system

Abstract

We provide a system to further improve the quality of advertising messages. [Solution] A system comprising: means for receiving attribute information of a target audience; means for collecting data related to the target audience from the internet; means for analyzing the collected data using natural language processing technology to extract the interests and trends of the target audience; means for generating advertising messages using a generative AI model; means for evaluating multiple generated advertising messages and proposing the optimal advertising message; means for receiving feedback on the proposed advertising message; and means for accumulating the received feedback and improving the generative AI model.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the advertising market, it is difficult to generate an advertising message that quickly and accurately reflects the attributes, preferences, and online trends of the target audience. In addition, in order to efficiently and effectively deploy advertisements while differentiating from competing companies, it is necessary to handle a large amount of data and propose catchy phrases based on the analysis thereof. However, in the current methods, the selection of phrases often relies on intuition or experience, which is one of the factors hindering the improvement of advertising effects. In addition, there is a lack of a mechanism for effectively utilizing feedback to continuously improve the quality of message proposals.

Means for Solving the Problems

[0005] This invention provides a means for receiving attribute information of a target audience and collecting relevant data from the internet. Based on the collected data, it includes means for analyzing the interests and trends of the target audience using natural language processing technology and generating advertising messages using a generative AI model based on this information. Furthermore, it includes means for evaluating multiple generated advertising messages, selecting the optimal one, and proposing it. After the proposal, it receives feedback from the user, accumulates this feedback, and improves the generative AI model based on this feedback, thereby further improving the quality of the advertising messages.

[0006] A "target audience" refers to a group of people who possess specific attributes and preferences and are expected to be recipients of an advertisement or message.

[0007] "Attribute information" refers to information that indicates characteristics of the target audience, such as age, gender, interests, and areas of interest.

[0008] The "Internet" refers to a wide-area information and communication network that connects computer networks around the world and is used as a source of data.

[0009] "Data collection" refers to the process of obtaining information related to the target audience from sources such as the internet.

[0010] "Natural language processing technology" refers to the technology that enables computers to understand and process human language.

[0011] A "generative AI model" refers to a model that uses artificial intelligence technology to generate advertising copy and other content based on new information.

[0012] An "advertising message" refers to the information or content that is conveyed to the recipient in order to achieve a specific purpose.

[0013] "Feedback" refers to user opinions, evaluations, or reactions regarding a proposed advertising message.

[0014] "Accumulation" refers to collecting and storing information and data.

[0015] "Improvement" refers to improving the performance and results of a system or model.

Brief Explanation of Drawings

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

Modes for Carrying Out the Invention

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

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), and the like.

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

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

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

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

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0037] The advertising message generation system according to the present invention is implemented by a server, a terminal, and a user. It begins with the user inputting attribute information of the target audience through the terminal. For example, this includes age group, gender, interests, and regional data. This information is transmitted to the server.

[0038] The server accesses publicly available data sources on the internet to collect data relevant to the target audience. This includes social media posts, online reviews, search trends, and purchase history data. The server retrieves this data via APIs and uses it as foundational data to understand the interests and trends of the target audience.

[0039] The collected data is analyzed on the server using natural language processing techniques. This analysis extracts sentiments and trends that indicate the target audience's interests and preferences. For example, it can identify what interests them and what keywords they frequently use.

[0040] Next, the server utilizes a generative AI model to generate advertising messages based on the extracted information. The generated messages include catchphrases and wording tailored to each target audience. The server then selects the most relevant and effective advertising message from among those generated.

[0041] The server then sends the selected ad message to the device and presents it to the user. The user reviews the multiple ad messages presented and chooses the one that best suits their purpose and context. The user then provides feedback on the selected ad message.

[0042] The server stores the received feedback in a database and uses this feedback to improve the generating AI model. This allows for improved accuracy and effectiveness of future advertising message generation.

[0043] As a concrete example, consider a youth fashion brand running a campaign for a new product. The user enters the target audience attributes as "18-24 years old," "female," "interested in fashion and trends," and "urban area." From the data collected by the server, it generates advertising messages that include keywords such as "eco-friendly" and "casual chic," which are recent trends, and makes suggestions such as "Discover a new you with an environmentally conscious style." In this way, advertising messages that fit the target audience are provided.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user uses a device to input attribute information for the target audience. This includes information such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0047] Step 2:

[0048] Based on the attribute information received by the server, it collects data related to the target audience from publicly available data sources on the internet. The server retrieves data via APIs from sources such as social media posts, online reviews, search trends, and purchase history.

[0049] Step 3:

[0050] The server applies natural language processing techniques to the collected data and analyzes the text data. This identifies sentiments, frequently occurring keywords, and trends that indicate the target audience's interests and preferences.

[0051] Step 4:

[0052] The server generates advertising messages using a generation AI model based on the analysis results. The generated messages include catchy slogans and content tailored to the target audience.

[0053] Step 5:

[0054] The server evaluates the generated advertising messages and selects the most effective and relevant ones. It considers multiple options and prepares them for the user to choose from.

[0055] Step 6:

[0056] The server selects an advertising message and sends it to the user's device, presenting it to them. The user reviews the message and chooses the most suitable option from the provided choices.

[0057] Step 7:

[0058] The system provides feedback to the server regarding the ad messages selected by the user, including their opinions and evaluations.

[0059] Step 8:

[0060] The server stores user feedback in a database and uses this to improve the AI ​​model that generates messages. This allows for improved accuracy and effectiveness in future message generation.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In advertising strategies, there is a need to quickly generate effective promotional messages tailored to the characteristics of the target group and continuously improve them based on the response. However, traditional methods are time-consuming and labor-intensive, and often fail to accurately respond to the interests and preferences of the target group. Therefore, there is a need for a system that generates precisely tailored promotional messages for the target group and incorporates the response as feedback to create even more effective messages.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for receiving characteristic information of a target group, means for collecting information related to the target group from a communication network, and means for analyzing the collected information using language analysis technology to extract the interests and tendencies of the target group. This enables the generation of promotional messages that are optimal for the target group and improvements based on feedback on their effectiveness.

[0066] A "target group" refers to a specific customer segment or market segment to which an advertising or promotional message is intended.

[0067] "Characteristic information" refers to data that includes attributes of the target group, such as age group, gender, interests, and regional information.

[0068] A "communication network" refers to the infrastructure used to collect and transmit data via the internet and various other networks.

[0069] "Information" refers to data collected from various sources related to the target group, including social media posts, online reviews, and search trends.

[0070] "Language analysis technology" refers to methods that use natural language processing techniques to analyze text data and understand and classify its content.

[0071] "Interests and trends" refer to information that indicates what kind of interest a target group shows in a particular topic or product, and what trends exist within that topic.

[0072] A "promotional message" refers to advertising copy or slogans created with the purpose of appealing to a target group and encouraging them to take action regarding a product or service.

[0073] "Response" refers to the evaluation or feedback that the target group gives to the proposed promotional message.

[0074] This invention is an advertising message generation system implemented using a server and a terminal.

[0075] Server: The server operates using programs installed on a cloud service. Upon receiving characteristic information of the target group, the server accesses publicly available data sources on the internet via a communication network. This includes social media APIs, review site APIs, and search engine trend information APIs. The collected information is analyzed by a natural language processing engine running on the server. This engine is used to extract keywords that indicate the interests and trends of the target group.

[0076] Generative AI Model: The server utilizes a generative AI model to generate promotional messages based on extracted keywords and sentiment scores. The generative AI model is built using machine learning libraries and is continuously improved by incorporating historical data and user feedback. By inputting prompts, the model generates specific advertising messages.

[0077] Terminals and Users: Terminals are devices that allow users to view advertising messages through an interface and provide feedback. Users evaluate the proposed promotional messages and provide feedback to the server. This feedback is also stored on the server and used to improve the generating AI model.

[0078] Specific example: As a specific example, if an apparel company were to run a campaign for new eco-friendly fashion items targeting women aged 18-24 living in urban areas, the target information would be "18-24 years old," "female," "fashion, environmental awareness," and "urban area." From the collected data, keywords such as "sustainable," "modal," and "casual chic" would be extracted. By inputting the prompt "Let's find your eco-friendly style" into the generating AI model, a message suitable for the target audience would be generated.

[0079] In this way, the system delivers messages tailored to the specific interests of the target group and enables more refined advertising strategies based on user feedback.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] Users input characteristic information about the target group through their device. This data includes attribute information such as age group, gender, interests, and region. This information is then transmitted from the device to the server.

[0083] Step 2:

[0084] Based on the characteristics information of the target group received, the server accesses publicly available data sources via the communication network to collect relevant information. Specifically, it obtains posts, reviews, and search trends related to the target group through social media APIs, review site APIs, etc. The collected raw data is obtained as output.

[0085] Step 3:

[0086] A natural language processing engine runs on the server and analyzes the collected raw data. Morphological analysis and sentiment analysis are used to extract keywords and sentiment scores that indicate the interests and tendencies of the target group. The input is the collected raw data, and the output is the analyzed topics and keywords.

[0087] Step 4:

[0088] The server uses a generative AI model to generate promotional messages based on the analysis results. It takes prompts that consider keywords and sentiment scores obtained from the analysis as input, and the generative AI model creates advertising messages tailored to each target group. The output is the generated advertising message.

[0089] Step 5:

[0090] The server evaluates the multiple promotional messages generated. Using an evaluation algorithm, it selects messages that are predicted to be highly relevant and effective based on past data. The selected messages are then output.

[0091] Step 6:

[0092] The server sends the selected advertising message to the device and proposes it to the user. The user reviews multiple proposed messages through the device and chooses the one that best suits their purpose and context.

[0093] Step 7:

[0094] Users provide feedback on the promotional messages they have selected. This feedback includes evaluation comments and reasons for their selection. This feedback is sent from the device to the server.

