced advertisement delivery that takes user emotions into consideration, making it possible to maximize the effectiveness of advertisements that attract the user's attention.

[1001] 1. "User" means any individual or legal entity that uses the System or Application.

[1002] 2. "Reviews" refers to ratings and comments provided by users to other users about products or services based on their own experiences.

[1003] 3. "Feedback Data" refers to information such as opinions, impressions, and behavioral data provided by users.

[1004] 4. "Real-time" refers to the temporal concept of data being processed almost simultaneously at the moment it is generated.

[1005] 5. "Generative AI engine" refers to a software module that uses artificial intelligence to perform analysis and generation.

[1006] 6. "Interests and Preferences" refers to a user's interest in or preference for a particular product or service.

[1007] 7. “Sentiment Analysis” refers to the process of assessing a user’s emotional state based on collected data.

[1008] 8. "Custom Ads" refers to ads that are specifically tailored to a user's individual needs, interests, and even emotions.

[1009] 9. "Automatic generation means" refers to a system in which advertisements are automatically generated by a machine based on pre-set rules or algorithms.

[1010] 10. "Right timing" refers to the optimal time for ad delivery based on a user's behavioral history and emotional state.

[1011] 11. "Device" means the device used by a User to receive and display advertisements.

[1012] 12. "Means for evaluating and optimizing effectiveness" refers to a system for evaluating the effectiveness of delivered advertisements and making adjustments to further improve their effectiveness.

[1013] Based on these definitions, the features of the present invention and the terms thereof can be clearly understood.

[1014] System Overview

[1015] This system uses word-of-mouth and feedback data collected from users in real time, and through sentiment analysis, automatically generates and delivers custom ads based on the user's interests, preferences, and emotions. It also evaluates and optimizes the effectiveness of ads based on the feedback.

[1016] Hardware and software used

[1017] Hardware: Servers, user devices (smartphones and tablets), cameras, sensors

[1018] Software: Natural language processing engines (e.g., TextBlob), generative AI engines (e.g., the Transformers library), sentiment analysis engines, marketing automation tools

[1019] Program Processing Overview

[1020] 1. Data Collection:

[1021] When users post reviews or feedback on their smartphones or tablets, the data is sent to the server in real time, including text data, image data, and audio data.

[1022] 2. Data Analysis:

[1023] The server analyzes the collected data using a natural language processing engine (TextBlob) and a sentiment analysis engine (Transformers library), extracting keywords from the text and classifying sentiment as positive, negative, or neutral.

[1024] 3. Ad generation:

[1025] Based on the analysis results, the generative AI engine automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, if a user posts positive feedback, the ad copy will be tailored to that emotion.

[1026] 4. Advertisement Delivery:

[1027] Custom ads are delivered to users' devices at optimal times via marketing automation tools, which are determined based on users' behavioral history and emotional data.

[1028] 5. Feedback collection and optimization:

[1029] After the ad is delivered, the user's response data (clicks, skips, etc.) is sent back to the server. The server analyzes this data and evaluates the effectiveness of the ad. Based on the evaluation results, the generation AI engine and sentiment analysis engine will reflect this in the next ad generation.

[1030] Specific examples

[1031] Example 1: Generating ads in response to positive reviews

[1032] When a user posts feedback such as "I love the new lipstick," the sentiment analysis engine determines this as a positive emotion. The generative AI engine generates advertising copy such as "Perfect for you! Try our new lipstick color!" and delivers it to the user's device at the appropriate time.

[1033] Prompt Sentence Examples

[1034] "User posted feedback: 'I love my new lipstick.' Analyze it."

[1035] Example 2: Generating ads in response to negative reviews

[1036] When a user posts feedback such as "This perfume was a little too strong," the sentiment analysis engine determines this as a negative sentiment. The generative AI engine generates advertising copy such as "Great deals! Popular products at special prices!" and delivers it to the user's device at the appropriate time.

[1037] In this way, a system is realized that delivers advanced advertisements based on real-time user emotional data, maximizing advertising effectiveness.

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

[1039] Step 1:

[1040] Users post reviews and feedback on their smartphones or tablets. This generates text data, image data, and audio data. The user's device sends this data to the server in real time. The input is the reviews and feedback data, and the output is the data sent to the server.

[1041] Step 2:

[1042] The server inputs the received word-of-mouth and feedback data into a natural language processing engine (e.g., TextBlob) and analyzes the text data. Through analysis, keywords within the text are extracted and the user's interests and preferences are determined. The input is the word-of-mouth and feedback text data, and the output is the extracted keywords and data on interests and preferences.

[1043] Step 3:

[1044] The server inputs the extracted keywords, interests, and preference data into a sentiment analysis engine (e.g., the Transformers library) to classify the user's sentiment into positive, negative, or neutral. The input is keywords and interest and preference data, and the output is the sentiment classification result.

[1045] Step 4:

[1046] The server inputs the sentiment classification results into a generative AI engine to automatically generate custom ads based on the user's interests, preferences, and emotions. The generative AI engine uses a deep learning model to generate ad copy. The input is the sentiment classification results, and the output is the generated custom ad.

[1047] Step 5:

[1048] The server delivers the generated custom ads to user devices at the appropriate time via a marketing automation tool. The delivery timing is determined based on the user's behavioral history and emotional data. The input is the generated custom ads and delivery timing data, and the output is the delivery of the ads to the user devices.

[1049] Step 6:

[1050] The user reacts to the delivered advertisement, for example, by clicking or skipping the advertisement. This behavioral data is sent from the terminal to the server. The input is the user's behavioral data regarding the advertisement, and the output is the behavioral data sent to the server.

[1051] Step 7:

[1052] The server analyzes user behavior data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generation AI engine and sentiment analysis engine reflect them in the generation of the next advertisement. This process makes it possible to optimize the content of the advertisement and its distribution strategy. The input is user behavior data and advertisement effectiveness evaluation data, and the output is an optimized advertisement generation algorithm.