[0095] Step 8:

[0096] The server records user feedback in a database. Based on this, it updates the generative AI model to improve the accuracy and effectiveness of future ad message generation. The output is the improved generative AI model.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] The problem that this invention aims to solve is to present optimal advertising messages to target audiences in real time, based on their individual attributes. Conventional advertising message generation systems can only provide advertisements based on static information, making it difficult to personalize based on dynamic environmental factors and real-time attribute analysis.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for receiving attribute information of the target audience, means for recognizing surrounding environmental information and inferring the age group and gender of the detected people, and means for presenting advertising messages to a visual display device in real time. This enables the real-time presentation of personalized advertising messages that adapt to dynamic environmental changes.

[0102] A "target audience" is a group of people who are targeted to receive a specific advertising message, and it includes attribute information such as age group, gender, interests, and location.

[0103] "Attribute information" refers to a collection of information such as age group, gender, interests, and region, used to identify a target audience and understand their characteristics and interests.

[0104] "Means of collecting data from the internet" refers to technologies that have the ability to obtain information related to a target audience from publicly available data sources.

[0105] "Natural language processing technology" is a technology that uses computers to understand, analyze, and generate responses to human language, and is used for analyzing collected text data.

[0106] A "generative AI model" is an artificial intelligence technology used to generate advertising messages based on collected data.

[0107] An "advertising message" is a collection of information intended to promote a specific product or service and is conveyed to a target audience.

[0108] A "visual display device" refers to a device used to visually present advertising messages to users, such as smart glasses.

[0109] "Means for recognizing surrounding environmental information" refers to technologies that use cameras or other visual display devices to detect and analyze the situation of surrounding objects and people.

[0110] "Feedback" refers to user reactions and evaluations of proposed advertising messages, and the system is improved based on this feedback.

[0111] To implement this invention, a system consisting of a server, a terminal, and a user is required. The system generates and presents advertising messages through several stages, as follows:

[0112] The terminal is a device that receives attribute information of the target audience from the user. This includes, for example, age group, gender, interests, and region. This attribute information is transmitted to the server via the network.

[0113] The server accesses publicly available data sources on the Internet to collect data relevant to the target audience. This data collection is carried out using API technology. The collected data may include social media posts, online reviews, search trends, or purchase history.

[0114] Next, the server uses natural language processing techniques to analyze the collected data. This analysis extracts sentiments and keywords that indicate the target audience's interests and trends. The software used in this process includes libraries for text analysis.

[0115] The generative AI model automatically generates advertising messages based on this extracted information. The generative AI model is used to generate these advertising messages, which are designed to be most relevant to the target audience.

[0116] Furthermore, smart glasses are used to analyze visual information and recognize the surrounding environment. This enables the display of real-time advertisements based on the attributes of the detected individuals.

[0117] Real-time advertising messages are displayed via the visual display device of smart glasses. The displayed messages receive feedback from the user and are sent to the server. This feedback is used to improve the system.

[0118] As a concrete example, if a group of young people is detected in a shopping mall, the smart glasses will display an advertising message informing them of a special sale from a new fashion brand. An example of a prompt message to use would be, "Generate an advertisement highlighting the latest fashion trends for young people."

[0119] In this way, the system enables the delivery of dynamic and highly personalized advertising messages.

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The user enters attribute information of the target audience into the device. Specifically, they fill in information such as age group, gender, interests, and region in a form. This input information becomes the basis for the next processing. The device sends the entered information to the server as digital data.

[0123] Step 2:

[0124] The server accesses publicly available data sources on the internet to collect relevant data based on the attribute information it receives. This process involves using APIs to retrieve data such as social media posts, online reviews, and search trends. The input is attribute information, and the output is the retrieved relevant data.

[0125] Step 3:

[0126] The server analyzes the collected data using natural language processing techniques. Through this analysis, it extracts keywords and sentiments that indicate the target audience's interests and trends. Specifically, it analyzes text data and identifies frequently used keywords. This process yields extracted information indicating interests and trends as output.

[0127] Step 4:

[0128] The server uses a generative AI model to generate advertising messages based on the extracted information. It is given a prompt in the form of, "Generate an advertising message suitable for the target audience based on the extracted keywords," and uses this instruction to construct the advertising content. The generated message is obtained as output.

[0129] Step 5:

[0130] The server recognizes the surrounding environment and estimates the age group and gender of people visually detected using smart glasses. Using visual information from the smart glasses' camera as input, it performs real-time attribute prediction and determines an appropriate advertising message. The output is an optimized advertising message.

[0131] Step 6:

[0132] The server presents optimized advertising messages to the user in real time through the visual display device of the smart glasses. This visually delivers advertisements that are appropriately customized to the target audience. The output is the displayed advertising message.

[0133] Step 7:

[0134] Users provide feedback on suggested ad messages, and this feedback is sent to the server via their device. This feedback is used as input to improve the generating AI model and is stored in a database to improve the accuracy of future ads.

[0135] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0136] By combining the advertising message generation system according to the present invention with an emotion engine, it becomes possible to generate advertising messages that take into account the emotions of the target audience. In this embodiment, the server, terminal, user, and emotion engine play central roles.

[0137] The process begins with users entering target audience attribute information via their devices and sending it to a server. This information may include age, gender, interests, and location. Based on this information, the server collects data relevant to the target audience from publicly available data sources on the internet. This collected data may include social media posts, online reviews, search trends, and purchase history.

[0138] On the server, natural language processing technology is used to perform text analysis on the collected data. This analysis extracts frequently occurring keywords and trends that indicate the emotions and preferences of the target audience. In addition, an emotion engine analyzes the user's state and acquires emotional data.

[0139] Next, the server utilizes a generative AI model to generate advertising messages based on the analysis results and the output of the emotion engine. Each message is structured to reflect the emotions of the target audience. From the generated set of advertising messages, the server selects the message optimized for the emotion data and proposes it effectively.

[0140] The server sends the selected advertising message to the device and displays it to the user. The user can review the message they received and provide feedback. Furthermore, sentiment data and feedback information are stored on the server and used to improve the AI ​​model for generating messages.

[0141] For example, when running a campaign for a youth fashion brand, the user's emotional engine might recognize feelings of excitement and anticipation. By incorporating this data into the analysis, emotionally appealing messages such as "Let's enjoy each day even more positively with a new style!" are generated and selected. This results in advertising messages that reflect the emotional state of the target audience.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The user enters attribute information for the target audience using their device. This attribute information includes basic characteristics such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0145] Step 2:

[0146] Based on the attribute information received by the server, data relevant to the target audience is collected from publicly available data sources on the internet. This collection includes obtaining social media posts, online reviews, search trends, and purchase history via APIs.

[0147] Step 3:

[0148] The server uses an emotion engine to collect user emotion data. The emotion engine reads emotions from the user's facial expressions and tone of voice as they input information. This data is used to generate advertising messages.

[0149] Step 4:

[0150] The server analyzes target audience data and sentiment data collected using natural language processing technology. This analysis extracts information indicating the target audience's interests, trends, and emotional state, and extracts keywords optimized for that emotional state.

[0151] Step 5:

[0152] The server uses an AI model to generate advertising messages based on the analysis results. Because the generated messages take sentiment data into account, they are tailored to the emotions of the target audience.

[0153] Step 6:

[0154] The server evaluates multiple generated advertising messages and selects the optimal one. This evaluation process considers sentiment relevance and predicted effect as selection criteria.

[0155] Step 7:

[0156] The server selects an advertising message and sends it to the user's device for display. The user reviews the message and chooses the one that best suits the advertising campaign's objectives.

[0157] Step 8:

[0158] The system feeds back user feedback and evaluations of selected ad messages to the server. It also collects new user sentiment data.

[0159] Step 9:

[0160] The server collects feedback and sentiment data, which is used to improve the generating AI model. This increases the accuracy of future ad message generation.

[0161] (Example 2)

[0162] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0163] Current ad generation systems struggle to create messages that adequately consider the emotions and preferences of target audiences, making it difficult to develop effective advertising strategies. Furthermore, there is a lack of mechanisms to effectively utilize feedback on generated messages and appropriately improve the AI ​​model for message generation.

[0164] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0165] In this invention, the server includes means for receiving attribute information of the target audience, means for acquiring relevant information from a data network, means for analyzing the information using natural language processing technology, means for analyzing the user's emotions using emotion analysis means, means for generating ad copy using a generative AI model, means for evaluating and selecting ad copy, and means for receiving responses and improving the model. This enables the efficient generation of ad messages that are suitable for the emotions and preferences of the target audience, and the realization of an effective advertising strategy based on them.

[0166] A "target audience" refers to a group of people who have specific attributes (age, gender, interests, location, etc.) and are the recipients of an advertisement or message.

[0167] A "data network" refers to a distributed information system, including the internet, used for collecting and transmitting information.

[0168] "Natural language processing technology" refers to a set of technologies for computers to understand and generate human language, including text analysis and sentiment analysis.

[0169] "Emotional analysis means" refers to methods or devices that analyze a user's psychological state and emotions based on data and evaluate them numerically or categorically.

[0170] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates new content or messages based on input data.

[0171] A "prompt" refers to text input to a generative AI model that contains instructions or questions designed to elicit a specific output.

[0172] "Ad copy" refers to text messages designed to promote a product or service to a specific target audience.

[0173] "Responses" refer to user reactions and feedback information regarding the generated advertising messages.

[0174] This invention provides a means for generating effective advertisements based on the emotions and preferences of a target audience in an advertising message generation system.

[0175] First, the user uses their device to input attribute information of the target audience. This input information includes age, gender, interests, and location. The entered information is sent from the device to the server. After receiving this information, the server initiates a process to collect relevant data via the data network. In this process, it accesses various data sources such as social media posts, online reviews, and purchase history.

[0176] The server analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy). The purpose of this analysis is to extract key keywords and trends that indicate the interests and tendencies of the target audience. In addition to this analysis, the server uses sentiment analysis tools to understand the user's current emotional state. For example, it infers what emotions the user is experiencing based on user input and data from terminal sensors.

[0177] Next, the server uses a generative AI model to create a prompt, and then generates ad copy based on that. The generated ad copy is then adjusted to match the sentiment of the target audience. For example, in an advertising campaign about youth fashion, the server might generate a prompt such as, "Youth Fashion Ads: Create Messages that Convey Excitement."

[0178] Multiple generated ad copy is evaluated by the server, and the best one is selected. The server sends the selected ad copy to the device and displays it to the user. The user responds to the received ad copy through the device, and this response is stored on the server as feedback. This feedback information is used to improve the generation AI model and is reflected in the new ad copy generation process.

[0179] In this way, the system of the present invention can generate advertising messages that accurately reflect the emotions and preferences of the target audience, thereby maximizing the effectiveness of the advertising.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The user uses a device to input attribute information of the target audience. This attribute information includes age, gender, interests, and location. This information is entered by the user into the device and sent as input data to the server. As output, a dataset of attribute information is generated.

[0183] Step 2:

[0184] The server retrieves relevant information from the data network based on the received attribute information. At this stage, it collects data relevant to the target audience from data sources such as social media, online reviews, and purchase history. The input is attribute information, and the output is the collected relevant dataset. This process includes data retrieval using specific APIs.

[0185] Step 3:

[0186] The server uses natural language processing techniques to analyze the collected data. Specifically, it uses Python's NLTK and spaCy libraries to analyze text data and extract keywords and trends that indicate the target audience's sentiments and interests. The input is the collected dataset, and the output is information about keywords and sentiments obtained through the analysis.

[0187] Step 4:

[0188] The server analyzes the user's emotional state using emotion analysis tools. It executes a specific algorithm to calculate an emotion score based on past data and sensor information entered by the user. The input is the user's past data, and the output is the user's emotion score.

[0189] Step 5:

[0190] The server utilizes a generative AI model to create prompts and generate ad copy. These prompts include specific examples such as "Youth-oriented fashion advertising: Create a message that conveys excitement." By inputting prompts into the model, the corresponding ad copy is generated and output.

[0191] Step 6:

[0192] The server evaluates multiple generated ad copy and selects the most suitable one. Here, an evaluation algorithm based on sentiment scores is applied to determine the selected message. The input consists of multiple generated ad copy and their sentiment scores, while the output is the selected ad copy.

[0193] Step 7:

[0194] The server sends the selected ad copy to the device and displays it to the user. The user uses the device to respond to the displayed ad copy. The input is the selected ad copy, and the output is the user's response.

[0195] Step 8:

[0196] The user's response is sent to the server as feedback information, which the server stores. Based on the response, the parameters of the AI ​​model are adjusted as needed. As a result, the model's performance is improved, and feedback information is obtained as output that can be used to improve future ad generation.

[0197] (Application Example 2)

[0198] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0199] While there is a need to generate advertising messages that appropriately consider the emotions of the target audience, conventional methods make it difficult to create messages that adequately reflect their emotional state. Furthermore, there is a lack of feedback mechanisms to measure the effectiveness of the generated messages and to continuously improve them. As a result, there is a problem in providing advertising messages that effectively appeal to the target audience.

[0200] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0201] In this invention, the server includes means for receiving attribute information of the target audience, means for analyzing the emotional state of the target audience using an emotion engine, and means for generating advertising messages based on the emotional state of the target audience using a generative AI model. This enables the generation of effective advertising messages that take into account the emotions of the target audience, and their continuous improvement.

[0202] A "target audience" is a group of consumers designated as the recipients of advertisements and information for a specific product or service.

[0203] "Attribute information" refers to characteristics related to the target audience, and includes data such as age, gender, interests, and geographical information.

[0204] "Collecting data from the internet" refers to the process of obtaining relevant information from data sources that are publicly available online.

[0205] "Natural language processing technology" refers to the technology that enables computers to understand, process, and generate human language.

[0206] An "emotion engine" is a technology or system for analyzing and evaluating the emotional state of users or target audiences.

[0207] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text or other forms of data.

[0208] "Feedback" refers to information about evaluations and reactions to generated advertising messages, and is data used to improve models and systems.

[0209] This invention provides a system for generating advertising messages that take into account the emotions of a target audience. The server receives attribute information of the target audience from the user and collects relevant data from the internet. This data includes social media posts, online reviews, search trends, and purchase history.

[0210] The server analyzes the collected data using natural language processing techniques to extract the emotions and preferences of the target audience. This analysis utilizes Python and the natural language processing library NLTK. Furthermore, the server uses an emotion engine to analyze the emotional state of users and the target audience in detail.

[0211] Based on the analysis results and sentiment data, a generative AI model creates advertising messages. This model uses TENSORFLOW® to generate messages that match the sentiments of the target audience. The server then suggests the most effective message from among those generated.

[0212] Users can view suggested advertising messages through their devices and provide feedback. This feedback is sent to the server and used to improve the AI ​​model that generates the ads.

[0213] As a concrete example, consider a fashion advertisement targeting women in their 20s who are sensitive to new trends. In this case, an example prompt phrase would be "Women in their 20s, sensitive to new trends, interested in Scandinavian style," and the AI ​​model could generate an emotionally appealing message such as "Let's enjoy each day even more positively with a new style!"

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] Users input attribute information, interests, and location information of their target audience via their device and send it to the server. This inputs data about the attributes of the target audience.

[0217] Step 2:

[0218] The server collects data related to the target audience from the internet based on the attribute information it receives. This data includes social media posts, online reviews, search trends, and purchase history. This process outputs data about the target audience's interests and trends.

[0219] Step 3:

[0220] The server uses natural language processing techniques to analyze the collected data. Through this analysis, it extracts frequently occurring keywords and current trends, and identifies the sentiments and preferences of the target audience. As a result, analytical information, including sentiment data, is output.

[0221] Step 4:

[0222] The server uses an emotion engine to analyze the emotional state of the target audience set by the user. Based on the input text data, the emotion engine generates an emotion score and outputs a detailed description of that emotional state.

[0223] Step 5:

[0224] The server generates advertising messages using a generative AI model based on the collected data and emotional states obtained from the emotion engine. Python and TensorFlow are used here to output emotionally appealing messages.

[0225] Step 6:

[0226] The server evaluates multiple generated ad messages and selects and proposes the message optimized for the target audience's emotional state. The proposed ad message is then displayed on the device.

[0227] Step 7:

[0228] Users review the suggested advertising messages on their devices and provide feedback on their effectiveness and impression. This feedback generates data to evaluate the message's effectiveness.

[0229] Step 8:

[0230] The server stores user feedback and sentiment data, which is used to improve the generative AI model. This process enhances the model's performance, and these improvements are reflected in future advertising message generation.

[0231] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0232] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0233] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0234] [Second Embodiment]

[0235] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0236] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0237] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0238] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0239] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0240] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0241] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0242] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0243] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0244] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0245] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0246] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0247] The advertising message generation system according to the present invention is implemented by a server, a terminal, and a user. It begins with the user inputting attribute information of the target audience through the terminal. For example, this includes age group, gender, interests, and regional data. This information is transmitted to the server.

[0248] The server accesses publicly available data sources on the internet to collect data relevant to the target audience. This includes social media posts, online reviews, search trends, and purchase history data. The server retrieves this data via APIs and uses it as foundational data to understand the interests and trends of the target audience.

[0249] The collected data is analyzed on the server using natural language processing techniques. This analysis extracts sentiments and trends that indicate the target audience's interests and preferences. For example, it can identify what interests them and what keywords they frequently use.

[0250] Next, the server utilizes a generative AI model to generate advertising messages based on the extracted information. The generated messages include catchphrases and wording tailored to each target audience. The server then selects the most relevant and effective advertising message from among those generated.

[0251] The server then sends the selected ad message to the device and presents it to the user. The user reviews the multiple ad messages presented and chooses the one that best suits their purpose and context. The user then provides feedback on the selected ad message.

[0252] The server stores the received feedback in a database and uses this feedback to improve the generating AI model. This allows for improved accuracy and effectiveness of future advertising message generation.

[0253] As a concrete example, consider a youth fashion brand running a campaign for a new product. The user enters the target audience attributes as "18-24 years old," "female," "interested in fashion and trends," and "urban area." From the data collected by the server, it generates advertising messages that include keywords such as "eco-friendly" and "casual chic," which are recent trends, and makes suggestions such as "Discover a new you with an environmentally conscious style." In this way, advertising messages that fit the target audience are provided.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The user uses a device to input attribute information for the target audience. This includes information such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0257] Step 2:

[0258] Based on the attribute information received by the server, it collects data related to the target audience from publicly available data sources on the internet. The server retrieves data via APIs from sources such as social media posts, online reviews, search trends, and purchase history.

[0259] Step 3:

[0260] The server applies natural language processing techniques to the collected data and analyzes the text data. This identifies sentiments, frequently occurring keywords, and trends that indicate the target audience's interests and preferences.

[0261] Step 4:

[0262] The server generates advertising messages using a generation AI model based on the analysis results. The generated messages include catchy slogans and content tailored to the target audience.

[0263] Step 5:

[0264] The server evaluates the generated advertising messages and selects the most effective and relevant ones. It considers multiple options and prepares them for the user to choose from.

[0265] Step 6:

[0266] The server selects an advertising message and sends it to the user's device, presenting it to them. The user reviews the message and chooses the most suitable option from the provided choices.