[1053] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1054] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1055] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1056] [Fourth embodiment]

[1057] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1058] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1059] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1060] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1061] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1062] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1063] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1064] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1065] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1066] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1067] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1068] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1069] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1070] System Overview

[1071] The system has the ability to automatically generate and distribute personalized ads based on user reviews and feedback. Specifically, it analyzes collected data and uses a generative AI engine to generate custom ads. The ads are then distributed to user devices, and feedback is collected again to optimize advertising effectiveness.

[1072] Server Processing

[1073] Data collection

[1074] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[1075] Data analysis

[1076] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether a user's comment is positive, negative, or neutral. Based on this information, the server can identify the user's interests and preferences.

[1077] Ad Generation

[1078] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest users.

[1079] Ad serving

[1080] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[1081] Feedback collection and optimization

[1082] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[1083] Terminal handling

[1084] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[1085] User Behavior

[1086] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided.

[1087] This system generates ads based on real-time user feedback, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' interest and maximizing advertising effectiveness.

[1088] The processing flow will be explained below.

[1089] Step 1:

[1090] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[1091] Step 2:

[1092] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[1093] Step 3:

[1094] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[1095] Step 4:

[1096] The server inputs the stored data into a natural language processing (NLP) engine to extract text and keywords, such as "lipstick" and "like."

[1097] Step 5:

[1098] The server performs sentiment analysis to determine whether a user's comments are positive, negative, or neutral, and uses this information to identify the user's interests and preferences.

[1099] Step 6:

[1100] The server then feeds the analysis results into a generative AI engine that automatically generates custom ads based on the user's interests and preferences. These ads include text and visuals such as "Try these amazing shades!"

[1101] Step 7:

[1102] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[1103] Step 8:

[1104] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[1105] Step 9:

[1106] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[1107] Step 10:

[1108] Users respond to the ads they see by clicking on them, skipping them, or making a purchase, and this behavioral data is collected by the device.

[1109] Step 11:

[1110] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[1111] Step 12:

[1112] The server analyzes the collected behavioral data to evaluate the effectiveness of advertising, for example, calculating click-through rates and conversion rates.

[1113] Step 13:

[1114] The server inputs the results of the effectiveness evaluation back into the AI ​​engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and ads with low response rates are improved.

[1115] Step 14:

[1116] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[1117] Example 1

[1118] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1119] In modern advertising delivery, it is a difficult challenge to efficiently generate and deliver personalized advertisements that match users' interests and preferences. To solve this problem, a system is needed that effectively utilizes user word-of-mouth and feedback to optimize advertisements in real time.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1121] In this invention, the server includes means for collecting word-of-mouth or feedback data from user terminals in real time, means for analyzing the collected data using a natural language processing engine and identifying the user's interests and preferences, means for inputting prompt sentences into a generation AI engine based on the identified interests and preferences and automatically generating a customized advertisement, means for delivering the generated customized advertisement to the user terminals via a marketing automation tool, and means for collecting feedback data from users after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement.

[1122] This makes it possible to generate optimal advertisements based on users' interests and preferences in real time and deliver them efficiently.

[1123] A "user terminal" is a device operated by a user, and includes smartphones, tablets, personal computers, etc.

[1124] "Review or Feedback Data" means information posted by users through an application or website, and may be in the form of text, images, audio, or other information.

[1125] A "natural language processing engine" is a software tool that analyzes text data and performs keyword extraction and sentiment analysis, and examples include SpaCy and NLTK.

[1126] A "generative AI engine" is an artificial intelligence engine that generates custom ads based on user interests and preferences, and examples include OpenAI's GPT-4.

[1127] A "prompt sentence" is an instruction sentence input into the generative AI engine, and is specific input data for generating a custom ad.

[1128] "Custom ads" are ads automatically generated based on a user's interests and preferences, and come in the form of text, images, videos, and more.

[1129] A "marketing automation tool" is a software tool for automating advertising and marketing activities, such as HubSpot or Marketo.

[1130] "Feedback data" refers to information about a user's response to an advertisement (click, skip, purchase, etc.).

[1131] A "collection means" is a method or device for acquiring data from a user terminal.

[1132] "Means for analyzing" refers to a method or device for analyzing collected data and identifying user interests and preferences.

[1133] "Means for generating" refers to a method or device for inputting a prompt sentence into a generating AI engine based on the analysis results and generating a custom advertisement.

[1134] The "means for delivering" refers to a method or device for transmitting the generated custom advertisement to a user terminal.

[1135] The "optimization means" refers to a method or device for analyzing feedback data collected after advertisement distribution, and evaluating and improving the effectiveness of the advertisement.

[1136] This invention relates to a system that generates and distributes personalized advertisements based on word-of-mouth and feedback data collected from users. Specifically, it collects user behavior data in real time, analyzes it with a natural language processing (NLP) engine, and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback data is collected again to optimize the effectiveness of the advertisements.

[1137] Server Processing

[1138] Data collection

[1139] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user logs into a cosmetics app and posts a comment saying, "I love your new lipstick," that information is sent to the server.

[1140] Data analysis

[1141] The server analyzes the collected data using a natural language processing (NLP) engine (such as SpaCy or NLTK). This allows it to extract keywords such as "lipstick" and "like" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. Based on this information, it can identify the user's interests and preferences.

[1142] Ad Generation

[1143] Using the analysis results, the server inputs the data into a generative AI engine (e.g., OpenAI's GPT-4) to automatically generate custom ads tailored to the user's interests and preferences. For example, by inputting the prompt "Create an ad for a new lipstick color," the server generates ad copy such as "Try this amazing shade!"

[1144] Ad serving

[1145] The generated custom ads are delivered to the user's device via a marketing automation tool (e.g., HubSpot or Marketo). The server also considers the optimal delivery timing and frequency based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ads to be delivered at night.

[1146] Feedback collection and optimization

[1147] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click rates can be continued as they are, while ads with low responses can be changed.

[1148] Terminal handling

[1149] The user device receives the advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server for later analysis.

[1150] User Behavior

[1151] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, and users respond to the ads. This response is fed back into the generation and distribution of the next ad, allowing the system to continue providing ads that are more relevant to the user.

[1152] This system generates advertisements based on real-time user feedback and provides a constantly optimized advertising experience, effectively delivering advertisements that capture users' interest and maximizing advertising effectiveness.

[1153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1154] Step 1:

[1155] The user enters the feedback data.

[1156] Users submit reviews and feedback on applications and websites, and this data can include text, images, and audio.

[1157] Specific behavior: A user logs into a cosmetics app and posts a comment saying, "I love your new lipstick." The comment is sent to the central server through the application server.

[1158] Input: User comments and feedback.

[1159] Output: Review data collected on the server.

[1160] Step 2:

[1161] The server analyzes the collected data using a natural language processing (NLP) engine.

[1162] The server feeds the received reviews and feedback data into an NLP engine (e.g., SpaCy or NLTK), where keyword extraction and sentiment analysis are performed.

[1163] Specific operation: The server analyzes the comment "I like the new lipstick" and extracts keywords such as "lipstick" and "like." At the same time, it uses sentiment analysis to determine whether the comment is positive.

[1164] Input: Collected review data.

[1165] Output: Keyword and sentiment analysis results.

[1166] Step 3:

[1167] The server passes the analysis results to a generative AI engine to generate custom ads.

[1168] The server inputs the analysis results of the NLP engine into a generative AI engine (e.g., OpenAI's GPT-4) and requests it to generate a custom ad.

[1169] Specific operation: The server sends the prompt "Please create an advertisement for a new lipstick color" to the AI ​​engine. The AI ​​engine generates the advertisement copy "Try this amazing shade!"

[1170] Input: Keywords and sentiment analysis results.

[1171] Output: The generated custom ad copy.

[1172] Step 4:

[1173] The server delivers the generated custom advertisement to the user terminal via a marketing automation tool.

[1174] The generated advertisement is passed to an advertisement distribution tool (e.g., HubSpot or Marketo) and sent to the user's device at the optimal time.

[1175] Specific operation: The server sets up nighttime ad distribution based on the user's behavioral history. The ad distribution tool sends the ad to the user's smartphone.

[1176] Input: Your generated custom ad copy.

[1177] Output: Advertisement delivered to user device.

[1178] Step 5:

[1179] The server collects feedback data from users after delivering the advertisements, and evaluates and optimizes the effectiveness of the advertisements.

[1180] The server collects and analyzes data such as ad click rates, purchase rates, and skip rates, and uses this information to generate the next ad.

[1181] Specific operation: When a user clicks on an ad, the data is sent to the server. The server analyzes the click data and evaluates the effectiveness of the ad. If the click rate is high, the same ad format will continue to be displayed, but if the response is low, the ad content will be changed.

[1182] Input: User feedback data.

[1183] Output: Evaluation of the effectiveness of the ad and the results reflected in the next ad generation.

[1184] The above is the specific processing flow of this system, which makes it possible to generate and distribute advertisements optimized for users in real time.

[1185] (Application example 1)

[1186] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1187] Conventional ad delivery systems have difficulty accurately grasping users' interests and preferences, making it difficult to deliver ads effectively. In particular, there is a lack of a way to deliver ads optimized for individual users in a timely manner, which reduces the effectiveness of advertising.

[1188] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1189] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine for analyzing the collected data and identifying user interests and preferences; means for automatically generating customized advertisements based on the identified interests and preferences and creating advertisement copy using prompt text using a generation AI model; means for delivering the generated customized advertisements to user devices at optimal times based on user behavior data; and means for collecting user feedback again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to generate personalized advertisements based on user preferences in real time and deliver them at optimal times.

[1190] "User" refers to the general consumer who uses a product or service, and in particular the person who provides word-of-mouth or feedback.

[1191] "Review or Feedback Data" refers to any user feedback or evaluation information, such as text, images, or audio, posted by users on an application or website.

[1192] "Means of collection" refers to the mechanism for obtaining word-of-mouth or feedback data from user devices in real time and sending it to a server.

[1193] "Analysis means" refers to technologies used to analyze collected reviews or feedback data and identify user interests and preferences.

[1194] A "generative AI engine" refers to an artificial intelligence engine that analyzes user preferences based on collected data and generates appropriate advertisements.

[1195] A "prompt" is an input to a generative AI model, and refers to an instruction to request the generation of a specific ad copy or sentence.

[1196] "Generative AI model" refers to an artificial intelligence model that automatically generates advertising copy and related information based on a given prompt.

[1197] "Ad generation method" refers to a mechanism that automatically generates custom advertisements based on a user's interests and preferences.

[1198] "Timely delivery" refers to a system that delivers advertisements at the optimal time based on the user's behavioral history and usage patterns.

[1199] "Means of collecting feedback" refers to a system that recollects user reactions and evaluation data after advertisement delivery and sends it to a server.

[1200] "Means for evaluating and optimizing advertising effectiveness" refers to a mechanism for analyzing the effectiveness of advertising using collected feedback data and reflecting the results in the generation and distribution of the next advertisement.

[1201] "User terminal" refers to a device that can connect to the Internet and is used by a user, such as a smartphone, tablet, or PC.

[1202] System Overview

[1203] This invention is a system that automatically generates and distributes personalized advertisements based on user behavioral data and feedback data. The system analyzes collected data and generates custom advertisements using a generative AI engine. The advertisements are then distributed to user devices, and feedback is collected again to optimize the effectiveness of the advertisements.

[1204] Server Processing

[1205] Data collection

[1206] The server receives real-time user reviews and feedback data from users' devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment on an online shopping site saying, "These sneakers are very comfortable," that information is sent to the server.