[0267] Step 7:

[0268] The system provides feedback to the server regarding the ad messages selected by the user, including their opinions and evaluations.

[0269] Step 8:

[0270] The server stores user feedback in a database and uses this to improve the AI ​​model that generates messages. This allows for improved accuracy and effectiveness in future message generation.

[0271] (Example 1)

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

[0273] In advertising strategies, there is a need to quickly generate effective promotional messages tailored to the characteristics of the target group and continuously improve them based on the response. However, traditional methods are time-consuming and labor-intensive, and often fail to accurately respond to the interests and preferences of the target group. Therefore, there is a need for a system that generates precisely tailored promotional messages for the target group and incorporates the response as feedback to create even more effective messages.

[0274] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0275] In this invention, the server includes means for receiving characteristic information of a target group, means for collecting information related to the target group from a communication network, and means for analyzing the collected information using language analysis technology to extract the interests and tendencies of the target group. This enables the generation of promotional messages that are optimal for the target group and improvements based on feedback on their effectiveness.

[0276] A "target group" refers to a specific customer segment or market segment to which an advertising or promotional message is intended.

[0277] "Characteristic information" refers to data that includes attributes of the target group, such as age group, gender, interests, and regional information.

[0278] A "communication network" refers to the infrastructure used to collect and transmit data via the internet and various other networks.

[0279] "Information" refers to data collected from various sources related to the target group, including social media posts, online reviews, and search trends.

[0280] "Language analysis technology" refers to methods that use natural language processing techniques to analyze text data and understand and classify its content.

[0281] "Interests and trends" refers to information indicating how the target group shows interest in specific topics or products and what trends exist.

[0282] "Promotion message" refers to advertising texts or catchphrases created for the purpose of appealing to the target group about products or services and prompting actions.

[0283] "Reaction" refers to the evaluation or feedback shown by the target group towards the proposed promotion message.

[0284] This invention is an advertising message generation system implemented using a server and a terminal.

[0285] Server: The server operates using a program installed on cloud services. When receiving the characteristic information of the target group, the server accesses public data sources on the Internet via a communication network. This includes APIs of social media, review sites, search engine trend information APIs, etc. The collected information is analyzed by a natural language processing engine running on the server. This engine is used to extract keywords indicating the interests and trends of the target group.

[0286] Generative AI model: The server utilizes a generative AI model to generate promotion messages based on the extracted keywords and sentiment scores. The generative AI model is constructed using a machine learning library and is continuously improved by reflecting past data and feedback from users. By inputting a prompt text to this model, a specific advertising message is generated.

[0287] Terminals and Users: Terminals are devices that allow users to view advertising messages through an interface and provide feedback. Users evaluate the proposed promotional messages and provide feedback to the server. This feedback is also stored on the server and used to improve the generating AI model.

[0288] Specific example: As a specific example, if an apparel company were to run a campaign for new eco-friendly fashion items targeting women aged 18-24 living in urban areas, the target information would be "18-24 years old," "female," "fashion, environmental awareness," and "urban area." From the collected data, keywords such as "sustainable," "modal," and "casual chic" would be extracted. By inputting the prompt "Let's find your eco-friendly style" into the generating AI model, a message suitable for the target audience would be generated.

[0289] In this way, the system delivers messages tailored to the specific interests of the target group and enables more refined advertising strategies based on user feedback.

[0290] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0291] Step 1:

[0292] Users input characteristic information about the target group through their device. This data includes attribute information such as age group, gender, interests, and region. This information is then transmitted from the device to the server.

[0293] Step 2:

[0294] Based on the characteristics information of the target group received, the server accesses publicly available data sources via the communication network to collect relevant information. Specifically, it obtains posts, reviews, and search trends related to the target group through social media APIs, review site APIs, etc. The collected raw data is obtained as output.

[0295] Step 3:

[0296] A natural language processing engine runs on the server and analyzes the collected raw data. Morphological analysis and sentiment analysis are used to extract keywords and sentiment scores that indicate the interests and tendencies of the target group. The input is the collected raw data, and the output is the analyzed topics and keywords.

[0297] Step 4:

[0298] The server uses a generative AI model to generate promotional messages based on the analysis results. It takes prompts that consider keywords and sentiment scores obtained from the analysis as input, and the generative AI model creates advertising messages tailored to each target group. The output is the generated advertising message.

[0299] Step 5:

[0300] The server evaluates the multiple promotional messages generated. Using an evaluation algorithm, it selects messages that are predicted to be highly relevant and effective based on past data. The selected messages are then output.

[0301] Step 6:

[0302] The server sends the selected advertising message to the device and proposes it to the user. The user reviews multiple proposed messages through the device and chooses the one that best suits their purpose and context.

[0303] Step 7:

[0304] The user provides feedback on the promotion message they selected. The feedback includes evaluation comments and reasons for selection. This feedback is sent from the terminal to the server.

[0305] Step 8:

[0306] The server records the feedback received from the user in the database. Based on this, the generated AI model is updated to improve the accuracy and effectiveness of the next advertisement message generation. The output is an improved generated AI model.

[0307] (Application Example 1)

[0308] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] The problem to be solved by the present invention is to present an optimal advertisement message based on individual attributes to the target audience in real time. In the conventional advertisement message generation system, only advertisements based on static information can be provided, and it is difficult to achieve individualization based on dynamic environmental factors and real-time attribute analysis.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0311] In this invention, the server includes means for receiving the attribute information of the target audience, means for recognizing the surrounding environmental information and inferring the age group and gender of the detected people, and means for presenting an advertisement message to the visual display device in real time. This enables the real-time presentation of individualized advertisement messages adapted to dynamic environmental changes.

[0312] The "target audience" is a group of people targeted to convey a specific advertisement message and has attribute information such as age group, gender, interest, and region.

[0313] "Attribute information" refers to a collection of information such as age group, gender, interests, and region, used to identify a target audience and understand their characteristics and interests.

[0314] "Means of collecting data from the internet" refers to technologies that have the ability to obtain information related to a target audience from publicly available data sources.

[0315] "Natural language processing technology" is a technology that uses computers to understand, analyze, and generate responses to human language, and is used for analyzing collected text data.

[0316] A "generative AI model" is an artificial intelligence technology used to generate advertising messages based on collected data.

[0317] An "advertising message" is a collection of information intended to promote a specific product or service and is conveyed to a target audience.

[0318] A "visual display device" refers to a device used to visually present advertising messages to users, such as smart glasses.

[0319] "Means for recognizing surrounding environmental information" refers to technologies that use cameras or other visual display devices to detect and analyze the situation of surrounding objects and people.

[0320] "Feedback" refers to user reactions and evaluations of proposed advertising messages, and the system is improved based on this feedback.

[0321] To implement this invention, a system consisting of a server, a terminal, and a user is required. The system generates and presents advertising messages through several stages, as follows:

[0322] The terminal is a device that receives attribute information of the target audience from the user. This includes, for example, age group, gender, interests, and region. This attribute information is transmitted to the server via the network.

[0323] The server accesses publicly available data sources on the Internet to collect data relevant to the target audience. This data collection is carried out using API technology. The collected data may include social media posts, online reviews, search trends, or purchase history.

[0324] Next, the server uses natural language processing techniques to analyze the collected data. This analysis extracts sentiments and keywords that indicate the target audience's interests and trends. The software used in this process includes libraries for text analysis.

[0325] The generative AI model automatically generates advertising messages based on this extracted information. The generative AI model is used to generate these advertising messages, which are designed to be most relevant to the target audience.

[0326] Furthermore, smart glasses are used to analyze visual information and recognize the surrounding environment. This enables the display of real-time advertisements based on the attributes of the detected individuals.

[0327] Real-time advertising messages are displayed via the visual display device of smart glasses. The displayed messages receive feedback from the user and are sent to the server. This feedback is used to improve the system.

[0328] As a concrete example, if a group of young people is detected in a shopping mall, the smart glasses will display an advertising message informing them of a special sale from a new fashion brand. An example of a prompt message to use would be, "Generate an advertisement highlighting the latest fashion trends for young people."

[0329] In this way, the system enables the delivery of dynamic and highly personalized advertising messages.

[0330] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0331] Step 1:

[0332] The user enters attribute information of the target audience into the device. Specifically, they fill in information such as age group, gender, interests, and region in a form. This input information becomes the basis for the next processing. The device sends the entered information to the server as digital data.

[0333] Step 2:

[0334] The server accesses publicly available data sources on the internet to collect relevant data based on the attribute information it receives. This process involves using APIs to retrieve data such as social media posts, online reviews, and search trends. The input is attribute information, and the output is the retrieved relevant data.

[0335] Step 3:

[0336] The server analyzes the collected data using natural language processing techniques. Through this analysis, it extracts keywords and sentiments that indicate the target audience's interests and trends. Specifically, it analyzes text data and identifies frequently used keywords. This process yields extracted information indicating interests and trends as output.

[0337] Step 4:

[0338] The server uses a generative AI model to generate advertising messages based on the extracted information. It is given a prompt in the form of, "Generate an advertising message suitable for the target audience based on the extracted keywords," and uses this instruction to construct the advertising content. The generated message is obtained as output.

[0339] Step 5:

[0340] The server recognizes the surrounding environment and estimates the age group and gender of people visually detected using smart glasses. Using visual information from the smart glasses' camera as input, it performs real-time attribute prediction and determines an appropriate advertising message. The output is an optimized advertising message.

[0341] Step 6:

[0342] The server presents optimized advertising messages to the user in real time through the visual display device of the smart glasses. This visually delivers advertisements that are appropriately customized to the target audience. The output is the displayed advertising message.

[0343] Step 7:

[0344] Users provide feedback on suggested ad messages, and this feedback is sent to the server via their device. This feedback is used as input to improve the generating AI model and is stored in a database to improve the accuracy of future ads.

[0345] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0346] By combining the advertising message generation system according to the present invention with an emotion engine, it becomes possible to generate advertising messages that take into account the emotions of the target audience. In this embodiment, the server, terminal, user, and emotion engine play central roles.

[0347] The process begins with users entering target audience attribute information via their devices and sending it to a server. This information may include age, gender, interests, and location. Based on this information, the server collects data relevant to the target audience from publicly available data sources on the internet. This collected data may include social media posts, online reviews, search trends, and purchase history.

[0348] On the server, natural language processing technology is used to perform text analysis on the collected data. This analysis extracts frequently occurring keywords and trends that indicate the emotions and preferences of the target audience. In addition, an emotion engine analyzes the user's state and acquires emotional data.

[0349] Next, the server utilizes a generative AI model to generate advertising messages based on the analysis results and the output of the emotion engine. Each message is structured to reflect the emotions of the target audience. From the generated set of advertising messages, the server selects the message optimized for the emotion data and proposes it effectively.

[0350] The server sends the selected advertising message to the device and displays it to the user. The user can review the message they received and provide feedback. Furthermore, sentiment data and feedback information are stored on the server and used to improve the AI ​​model for generating messages.

[0351] For example, when running a campaign for a youth fashion brand, the user's emotional engine might recognize feelings of excitement and anticipation. By incorporating this data into the analysis, emotionally appealing messages such as "Let's enjoy each day even more positively with a new style!" are generated and selected. This results in advertising messages that reflect the emotional state of the target audience.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The user enters attribute information for the target audience using their device. This attribute information includes basic characteristics such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0355] Step 2:

[0356] Based on the attribute information received by the server, data relevant to the target audience is collected from publicly available data sources on the internet. This collection includes obtaining social media posts, online reviews, search trends, and purchase history via APIs.

[0357] Step 3:

[0358] The server uses an emotion engine to collect user emotion data. The emotion engine reads emotions from the user's facial expressions and tone of voice as they input information. This data is used to generate advertising messages.

[0359] Step 4:

[0360] The server analyzes target audience data and sentiment data collected using natural language processing technology. This analysis extracts information indicating the target audience's interests, trends, and emotional state, and extracts keywords optimized for that emotional state.

[0361] Step 5:

[0362] The server uses an AI model to generate advertising messages based on the analysis results. Because the generated messages take sentiment data into account, they are tailored to the emotions of the target audience.

[0363] Step 6:

[0364] The server evaluates multiple generated advertising messages and selects the optimal one. This evaluation process considers sentiment relevance and predicted effect as selection criteria.

[0365] Step 7:

[0366] The server selects an advertising message and sends it to the user's device for display. The user reviews the message and chooses the one that best suits the advertising campaign's objectives.

[0367] Step 8:

[0368] The system feeds back user feedback and evaluations of selected ad messages to the server. It also collects new user sentiment data.

[0369] Step 9:

[0370] The server collects feedback and sentiment data, which is used to improve the generating AI model. This increases the accuracy of future ad message generation.

[0371] (Example 2)

[0372] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0373] Current ad generation systems struggle to create messages that adequately consider the emotions and preferences of target audiences, making it difficult to develop effective advertising strategies. Furthermore, there is a lack of mechanisms to effectively utilize feedback on generated messages and appropriately improve the AI ​​model for message generation.

[0374] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0375] In this invention, the server includes means for receiving attribute information of the target audience, means for acquiring relevant information from a data network, means for analyzing the information using natural language processing technology, means for analyzing the user's emotions using emotion analysis means, means for generating ad copy using a generative AI model, means for evaluating and selecting ad copy, and means for receiving responses and improving the model. This enables the efficient generation of ad messages that are suitable for the emotions and preferences of the target audience, and the realization of an effective advertising strategy based on them.

[0376] A "target audience" refers to a group of people who have specific attributes (age, gender, interests, location, etc.) and are the recipients of an advertisement or message.

[0377] A "data network" refers to a distributed information system, including the internet, used for collecting and transmitting information.

[0378] "Natural language processing technology" refers to a set of technologies for computers to understand and generate human language, including text analysis and sentiment analysis.

[0379] "Emotional analysis means" refers to methods or devices that analyze a user's psychological state and emotions based on data and evaluate them numerically or categorically.

[0380] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates new content or messages based on input data.

[0381] A "prompt" refers to text input to a generative AI model that contains instructions or questions designed to elicit a specific output.

[0382] "Ad copy" refers to text messages designed to promote a product or service to a specific target audience.

[0383] "Responses" refer to user reactions and feedback information regarding the generated advertising messages.

[0384] This invention provides a means for generating effective advertisements based on the emotions and preferences of a target audience in an advertising message generation system.

[0385] First, the user uses their device to input attribute information of the target audience. This input information includes age, gender, interests, and location. The entered information is sent from the device to the server. After receiving this information, the server initiates a process to collect relevant data via the data network. In this process, it accesses various data sources such as social media posts, online reviews, and purchase history.

[0386] The server analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy). The purpose of this analysis is to extract key keywords and trends that indicate the interests and tendencies of the target audience. In addition to this analysis, the server uses sentiment analysis tools to understand the user's current emotional state. For example, it infers what emotions the user is experiencing based on user input and data from terminal sensors.

[0387] Next, the server uses a generative AI model to create a prompt, and then generates ad copy based on that. The generated ad copy is then adjusted to match the sentiment of the target audience. For example, in an advertising campaign about youth fashion, the server might generate a prompt such as, "Youth Fashion Ads: Create Messages that Convey Excitement."

[0388] Multiple generated ad copy is evaluated by the server, and the best one is selected. The server sends the selected ad copy to the device and displays it to the user. The user responds to the received ad copy through the device, and this response is stored on the server as feedback. This feedback information is used to improve the generation AI model and is reflected in the new ad copy generation process.

[0389] In this way, the system of the present invention can generate advertising messages that accurately reflect the emotions and preferences of the target audience, thereby maximizing the effectiveness of the advertising.

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The user uses a device to input attribute information of the target audience. This attribute information includes age, gender, interests, and location. This information is entered by the user into the device and sent as input data to the server. As output, a dataset of attribute information is generated.

[0393] Step 2:

[0394] The server retrieves relevant information from the data network based on the received attribute information. At this stage, it collects data relevant to the target audience from data sources such as social media, online reviews, and purchase history. The input is attribute information, and the output is the collected relevant dataset. This process includes data retrieval using specific APIs.

[0395] Step 3:

[0396] The server uses natural language processing techniques to analyze the collected data. Specifically, it uses Python's NLTK and spaCy libraries to analyze text data and extract keywords and trends that indicate the target audience's sentiments and interests. The input is the collected dataset, and the output is information about keywords and sentiments obtained through the analysis.

[0397] Step 4:

[0398] The server analyzes the user's emotional state using emotion analysis tools. It executes a specific algorithm to calculate an emotion score based on past data and sensor information entered by the user. The input is the user's past data, and the output is the user's emotion score.

[0399] Step 5:

[0400] The server utilizes a generative AI model to create prompts and generate ad copy. These prompts include specific examples such as "Youth-oriented fashion advertising: Create a message that conveys excitement." By inputting prompts into the model, the corresponding ad copy is generated and output.

[0401] Step 6:

[0402] The server evaluates multiple generated ad copy and selects the most suitable one. Here, an evaluation algorithm based on sentiment scores is applied to determine the selected message. The input consists of multiple generated ad copy and their sentiment scores, while the output is the selected ad copy.

[0403] Step 7:

[0404] The server sends the selected ad copy to the device and displays it to the user. The user uses the device to respond to the displayed ad copy. The input is the selected ad copy, and the output is the user's response.

[0405] Step 8:

[0406] The user's response is sent to the server as feedback information, which the server stores. Based on the response, the parameters of the AI ​​model are adjusted as needed. As a result, the model's performance is improved, and feedback information is obtained as output that can be used to improve future ad generation.

[0407] (Application Example 2)

[0408] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0409] While there is a need to generate advertising messages that appropriately consider the emotions of the target audience, conventional methods make it difficult to create messages that adequately reflect their emotional state. Furthermore, there is a lack of feedback mechanisms to measure the effectiveness of the generated messages and to continuously improve them. As a result, there is a problem in providing advertising messages that effectively appeal to the target audience.

[0410] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0411] In this invention, the server includes means for receiving attribute information of the target audience, means for analyzing the emotional state of the target audience using an emotion engine, and means for generating advertising messages based on the emotional state of the target audience using a generative AI model. This enables the generation of effective advertising messages that take into account the emotions of the target audience, and their continuous improvement.

[0412] A "target audience" is a group of consumers designated as the recipients of advertisements and information for a specific product or service.

[0413] "Attribute information" refers to characteristics related to the target audience, and includes data such as age, gender, interests, and geographical information.

[0414] "Collecting data from the internet" refers to the process of obtaining relevant information from data sources that are publicly available online.

[0415] "Natural language processing technology" refers to the technology that enables computers to understand, process, and generate human language.

[0416] An "emotion engine" is a technology or system for analyzing and evaluating the emotional state of users or target audiences.

[0417] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text or other forms of data.

[0418] "Feedback" refers to information about evaluations and reactions to generated advertising messages, and is data used to improve models and systems.

[0419] This invention provides a system for generating advertising messages that take into account the emotions of a target audience. The server receives attribute information of the target audience from the user and collects relevant data from the internet. This data includes social media posts, online reviews, search trends, and purchase history.

[0420] The server analyzes the collected data using natural language processing techniques to extract the emotions and preferences of the target audience. This analysis utilizes Python and the natural language processing library NLTK. Furthermore, the server uses an emotion engine to analyze the emotional state of users and the target audience in detail.