[1207] Data analysis

[1208] The server analyzes the collected data using a natural language processing (NLP) engine, extracting keywords such as "sneakers" and "comfortable" from user comments. It also uses sentiment analysis to determine whether user comments are positive, negative, or neutral. This information is used to identify the user's interests and preferences.

[1209] Ad Generation

[1210] Using the analysis results, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests and preferences. Specific ad copy is generated by inputting a prompt into the generative AI model. For example, in the previous example, the prompt would be, "Generate ad copy for a new product suitable for a user looking for comfortable sneakers." Using this prompt, the generative AI model would generate ad copy such as, "Our newly released sneakers will provide you with the ultimate in comfort. Click now to see the details!"

[1211] Ad serving

[1212] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery based on the user's behavioral history. For example, if a user frequently uses the app at night, the server can set the ad delivery time to be nighttime.

[1213] Feedback collection and optimization

[1214] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the AI ​​engine optimizes the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[1215] User terminal processing

[1216] The user device receives the advertisement and feedback request sent from the server and displays it to the user in an appropriate interface. When the user responds to the advertisement (clicks, skips, etc.), the data is sent to the server. For example, if a user clicks on an advertisement for sneakers on their smartphone, the information is immediately sent to the server and used for later analysis.

[1217] Hardware and software used

[1218] The servers are deployed on cloud platforms (e.g., AWS, Google Cloud, Azure). Natural language processing engines (e.g., Google NLP, IBM Watson) are used for analysis, generative AI engines (e.g., OpenAI GPT-4) are used for ad generation, and marketing automation tools (e.g., Mailchimp, HubSpot) are used for ad delivery.

[1219] With the above configuration, it is possible to generate personalized advertisements based on user preferences in real time and deliver them at the optimal timing.

[1220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1221] Step 1:

[1222] The server collects word-of-mouth and feedback data from user devices in real time. Specifically, it receives text, images, and audio data posted by users on applications and websites and stores this data on a cloud server. The input is word-of-mouth and feedback data from users, and the output is the data stored on the cloud server.

[1223] Step 2:

[1224] The server analyzes the collected data using a natural language processing (NLP) engine. Specifically, it extracts keywords from the text data and performs sentiment analysis to determine whether the comments are positive, negative, or neutral. The input is the reviews and feedback data stored on the cloud server, and the output is the extracted keywords and sentiment information.

[1225] Step 3:

[1226] The server inputs a prompt text based on the analysis results into the generative AI engine, which then generates a custom ad tailored to the user's interests and preferences. Specifically, a prompt text such as "Please generate advertising copy for a new product suitable for a user looking for comfortable sneakers" is generated and input into the generative AI model. The input is a prompt text based on the analysis results, and the output is the advertising copy created by the generative AI model.

[1227] Step 4:

[1228] The server delivers the generated custom ads to the user's device via a marketing automation tool. Specifically, it configures the settings to deliver ads at the optimal time based on the user's behavioral history. For example, if a user frequently uses the app at night, it delivers ads at night. The input is the generated ad copy and the user's behavioral history, and the output is the ad delivered to the user's device.

[1229] Step 5:

[1230] When a user responds to an ad (by clicking, skipping, purchasing, etc.), the device sends that data to the server. Specifically, when a user clicks on an ad, that information is immediately sent to the server and stored on the cloud server. The input is the user's response data to the ad, and the output is the response data stored on the cloud server.

[1231] Step 6:

[1232] The server analyzes the collected feedback data and evaluates the effectiveness of the ads. Specifically, it analyzes which ads were effective based on behavioral data such as click rates, skip rates, and purchase rates. The input is the feedback data stored on the cloud server, and the output is the evaluation results of the advertising effectiveness.

[1233] Step 7:

[1234] The server then performs optimization based on the evaluation results to reflect them in the next ad generation. Specifically, ads with high click-through rates are continued without any improvements, while ads with low responses are modified in content or targeting. The input is the evaluation results of the advertising effectiveness, and the output is optimization data for the next ad generation.

[1235] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1236] System Overview

[1237] This system has the ability to personalize, automatically generate, and deliver advertisements based on user reviews and feedback. It also combines an emotion engine that analyzes user emotions to achieve even more accurate ad generation and delivery. Specifically, it analyzes collected data and generates custom ads using the emotion engine and generative AI engine. The ads are then delivered to user devices, and feedback is collected again to optimize advertising effectiveness.

[1238] Server Processing

[1239] Data collection

[1240] The server receives real-time word-of-mouth and feedback data from user devices, including text, image, and audio data posted by users on specific applications and websites. For example, if a user posts a comment like "I love your new lipstick" on a cosmetics app, that information is sent to the server.

[1241] Data analysis

[1242] The server inputs the collected data into a natural language processing (NLP) and emotion engine to extract text and analyze user sentiment. This allows it to extract keywords such as "lipstick" and "like" and determine whether the comment is positive, negative, or neutral. This information is then used to identify the user's interests and preferences.

[1243] Ad Generation

[1244] Using the results of the analysis and sentiment analysis, the server inputs the data into a generative AI engine, which automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, in the previous example, when generating an ad for a "new lipstick color," the server generates ad copy such as "Try these amazing shades!" This ad copy includes words and images that are likely to interest the user.

[1245] Ad serving

[1246] The generated custom ads are delivered to the user's device via a marketing automation tool. The server also considers the optimal timing and frequency of delivery, delivering them based on the user's emotions and behavioral history. For example, if a user frequently uses the app at night and has positive emotions at that time, the server will set the ads to be delivered at night.

[1247] Feedback collection and optimization

[1248] After the ad is delivered, the server again collects feedback data, including behavioral data such as whether the user clicked on the ad, made a purchase, or skipped it. The server analyzes this data and evaluates the effectiveness of the ad. Based on this evaluation, the generative AI and emotion engine optimize the ad content and delivery strategy to reflect it in the next ad generation. For example, ads with high click-through rates can be continued without any improvements, while ads with low responses can have their content or targeting changed.