[0421] Based on the analysis results and sentiment data, a generative AI model creates advertising messages. This model uses TensorFlow to generate messages that match the sentiment of the target audience. The server then suggests the most effective message from among those generated.

[0422] Users can view suggested advertising messages through their devices and provide feedback. This feedback is sent to the server and used to improve the AI ​​model that generates the ads.

[0423] As a concrete example, consider a fashion advertisement targeting women in their 20s who are sensitive to new trends. In this case, an example prompt phrase would be "Women in their 20s, sensitive to new trends, interested in Scandinavian style," and the AI ​​model could generate an emotionally appealing message such as "Let's enjoy each day even more positively with a new style!"

[0424] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0425] Step 1:

[0426] Users input attribute information, interests, and location information of their target audience via their device and send it to the server. This inputs data about the attributes of the target audience.

[0427] Step 2:

[0428] The server collects data related to the target audience from the internet based on the attribute information it receives. This data includes social media posts, online reviews, search trends, and purchase history. This process outputs data about the target audience's interests and trends.

[0429] Step 3:

[0430] The server uses natural language processing techniques to analyze the collected data. Through this analysis, it extracts frequently occurring keywords and current trends, and identifies the sentiments and preferences of the target audience. As a result, analytical information, including sentiment data, is output.

[0431] Step 4:

[0432] The server uses an emotion engine to analyze the emotional state of the target audience set by the user. Based on the input text data, the emotion engine generates an emotion score and outputs a detailed description of that emotional state.

[0433] Step 5:

[0434] The server generates advertising messages using a generative AI model based on the collected data and emotional states obtained from the emotion engine. Python and TensorFlow are used here to output emotionally appealing messages.

[0435] Step 6:

[0436] The server evaluates multiple generated ad messages and selects and proposes the message optimized for the target audience's emotional state. The proposed ad message is then displayed on the device.

[0437] Step 7:

[0438] Users review the suggested advertising messages on their devices and provide feedback on their effectiveness and impression. This feedback generates data to evaluate the message's effectiveness.

[0439] Step 8:

[0440] The server stores user feedback and sentiment data, which is used to improve the generative AI model. This process enhances the model's performance, and these improvements are reflected in future advertising message generation.

[0441] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0442] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0447] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0448] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0449] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0450] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0451] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0452] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0453] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0454] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0455] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0456] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0457] The advertising message generation system according to the present invention is implemented by a server, a terminal, and a user. It begins with the user inputting attribute information of the target audience through the terminal. For example, this includes age group, gender, interests, and regional data. This information is transmitted to the server.

[0458] The server accesses publicly available data sources on the internet to collect data relevant to the target audience. This includes social media posts, online reviews, search trends, and purchase history data. The server retrieves this data via APIs and uses it as foundational data to understand the interests and trends of the target audience.

[0459] The collected data is analyzed on the server using natural language processing techniques. This analysis extracts sentiments and trends that indicate the target audience's interests and preferences. For example, it can identify what interests them and what keywords they frequently use.

[0460] Next, the server utilizes a generative AI model to generate advertising messages based on the extracted information. The generated messages include catchphrases and wording tailored to each target audience. The server then selects the most relevant and effective advertising message from among those generated.

[0461] The server then sends the selected ad message to the device and presents it to the user. The user reviews the multiple ad messages presented and chooses the one that best suits their purpose and context. The user then provides feedback on the selected ad message.

[0462] The server stores the received feedback in a database and uses this feedback to improve the generating AI model. This allows for improved accuracy and effectiveness of future advertising message generation.

[0463] As a concrete example, consider a youth fashion brand running a campaign for a new product. The user enters the target audience attributes as "18-24 years old," "female," "interested in fashion and trends," and "urban area." From the data collected by the server, it generates advertising messages that include keywords such as "eco-friendly" and "casual chic," which are recent trends, and makes suggestions such as "Discover a new you with an environmentally conscious style." In this way, advertising messages that fit the target audience are provided.

[0464] The following describes the processing flow.

[0465] Step 1:

[0466] The user uses a device to input attribute information for the target audience. This includes information such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0467] Step 2:

[0468] Based on the attribute information received by the server, it collects data related to the target audience from publicly available data sources on the internet. The server retrieves data via APIs from sources such as social media posts, online reviews, search trends, and purchase history.

[0469] Step 3:

[0470] The server applies natural language processing techniques to the collected data and analyzes the text data. This identifies sentiments, frequently occurring keywords, and trends that indicate the target audience's interests and preferences.

[0471] Step 4:

[0472] The server generates advertising messages using a generation AI model based on the analysis results. The generated messages include catchy slogans and content tailored to the target audience.

[0473] Step 5:

[0474] The server evaluates the generated advertising messages and selects the most effective and relevant ones. It considers multiple options and prepares them for the user to choose from.

[0475] Step 6:

[0476] The server selects an advertising message and sends it to the user's device, presenting it to them. The user reviews the message and chooses the most suitable option from the provided choices.

[0477] Step 7:

[0478] The system provides feedback to the server regarding the ad messages selected by the user, including their opinions and evaluations.

[0479] Step 8:

[0480] The server stores user feedback in a database and uses this to improve the AI ​​model that generates messages. This allows for improved accuracy and effectiveness in future message generation.

[0481] (Example 1)

[0482] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0483] In advertising strategies, there is a need to quickly generate effective promotional messages tailored to the characteristics of the target group and continuously improve them based on the response. However, traditional methods are time-consuming and labor-intensive, and often fail to accurately respond to the interests and preferences of the target group. Therefore, there is a need for a system that generates precisely tailored promotional messages for the target group and incorporates the response as feedback to create even more effective messages.

[0484] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0485] In this invention, the server includes means for receiving characteristic information of a target group, means for collecting information related to the target group from a communication network, and means for analyzing the collected information using language analysis technology to extract the interests and tendencies of the target group. This enables the generation of promotional messages that are optimal for the target group and improvements based on feedback on their effectiveness.

[0486] A "target group" refers to a specific customer segment or market segment to which an advertising or promotional message is intended.

[0487] "Characteristic information" refers to data that includes attributes of the target group, such as age group, gender, interests, and regional information.

[0488] A "communication network" refers to the infrastructure used to collect and transmit data via the internet and various other networks.

[0489] "Information" refers to data collected from various sources related to the target group, including social media posts, online reviews, and search trends.

[0490] "Language analysis technology" refers to methods that use natural language processing techniques to analyze text data and understand and classify its content.

[0491] "Interests and trends" refer to information that indicates what kind of interest a target group shows in a particular topic or product, and what trends exist within that topic.

[0492] A "promotional message" refers to advertising copy or slogans created with the purpose of appealing to a target group and encouraging them to take action regarding a product or service.

[0493] "Response" refers to the evaluation or feedback that the target group gives to the proposed promotional message.

[0494] This invention is an advertising message generation system implemented using a server and a terminal.

[0495] Server: The server operates using programs installed on a cloud service. Upon receiving characteristic information of the target group, the server accesses publicly available data sources on the internet via a communication network. This includes social media APIs, review site APIs, and search engine trend information APIs. The collected information is analyzed by a natural language processing engine running on the server. This engine is used to extract keywords that indicate the interests and trends of the target group.

[0496] Generative AI Model: The server utilizes a generative AI model to generate promotional messages based on extracted keywords and sentiment scores. The generative AI model is built using machine learning libraries and is continuously improved by incorporating historical data and user feedback. By inputting prompts, the model generates specific advertising messages.

[0497] Terminals and Users: Terminals are devices that allow users to view advertising messages through an interface and provide feedback. Users evaluate the proposed promotional messages and provide feedback to the server. This feedback is also stored on the server and used to improve the generating AI model.

[0498] Specific example: As a specific example, if an apparel company were to run a campaign for new eco-friendly fashion items targeting women aged 18-24 living in urban areas, the target information would be "18-24 years old," "female," "fashion, environmental awareness," and "urban area." From the collected data, keywords such as "sustainable," "modal," and "casual chic" would be extracted. By inputting the prompt "Let's find your eco-friendly style" into the generating AI model, a message suitable for the target audience would be generated.

[0499] In this way, the system delivers messages tailored to the specific interests of the target group and enables more refined advertising strategies based on user feedback.

[0500] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0501] Step 1:

[0502] Users input characteristic information about the target group through their device. This data includes attribute information such as age group, gender, interests, and region. This information is then transmitted from the device to the server.

[0503] Step 2:

[0504] Based on the characteristics information of the target group received, the server accesses publicly available data sources via the communication network to collect relevant information. Specifically, it obtains posts, reviews, and search trends related to the target group through social media APIs, review site APIs, etc. The collected raw data is obtained as output.

[0505] Step 3:

[0506] A natural language processing engine runs on the server and analyzes the collected raw data. Morphological analysis and sentiment analysis are used to extract keywords and sentiment scores that indicate the interests and tendencies of the target group. The input is the collected raw data, and the output is the analyzed topics and keywords.

[0507] Step 4:

[0508] The server uses a generative AI model to generate promotional messages based on the analysis results. It takes prompts that consider keywords and sentiment scores obtained from the analysis as input, and the generative AI model creates advertising messages tailored to each target group. The output is the generated advertising message.

[0509] Step 5:

[0510] The server evaluates the multiple promotional messages generated. Using an evaluation algorithm, it selects messages that are predicted to be highly relevant and effective based on past data. The selected messages are then output.

[0511] Step 6:

[0512] The server sends the selected advertising message to the device and proposes it to the user. The user reviews multiple proposed messages through the device and chooses the one that best suits their purpose and context.

[0513] Step 7:

[0514] Users provide feedback on the promotional messages they have selected. This feedback includes evaluation comments and reasons for their selection. This feedback is sent from the device to the server.

[0515] Step 8:

[0516] The server records user feedback in a database. Based on this, it updates the generative AI model to improve the accuracy and effectiveness of future ad message generation. The output is the improved generative AI model.

[0517] (Application Example 1)

[0518] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0519] The problem that this invention aims to solve is to present optimal advertising messages to target audiences in real time, based on their individual attributes. Conventional advertising message generation systems can only provide advertisements based on static information, making it difficult to personalize based on dynamic environmental factors and real-time attribute analysis.

[0520] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0521] In this invention, the server includes means for receiving attribute information of the target audience, means for recognizing surrounding environmental information and inferring the age group and gender of the detected people, and means for presenting advertising messages to a visual display device in real time. This enables the real-time presentation of personalized advertising messages that adapt to dynamic environmental changes.

[0522] A "target audience" is a group of people who are targeted to receive a specific advertising message, and it includes attribute information such as age group, gender, interests, and location.

[0523] "Attribute information" refers to a collection of information such as age group, gender, interests, and region, used to identify a target audience and understand their characteristics and interests.

[0524] "Means of collecting data from the internet" refers to technologies that have the ability to obtain information related to a target audience from publicly available data sources.

[0525] "Natural language processing technology" is a technology that uses computers to understand, analyze, and generate responses to human language, and is used for analyzing collected text data.

[0526] A "generative AI model" is an artificial intelligence technology used to generate advertising messages based on collected data.

[0527] An "advertising message" is a collection of information intended to promote a specific product or service and is conveyed to a target audience.

[0528] A "visual display device" refers to a device used to visually present advertising messages to users, such as smart glasses.

[0529] "Means for recognizing surrounding environmental information" refers to technologies that use cameras or other visual display devices to detect and analyze the situation of surrounding objects and people.

[0530] "Feedback" refers to user reactions and evaluations of proposed advertising messages, and the system is improved based on this feedback.

[0531] To implement this invention, a system consisting of a server, a terminal, and a user is required. The system generates and presents advertising messages through several stages, as follows:

[0532] The terminal is a device that receives attribute information of the target audience from the user. This includes, for example, age group, gender, interests, and region. This attribute information is transmitted to the server via the network.

[0533] The server accesses publicly available data sources on the Internet to collect data relevant to the target audience. This data collection is carried out using API technology. The collected data may include social media posts, online reviews, search trends, or purchase history.

[0534] Next, the server uses natural language processing techniques to analyze the collected data. This analysis extracts sentiments and keywords that indicate the target audience's interests and trends. The software used in this process includes libraries for text analysis.

[0535] The generative AI model automatically generates advertising messages based on this extracted information. The generative AI model is used to generate these advertising messages, which are designed to be most relevant to the target audience.

[0536] Furthermore, smart glasses are used to analyze visual information and recognize the surrounding environment. This enables the display of real-time advertisements based on the attributes of the detected individuals.

[0537] Real-time advertising messages are displayed via the visual display device of smart glasses. The displayed messages receive feedback from the user and are sent to the server. This feedback is used to improve the system.

[0538] As a concrete example, if a group of young people is detected in a shopping mall, the smart glasses will display an advertising message informing them of a special sale from a new fashion brand. An example of a prompt message to use would be, "Generate an advertisement highlighting the latest fashion trends for young people."

[0539] In this way, the system enables the delivery of dynamic and highly personalized advertising messages.

[0540] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0541] Step 1:

[0542] The user enters attribute information of the target audience into the device. Specifically, they fill in information such as age group, gender, interests, and region in a form. This input information becomes the basis for the next processing. The device sends the entered information to the server as digital data.

[0543] Step 2:

[0544] The server accesses publicly available data sources on the internet to collect relevant data based on the attribute information it receives. This process involves using APIs to retrieve data such as social media posts, online reviews, and search trends. The input is attribute information, and the output is the retrieved relevant data.

[0545] Step 3:

[0546] The server analyzes the collected data using natural language processing techniques. Through this analysis, it extracts keywords and sentiments that indicate the target audience's interests and trends. Specifically, it analyzes text data and identifies frequently used keywords. This process yields extracted information indicating interests and trends as output.

[0547] Step 4:

[0548] The server uses a generative AI model to generate advertising messages based on the extracted information. It is given a prompt in the form of, "Generate an advertising message suitable for the target audience based on the extracted keywords," and uses this instruction to construct the advertising content. The generated message is obtained as output.

[0549] Step 5:

[0550] The server recognizes the surrounding environment and estimates the age group and gender of people visually detected using smart glasses. Using visual information from the smart glasses' camera as input, it performs real-time attribute prediction and determines an appropriate advertising message. The output is an optimized advertising message.

[0551] Step 6:

[0552] The server presents optimized advertising messages to the user in real time through the visual display device of the smart glasses. This visually delivers advertisements that are appropriately customized to the target audience. The output is the displayed advertising message.

[0553] Step 7:

[0554] Users provide feedback on suggested ad messages, and this feedback is sent to the server via their device. This feedback is used as input to improve the generating AI model and is stored in a database to improve the accuracy of future ads.

[0555] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0556] By combining the advertising message generation system according to the present invention with an emotion engine, it becomes possible to generate advertising messages that take into account the emotions of the target audience. In this embodiment, the server, terminal, user, and emotion engine play central roles.

[0557] The process begins with users entering target audience attribute information via their devices and sending it to a server. This information may include age, gender, interests, and location. Based on this information, the server collects data relevant to the target audience from publicly available data sources on the internet. This collected data may include social media posts, online reviews, search trends, and purchase history.

[0558] On the server, natural language processing technology is used to perform text analysis on the collected data. This analysis extracts frequently occurring keywords and trends that indicate the emotions and preferences of the target audience. In addition, an emotion engine analyzes the user's state and acquires emotional data.

[0559] Next, the server utilizes a generative AI model to generate advertising messages based on the analysis results and the output of the emotion engine. Each message is structured to reflect the emotions of the target audience. From the generated set of advertising messages, the server selects the message optimized for the emotion data and proposes it effectively.

[0560] The server sends the selected advertising message to the device and displays it to the user. The user can review the message they received and provide feedback. Furthermore, sentiment data and feedback information are stored on the server and used to improve the AI ​​model for generating messages.

[0561] For example, when running a campaign for a youth fashion brand, the user's emotional engine might recognize feelings of excitement and anticipation. By incorporating this data into the analysis, emotionally appealing messages such as "Let's enjoy each day even more positively with a new style!" are generated and selected. This results in advertising messages that reflect the emotional state of the target audience.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The user enters attribute information for the target audience using their device. This attribute information includes basic characteristics such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0565] Step 2:

[0566] Based on the attribute information received by the server, data relevant to the target audience is collected from publicly available data sources on the internet. This collection includes obtaining social media posts, online reviews, search trends, and purchase history via APIs.

[0567] Step 3:

[0568] The server uses an emotion engine to collect user emotion data. The emotion engine reads emotions from the user's facial expressions and tone of voice as they input information. This data is used to generate advertising messages.

[0569] Step 4:

[0570] The server analyzes target audience data and sentiment data collected using natural language processing technology. This analysis extracts information indicating the target audience's interests, trends, and emotional state, and extracts keywords optimized for that emotional state.

[0571] Step 5:

[0572] The server uses an AI model to generate advertising messages based on the analysis results. Because the generated messages take sentiment data into account, they are tailored to the emotions of the target audience.

[0573] Step 6:

[0574] The server evaluates multiple generated advertising messages and selects the optimal one. This evaluation process considers sentiment relevance and predicted effect as selection criteria.

[0575] Step 7:

[0576] The server selects an advertising message and sends it to the user's device for display. The user reviews the message and chooses the one that best suits the advertising campaign's objectives.

[0577] Step 8:

[0578] The system feeds back user feedback and evaluations of selected ad messages to the server. It also collects new user sentiment data.

[0579] Step 9:

[0580] The server collects feedback and sentiment data, which is used to improve the generating AI model. This increases the accuracy of future ad message generation.

[0581] (Example 2)

[0582] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0583] Current ad generation systems struggle to create messages that adequately consider the emotions and preferences of target audiences, making it difficult to develop effective advertising strategies. Furthermore, there is a lack of mechanisms to effectively utilize feedback on generated messages and appropriately improve the AI ​​model for message generation.

[0584] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0585] In this invention, the server includes means for receiving attribute information of the target audience, means for acquiring relevant information from a data network, means for analyzing the information using natural language processing technology, means for analyzing the user's emotions using emotion analysis means, means for generating ad copy using a generative AI model, means for evaluating and selecting ad copy, and means for receiving responses and improving the model. This enables the efficient generation of ad messages that are suitable for the emotions and preferences of the target audience, and the realization of an effective advertising strategy based on them.

[0586] A "target audience" refers to a group of people who have specific attributes (age, gender, interests, location, etc.) and are the recipients of an advertisement or message.

[0587] A "data network" refers to a distributed information system, including the internet, used for collecting and transmitting information.

[0588] "Natural language processing technology" refers to a set of technologies for computers to understand and generate human language, including text analysis and sentiment analysis.

[0589] "Emotional analysis means" refers to methods or devices that analyze a user's psychological state and emotions based on data and evaluate them numerically or categorically.

[0590] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates new content or messages based on input data.

[0591] A "prompt" refers to text input to a generative AI model that contains instructions or questions designed to elicit a specific output.

[0592] "Ad copy" refers to text messages designed to promote a product or service to a specific target audience.

[0593] "Responses" refer to user reactions and feedback information regarding the generated advertising messages.

[0594] This invention provides a means for generating effective advertisements based on the emotions and preferences of a target audience in an advertising message generation system.