[1249] Terminal handling

[1250] The user device receives advertisements and feedback requests sent from the server and displays them to the user in an appropriate interface. When the user responds to an advertisement (clicking, skipping, etc.), the data is sent to the server. Furthermore, the user's facial expressions and behavior are detected using cameras and sensors, and sent to the emotion engine for real-time emotion analysis. For example, if a user clicks on a lipstick advertisement on their smartphone, the information is immediately sent to the server and used for subsequent analysis.

[1251] User Behavior

[1252] Users post reviews and feedback through applications and websites. Personalized ads are then displayed on their devices, allowing users to respond to the ads. This response is fed back into the generation and distribution of the next ad, ensuring that ads that are more relevant to the user are continually provided. In addition, the user's facial expressions and behavior when viewing an ad are also sent to the emotion engine, and this is used as data for ad optimization.

[1253] This system generates ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience, thereby effectively delivering ads that capture users' attention and maximizing advertising effectiveness.

[1254] The processing flow will be explained below.

[1255] Step 1:

[1256] Users enter their reviews and feedback. Specifically, they log in to a smartphone app or website and post comments such as, "I love your new lipstick."

[1257] Step 2:

[1258] The device collects user review data and sends it to the server, where it is packaged in a format such as JSON or XML.

[1259] Step 3:

[1260] The server receives the review data sent from the device and stores it in a database, which is then analyzed in the next step.

[1261] Step 4:

[1262] The server inputs the stored data into a natural language processing (NLP) engine and sentiment engine to extract text, analyze keywords, and analyze sentiment. For example, it can extract keywords such as "lipstick" and "like" and determine whether a comment is positive.

[1263] Step 5:

[1264] The server uses the analysis results of the emotion engine to determine the user's emotional status, for example, determining that the user has a positive emotion.

[1265] Step 6:

[1266] The server inputs the analysis results and emotional status into a generation AI engine, which automatically generates custom ads tailored to the user's emotions as well as their interests and preferences. Specifically, it generates ad copy such as "Try these amazing shades!"

[1267] Step 7:

[1268] The server stores the generated custom ads in a database and prepares them for distribution, as well as generating an ad distribution schedule and target list.

[1269] Step 8:

[1270] The server connects to the marketing automation tool and sends a list of ads to be delivered and a delivery schedule. The ads are then delivered to the user's device via this tool.

[1271] Step 9:

[1272] The device receives the advertisement sent from the server and displays it to the user. For example, a lipstick advertisement is displayed on a smartphone app.

[1273] Step 10:

[1274] Users respond to the ads displayed to them by clicking on them, making a purchase, or skipping them, and this behavioral data is collected by the device.

[1275] Step 11:

[1276] The device sends the user's behavior data to the server, where it is again packaged in JSON or XML format.

[1277] Step 12:

[1278] The server analyzes the collected behavioral data and evaluates the effectiveness of the advertisement, specifically calculating click-through rates and conversion rates.

[1279] Step 13:

[1280] The server inputs the results of the effectiveness evaluation into the AI ​​engine and emotion engine to optimize the next ad generation and distribution strategy. Ads with high click-through rates are maintained, and the content and targeting of ads with low response rates are changed.

[1281] Step 14:

[1282] The server then stores the optimized ad back in its database, ready to serve, and this cycle continues to ensure ad performance is always optimized.

[1283] Step 15:

[1284] The device collects measurable emotional data (such as facial expressions and behavior) from the user and sends it to a server. For example, a camera or sensor can be used to detect the user's facial expressions, and the data is used for analysis.

[1285] Step 16:

[1286] The server analyzes the collected emotional data and uses it to optimize advertising. By including emotional data from users while they are viewing ads in the analysis of advertising effectiveness, more accurate optimization becomes possible.

[1287] Example 2

[1288] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1289] Conventional ad delivery systems have had difficulty in generating and delivering ads that fully incorporate real-time user reviews and feedback. Furthermore, they have been unable to adequately optimize ads based on user sentiment, making it difficult to maximize advertising effectiveness. Furthermore, there are issues with the significant time and effort required to utilize feedback after ad delivery to improve ad content and delivery strategies.

[1290] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1291] In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; means for analyzing the collected data using a natural language processing and sentiment analysis engine to identify user interests and preferences; a generation AI engine for automatically generating customized advertisements based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisements to user devices and optimizing the timing and frequency of delivery; and means for collecting feedback data from users again after advertisement delivery and evaluating and optimizing the effectiveness of the advertisements. This makes it possible to effectively generate and deliver advertisements that are always optimized based on users' real-time feedback and sentiment data, thereby maximizing advertising effectiveness.

[1292] "User" means an end user who uses a particular application or website to post reviews and feedback.

[1293] "Real-time" means that processing occurs immediately the moment the user sends the data.

[1294] "Review or Feedback Data" means data such as text, images, or audio that a user provides through an application or website.

[1295] "Natural language processing" is a technology for converting text data into a format that is easy for machines to understand and analyzing its meaning.

[1296] An "emotion analysis engine" is a system that analyzes text data and information obtained from sensors to detect user emotions.

[1297] "Interests and Preferences" refers to the interest or preference a user has in a particular product, service, or topic.

[1298] A "generative AI engine" is an engine that uses artificial intelligence technologies such as deep learning models to analyze data and automatically generate custom advertisements.

[1299] "Custom Ads" are ads that are personalized based on a particular user's interests, preferences, and emotions.

[1300] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[1301] "Optimizing delivery timing and frequency" refers to the process of adjusting the delivery of advertisements at the most effective time and frequency based on user behavioral history and emotional data.

[1302] "Feedback data" refers to data about the actions users take after viewing an ad (clicks, purchases, skips, etc.).

[1303] "Advertising effectiveness evaluation and optimization" refers to the process of analyzing collected feedback data, measuring advertising performance, and improving next ad generation and distribution strategies.

[1304] This invention is a system that automatically generates and distributes personalized advertisements based on real-time user reviews and feedback. Furthermore, by combining this with an emotion engine that analyzes user emotions, it is possible to generate and distribute advertisements with even greater accuracy.

[1305] The system uses the following hardware and software:

[1306] User device: A device such as a smartphone, tablet, or computer.

[1307] Server: A central computer that collects data, analyzes, generates and delivers advertisements.

[1308] Natural Language Processing (NLP) engine: Software that performs text analysis on user data.

[1309] Sentiment analysis engine: Software that analyzes emotions from user data.

[1310] Generative AI engine: Software that uses deep learning models to generate custom ads.

[1311] Marketing automation tool: Software that delivers generated advertisements to user devices.

[1312] The operation of the system will be specifically described below.

[1313] Data collection

[1314] When a user posts a review or feedback on a particular application or website, for example, when a user posts a comment in a cosmetics app saying, "I love your new lipstick," that data is sent from the user's device to a server. The data may include text, images, and audio.

[1315] Data analysis

[1316] The server inputs the collected data into a natural language processing (NLP) engine. The NLP engine extracts keywords from the text data. For example, the keywords "lipstick" and "like" are extracted. Then, a sentiment analysis engine analyzes the user's comments and classifies them as positive, negative, or neutral. In this case, a positive sentiment is detected from the expression "like."

[1317] Ad Generation

[1318] The server inputs the analysis results into a generation AI engine to generate custom ads based on the user's interests and preferences. For example, to generate an ad for a new lipstick color, the message "Try these amazing shades!" is generated. This ad copy includes specific words and images that are likely to interest the user.

[1319] Example prompt sentence:

[1320] "Generate ad copy for a new cosmetic product. A user review reads, 'I love your new lipstick.'"

[1321] Ad serving

[1322] The custom ads created by the generative AI engine are delivered to users' devices via marketing automation tools. The server calculates the optimal delivery timing and frequency based on the user's behavioral history and emotional data. For example, if a user uses the app more at night and shows positive emotions, the server will set the ads to be delivered at night.

[1323] Feedback collection and optimization

[1324] After an ad is delivered, the user's post-ad behavior (click, purchase, skip, etc.) is immediately collected as data. When a user clicks on a lipstick ad on their smartphone, that information is sent to the server. The server analyzes this feedback data and evaluates the effectiveness of the ad. Based on the evaluation results, the next ad generation and delivery strategy are optimized. For example, ads with high click rates can be continued as is, while ads with low responses can be improved.

[1325] This allows us to effectively generate and deliver ads that are always optimized based on real-time user feedback and sentiment data, maximizing advertising effectiveness.

[1326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1327] Step 1: Data collection

[1328] The server collects word-of-mouth and feedback data from user devices in real time. For example, a user posts a comment in a cosmetics app saying, "I like the new lipstick." The input is the text, image, and voice data posted by the user, and the output is the data received by the server. In this way, the server obtains the feedback data entered by the user.

[1329] Step 2: Natural Language Processing (NLP)

[1330] The server inputs the collected data into a natural language processing (NLP) engine. Specifically, it analyzes the text data of user engagement and extracts keywords. The input is the collected feedback data, and the output is the extracted keywords. For example, "lipstick" and "like" are extracted. Through this analysis, the server understands the user's interests and preferences.

[1331] Step 3: Sentiment Analysis

[1332] The server inputs the keywords obtained from the NLP engine into the sentiment analysis engine. The input is the keywords from the NLP engine, and the output is the emotional assessment result (positive, negative, neutral). For example, the keyword "I liked it" is analyzed to determine positive emotions. Based on this information, the server understands the user's emotions.

[1333] Step 4: Ad generation

[1334] The server inputs a prompt based on the analysis results into a generative AI engine, which then generates a custom ad based on the user's interests and preferences. The input is the analysis results and the prompt, and the output is the generated ad copy. Specifically, based on the comment "I love your new lipstick," the server generates a message saying "Try this great shade!". Through this generation, the server prepares a personalized ad for the user.

[1335] Step 5: Ad serving

[1336] The server uses a marketing automation tool to deliver the generated custom ads to the user's device. The input is the generated ad copy and delivery schedule data, and the output is the ad displayed on the user's device. For example, if a user uses the app more at night, the server can set it to deliver ads at night. Through this process, the server delivers ads to the user at the optimal time.

[1337] Step 6: Collect and analyze feedback

[1338] The server collects feedback data (clicks, purchases, skips, etc.) from users after delivering ads. The input is user response data, and the output is behavioral data sent to the server. For example, when a user clicks on an ad, that information is sent to the server. Based on this feedback, the server evaluates and analyzes the effectiveness of the ad.

[1339] Step 7: Optimization

[1340] The server analyzes the collected feedback data, evaluates the effectiveness of the ads, and optimizes the next ad generation and distribution strategy. The input is the ad effectiveness evaluation data, and the output is an optimized ad generation and distribution strategy. For example, ads with high click-through rates are continued as they are, while ads with low effectiveness are improved. This allows the server to make adjustments to maximize advertising contribution.

[1341] As described above, this system effectively generates and delivers ads based on real-time user feedback and emotional data, providing a constantly optimized advertising experience and maximizing advertising effectiveness.

[1342] (Application example 2)

[1343] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1344] Conventional ad delivery methods only take into account the user's interests and preferences, and have the problem of not being able to analyze user emotions in real time to optimize ad content and delivery timing. As a result, ads that capture the user's attention are not as effective as they could be, resulting in low ad click rates and purchase rates.

[1345] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting word-of-mouth or feedback data from users in real time; a generation AI engine that analyzes the collected data and identifies the user's interests, preferences, and emotions; means for automatically generating a customized advertisement based on the identified interests, preferences, and emotions; means for delivering the generated customized advertisement to the user terminal at an appropriate time based on the results of the user's emotion analysis; and means for collecting feedback from the user again after the advertisement is delivered and evaluating and optimizing the effectiveness of the advertisement. This enables advanced advertisement delivery that takes user emotions into consideration, making it possible to maximize the effectiveness of advertisements that attract the user's attention.

[1346] 1. "User" means any individual or legal entity that uses the System or Application.

[1347] 2. "Reviews" refers to ratings and comments provided by users to other users about products or services based on their own experiences.

[1348] 3. "Feedback Data" refers to information such as opinions, impressions, and behavioral data provided by users.

[1349] 4. "Real-time" refers to the temporal concept of data being processed almost simultaneously at the moment it is generated.

[1350] 5. "Generative AI engine" refers to a software module that uses artificial intelligence to perform analysis and generation.

[1351] 6. "Interests and Preferences" refers to a user's interest in or preference for a particular product or service.

[1352] 7. “Sentiment Analysis” refers to the process of assessing a user’s emotional state based on collected data.

[1353] 8. "Custom Ads" refers to ads that are specifically tailored to a user's individual needs, interests, and even emotions.

[1354] 9. "Automatic generation means" refers to a system in which advertisements are automatically generated by a machine based on pre-set rules or algorithms.

[1355] 10. "Right timing" refers to the optimal time for ad delivery based on a user's behavioral history and emotional state.

[1356] 11. "Device" means the device used by a User to receive and display advertisements.

[1357] 12. "Means for evaluating and optimizing effectiveness" refers to a system for evaluating the effectiveness of delivered advertisements and making adjustments to further improve their effectiveness.

[1358] Based on these definitions, the features of the present invention and the terms thereof can be clearly understood.

[1359] System Overview

[1360] This system uses word-of-mouth and feedback data collected from users in real time, and through sentiment analysis, automatically generates and delivers custom ads based on the user's interests, preferences, and emotions. It also evaluates and optimizes the effectiveness of ads based on the feedback.

[1361] Hardware and software used

[1362] Hardware: Servers, user devices (smartphones and tablets), cameras, sensors

[1363] Software: Natural language processing engines (e.g., TextBlob), generative AI engines (e.g., the Transformers library), sentiment analysis engines, marketing automation tools

[1364] Program Processing Overview

[1365] 1. Data Collection:

[1366] When users post reviews or feedback on their smartphones or tablets, the data is sent to the server in real time, including text data, image data, and audio data.

[1367] 2. Data Analysis:

[1368] The server analyzes the collected data using a natural language processing engine (TextBlob) and a sentiment analysis engine (Transformers library), extracting keywords from the text and classifying sentiment as positive, negative, or neutral.

[1369] 3. Ad generation:

[1370] Based on the analysis results, the generative AI engine automatically generates custom ads tailored to the user's interests, preferences, and emotions. For example, if a user posts positive feedback, the ad copy will be tailored to that emotion.

[1371] 4. Advertisement Delivery:

[1372] Custom ads are delivered to users' devices at optimal times via marketing automation tools, which are determined based on users' behavioral history and emotional data.

[1373] 5. Feedback collection and optimization:

[1374] After the ad is delivered, the user's response data (clicks, skips, etc.) is sent back to the server. The server analyzes this data and evaluates the effectiveness of the ad. Based on the evaluation results, the generation AI engine and sentiment analysis engine will reflect this in the next ad generation.

[1375] Specific examples

[1376] Example 1: Generating ads in response to positive reviews

[1377] When a user posts feedback such as "I love the new lipstick," the sentiment analysis engine determines this as a positive emotion. The generative AI engine generates advertising copy such as "Perfect for you! Try our new lipstick color!" and delivers it to the user's device at the appropriate time.

[1378] Prompt Sentence Examples

[1379] "User posted feedback: 'I love my new lipstick.' Analyze it."

[1380] Example 2: Generating ads in response to negative reviews

[1381] When a user posts feedback such as "This perfume was a little too strong," the sentiment analysis engine determines this as a negative sentiment. The generative AI engine generates advertising copy such as "Great deals! Popular products at special prices!" and delivers it to the user's device at the appropriate time.

[1382] In this way, a system is realized that delivers advanced advertisements based on real-time user emotional data, maximizing advertising effectiveness.

[1383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1384] Step 1:

[1385] Users post reviews and feedback on their smartphones or tablets. This generates text data, image data, and audio data. The user's device sends this data to the server in real time. The input is the reviews and feedback data, and the output is the data sent to the server.

[1386] Step 2:

[1387] The server inputs the received word-of-mouth and feedback data into a natural language processing engine (e.g., TextBlob) and analyzes the text data. Through analysis, keywords within the text are extracted and the user's interests and preferences are determined. The input is the word-of-mouth and feedback text data, and the output is the extracted keywords and data on interests and preferences.

[1388] Step 3:

[1389] The server inputs the extracted keywords, interests, and preference data into a sentiment analysis engine (e.g., the Transformers library) to classify the user's sentiment into positive, negative, or neutral. The input is keywords and interest and preference data, and the output is the sentiment classification result.

[1390] Step 4:

[1391] The server inputs the sentiment classification results into a generative AI engine to automatically generate custom ads based on the user's interests, preferences, and emotions. The generative AI engine uses a deep learning model to generate ad copy. The input is the sentiment classification results, and the output is the generated custom ad.

[1392] Step 5:

[1393] The server delivers the generated custom ads to user devices at the appropriate time via a marketing automation tool. The delivery timing is determined based on the user's behavioral history and emotional data. The input is the generated custom ads and delivery timing data, and the output is the delivery of the ads to the user devices.

[1394] Step 6:

[1395] The user reacts to the delivered advertisement, for example, by clicking or skipping the advertisement. This behavioral data is sent from the terminal to the server. The input is the user's behavioral data regarding the advertisement, and the output is the behavioral data sent to the server.

[1396] Step 7:

[1397] The server analyzes user behavior data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generation AI engine and sentiment analysis engine reflect them in the generation of the next advertisement. This process makes it possible to optimize the content of the advertisement and its distribution strategy. The input is user behavior data and advertisement effectiveness evaluation data, and the output is an optimized advertisement generation algorithm.

[1398] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1399] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1400] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1401] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1402] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1403] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1404] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1405] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1406] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1407] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1408] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1409] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1410] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1411] 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.

[1412] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1413] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1414] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1415] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1416] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1417] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1418] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1419] The following is further disclosed regarding the above embodiment.

[1420] (Claim 1)

[1421] A means of collecting real-time reviews or feedback data from users; and

[1422] A generative AI engine that analyzes collected data and identifies user interests and preferences;

[1423] means for automatically generating custom advertisements based on identified interests and preferences;

[1424] means for delivering the generated custom advertisement to a user device;

[1425] After the ads are delivered, we collect feedback from users again to evaluate and optimize the effectiveness of the ads.

[1426] A system including:

[1427] (Claim 2)

[1428] The system of claim 1 , wherein the word-of-mouth or feedback data is analyzed using natural language processing.

[1429] (Claim 3)

[1430] 10. The system of claim 1, wherein the generative AI engine uses a deep learning model to generate custom advertisements.

[1431] (Claim 4)

[1432] 2. The system according to claim 1, further comprising means for collecting user behavior data based on the delivered advertisements and automatically optimizing the content and delivery strategy of the advertisements based on the collected data.

[1433] "Example 1"

[1434] (Claim 1)

[1435] a means of collecting real-time word-of-mouth or feedback data from user devices;

[1436] A means of analyzing the collected data using a natural language processing engine to identify users' interests and preferences;

[1437] a means for inputting prompts into a generative AI engine based on identified interests and preferences to automatically generate custom advertisements;

[1438] A means for delivering the generated custom advertisements to user devices through a marketing automation tool;

[1439] A means of collecting feedback data from users after advertisement delivery to evaluate and optimize the effectiveness of advertisements;

[1440] A system including:

[1441] (Claim 2)

[1442] The system of claim 1 , wherein the word-of-mouth or feedback data is analyzed using natural language processing.

[1443] (Claim 3)

[1444] 10. The system of claim 1, wherein the generative AI engine uses a machine learning model to generate custom advertisements.

[1445] "Application Example 1"

[1446] (Claim 1)

[1447] A means of collecting real-time reviews or feedback data from users; and

[1448] A generative AI engine that analyzes collected data and identifies user interests and preferences;

[1449] a means for automatically generating customized advertisements based on the identified interests and preferences, and using a prompt to create generated advertisement copy using a generative AI model;

[1450] A means for delivering the generated custom advertisements to the user's device at the optimal timing based on the user's behavioral data;

[1451] After the ads are delivered, we collect feedback from users again to evaluate and optimize the effectiveness of the ads.

[1452] A system including:

[1453] (Claim 2)

[1454] The system of claim 1 , wherein the word-of-mouth or feedback data is analyzed using natural language processing.

[1455] (Claim 3)

[1456] 10. The system of claim 1, wherein the generative AI engine uses a deep learning model to generate custom advertisements.

[1457] "Example 2: Combining Emotion Engines"

[1458] (Claim 1)

[1459] A means of collecting real-time reviews or feedback data from users; and

[1460] A means of analyzing the collected data using natural language processing and sentiment analysis engines to identify users' interests and preferences;

[1461] a generative AI engine that automatically generates custom ads based on identified interests, preferences, and emotions;

[1462] A means to deliver the generated custom ads to user devices and optimize the timing and frequency of delivery;

[1463] After the advertisement is delivered, a means of collecting feedback data from users again to evaluate and optimize the effectiveness of the advertisement;

[1464] A system including:

[1465] (Claim 2)

[1466] The system of claim 1 , wherein the word-of-mouth or feedback data is analyzed using natural language processing and an emotion engine.

[1467] (Claim 3)

[1468] 10. The system of claim 1, wherein the generative AI engine uses a deep learning model to generate custom advertisements.

[1469] "Application example 2 when combining emotion engines"

[1470] (Claim 1)

[1471] A means of collecting real-time reviews or feedback data from users; and

[1472] A generative AI engine that analyzes collected data and identifies user interests, preferences, and emotions;

[1473] means for automatically generating custom advertisements based on identified interests, preferences and emotions;

[1474] A means for delivering custom advertisements generated at appropriate times based on the results of user sentiment analysis to user devices;

[1475] A means of collecting feedback from users again after ad delivery to evaluate and optimize the effectiveness of the ad;

[1476] A system including:

[1477] (Claim 2)

[1478] The system of claim 1 , wherein the word-of-mouth or feedback data is analyzed using natural language processing.

[1479] (Claim 3)

[1480] 10. The system of claim 1, wherein the generative AI engine uses a deep learning model to generate custom advertisements. [Explanation of symbols]

[1481] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting real-time reviews or feedback data from users; and A generative AI engine that analyzes collected data and identifies user interests and preferences; means for automatically generating custom advertisements based on identified interests and preferences; means for delivering the generated custom advertisement to a user device; After the ads are delivered, we collect feedback from users again to evaluate and optimize the effectiveness of the ads. A system including:

2. The system of claim 1 , wherein the word-of-mouth or feedback data is analyzed using natural language processing.

3. 10. The system of claim 1, wherein the generative AI engine uses a deep learning model to generate custom advertisements.

4. The system according to claim 1, further comprising means for collecting data on user behavior based on the delivered advertisements and automatically optimizing the content and delivery strategy of the advertisements based on the data.

Images