[0595] First, the user uses their device to input attribute information of the target audience. This input information includes age, gender, interests, and location. The entered information is sent from the device to the server. After receiving this information, the server initiates a process to collect relevant data via the data network. In this process, it accesses various data sources such as social media posts, online reviews, and purchase history.

[0596] The server analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy). The purpose of this analysis is to extract key keywords and trends that indicate the interests and tendencies of the target audience. In addition to this analysis, the server uses sentiment analysis tools to understand the user's current emotional state. For example, it infers what emotions the user is experiencing based on user input and data from terminal sensors.

[0597] Next, the server uses a generative AI model to create a prompt, and then generates ad copy based on that. The generated ad copy is then adjusted to match the sentiment of the target audience. For example, in an advertising campaign about youth fashion, the server might generate a prompt such as, "Youth Fashion Ads: Create Messages that Convey Excitement."

[0598] Multiple generated ad copy is evaluated by the server, and the best one is selected. The server sends the selected ad copy to the device and displays it to the user. The user responds to the received ad copy through the device, and this response is stored on the server as feedback. This feedback information is used to improve the generation AI model and is reflected in the new ad copy generation process.

[0599] In this way, the system of the present invention can generate advertising messages that accurately reflect the emotions and preferences of the target audience, thereby maximizing the effectiveness of the advertising.

[0600] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0601] Step 1:

[0602] The user uses a device to input attribute information of the target audience. This attribute information includes age, gender, interests, and location. This information is entered by the user into the device and sent as input data to the server. As output, a dataset of attribute information is generated.

[0603] Step 2:

[0604] The server retrieves relevant information from the data network based on the received attribute information. At this stage, it collects data relevant to the target audience from data sources such as social media, online reviews, and purchase history. The input is attribute information, and the output is the collected relevant dataset. This process includes data retrieval using specific APIs.

[0605] Step 3:

[0606] The server uses natural language processing techniques to analyze the collected data. Specifically, it uses Python's NLTK and spaCy libraries to analyze text data and extract keywords and trends that indicate the target audience's sentiments and interests. The input is the collected dataset, and the output is information about keywords and sentiments obtained through the analysis.

[0607] Step 4:

[0608] The server analyzes the user's emotional state using emotion analysis tools. It executes a specific algorithm to calculate an emotion score based on past data and sensor information entered by the user. The input is the user's past data, and the output is the user's emotion score.

[0609] Step 5:

[0610] The server utilizes a generative AI model to create prompts and generate ad copy. These prompts include specific examples such as "Youth-oriented fashion advertising: Create a message that conveys excitement." By inputting prompts into the model, the corresponding ad copy is generated and output.

[0611] Step 6:

[0612] The server evaluates multiple generated ad copy and selects the most suitable one. Here, an evaluation algorithm based on sentiment scores is applied to determine the selected message. The input consists of multiple generated ad copy and their sentiment scores, while the output is the selected ad copy.

[0613] Step 7:

[0614] The server sends the selected ad copy to the device and displays it to the user. The user uses the device to respond to the displayed ad copy. The input is the selected ad copy, and the output is the user's response.

[0615] Step 8:

[0616] The user's response is sent to the server as feedback information, which the server stores. Based on the response, the parameters of the AI ​​model are adjusted as needed. As a result, the model's performance is improved, and feedback information is obtained as output that can be used to improve future ad generation.

[0617] (Application Example 2)

[0618] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0619] While there is a need to generate advertising messages that appropriately consider the emotions of the target audience, conventional methods make it difficult to create messages that adequately reflect their emotional state. Furthermore, there is a lack of feedback mechanisms to measure the effectiveness of the generated messages and to continuously improve them. As a result, there is a problem in providing advertising messages that effectively appeal to the target audience.

[0620] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0621] In this invention, the server includes means for receiving attribute information of the target audience, means for analyzing the emotional state of the target audience using an emotion engine, and means for generating advertising messages based on the emotional state of the target audience using a generative AI model. This enables the generation of effective advertising messages that take into account the emotions of the target audience, and their continuous improvement.

[0622] A "target audience" is a group of consumers designated as the recipients of advertisements and information for a specific product or service.

[0623] "Attribute information" refers to characteristics related to the target audience, and includes data such as age, gender, interests, and geographical information.

[0624] "Collecting data from the internet" refers to the process of obtaining relevant information from data sources that are publicly available online.

[0625] "Natural language processing technology" refers to the technology that enables computers to understand, process, and generate human language.

[0626] An "emotion engine" is a technology or system for analyzing and evaluating the emotional state of users or target audiences.

[0627] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text or other forms of data.

[0628] "Feedback" refers to information about evaluations and reactions to generated advertising messages, and is data used to improve models and systems.

[0629] This invention provides a system for generating advertising messages that take into account the emotions of a target audience. The server receives attribute information of the target audience from the user and collects relevant data from the internet. This data includes social media posts, online reviews, search trends, and purchase history.

[0630] The server analyzes the collected data using natural language processing techniques to extract the emotions and preferences of the target audience. This analysis utilizes Python and the natural language processing library NLTK. Furthermore, the server uses an emotion engine to analyze the emotional state of users and the target audience in detail.

[0631] Based on the analysis results and sentiment data, a generative AI model creates advertising messages. This model uses TensorFlow to generate messages that match the sentiment of the target audience. The server then suggests the most effective message from among those generated.

[0632] Users can view suggested advertising messages through their devices and provide feedback. This feedback is sent to the server and used to improve the AI ​​model that generates the ads.

[0633] As a concrete example, consider a fashion advertisement targeting women in their 20s who are sensitive to new trends. In this case, an example prompt phrase would be "Women in their 20s, sensitive to new trends, interested in Scandinavian style," and the AI ​​model could generate an emotionally appealing message such as "Let's enjoy each day even more positively with a new style!"

[0634] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0635] Step 1:

[0636] Users input attribute information, interests, and location information of their target audience via their device and send it to the server. This inputs data about the attributes of the target audience.

[0637] Step 2:

[0638] The server collects data related to the target audience from the internet based on the attribute information it receives. This data includes social media posts, online reviews, search trends, and purchase history. This process outputs data about the target audience's interests and trends.

[0639] Step 3:

[0640] The server uses natural language processing techniques to analyze the collected data. Through this analysis, it extracts frequently occurring keywords and current trends, and identifies the sentiments and preferences of the target audience. As a result, analytical information, including sentiment data, is output.

[0641] Step 4:

[0642] The server uses an emotion engine to analyze the emotional state of the target audience set by the user. Based on the input text data, the emotion engine generates an emotion score and outputs a detailed description of that emotional state.

[0643] Step 5:

[0644] The server generates advertising messages using a generative AI model based on the collected data and emotional states obtained from the emotion engine. Python and TensorFlow are used here to output emotionally appealing messages.

[0645] Step 6:

[0646] The server evaluates multiple generated ad messages and selects and proposes the message optimized for the target audience's emotional state. The proposed ad message is then displayed on the device.

[0647] Step 7:

[0648] Users review the suggested advertising messages on their devices and provide feedback on their effectiveness and impression. This feedback generates data to evaluate the message's effectiveness.

[0649] Step 8:

[0650] The server stores user feedback and sentiment data, which is used to improve the generative AI model. This process enhances the model's performance, and these improvements are reflected in future advertising message generation.

[0651] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0652] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0653] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0654] [Fourth Embodiment]

[0655] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0656] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0657] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0658] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0659] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0660] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0661] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0662] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0663] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0664] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0665] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0666] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0667] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] The advertising message generation system according to the present invention is implemented by a server, a terminal, and a user. It begins with the user inputting attribute information of the target audience through the terminal. For example, this includes age group, gender, interests, and regional data. This information is transmitted to the server.

[0669] The server accesses publicly available data sources on the internet to collect data relevant to the target audience. This includes social media posts, online reviews, search trends, and purchase history data. The server retrieves this data via APIs and uses it as foundational data to understand the interests and trends of the target audience.

[0670] The collected data is analyzed on the server using natural language processing techniques. This analysis extracts sentiments and trends that indicate the target audience's interests and preferences. For example, it can identify what interests them and what keywords they frequently use.

[0671] Next, the server utilizes a generative AI model to generate advertising messages based on the extracted information. The generated messages include catchphrases and wording tailored to each target audience. The server then selects the most relevant and effective advertising message from among those generated.

[0672] The server then sends the selected ad message to the device and presents it to the user. The user reviews the multiple ad messages presented and chooses the one that best suits their purpose and context. The user then provides feedback on the selected ad message.

[0673] The server stores the received feedback in a database and uses this feedback to improve the generating AI model. This allows for improved accuracy and effectiveness of future advertising message generation.

[0674] As a concrete example, consider a youth fashion brand running a campaign for a new product. The user enters the target audience attributes as "18-24 years old," "female," "interested in fashion and trends," and "urban area." From the data collected by the server, it generates advertising messages that include keywords such as "eco-friendly" and "casual chic," which are recent trends, and makes suggestions such as "Discover a new you with an environmentally conscious style." In this way, advertising messages that fit the target audience are provided.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The user uses a device to input attribute information for the target audience. This includes information such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0678] Step 2:

[0679] Based on the attribute information received by the server, it collects data related to the target audience from publicly available data sources on the internet. The server retrieves data via APIs from sources such as social media posts, online reviews, search trends, and purchase history.

[0680] Step 3:

[0681] The server applies natural language processing techniques to the collected data and analyzes the text data. This identifies sentiments, frequently occurring keywords, and trends that indicate the target audience's interests and preferences.

[0682] Step 4:

[0683] The server generates advertising messages using a generation AI model based on the analysis results. The generated messages include catchy slogans and content tailored to the target audience.

[0684] Step 5:

[0685] The server evaluates the generated advertising messages and selects the most effective and relevant ones. It considers multiple options and prepares them for the user to choose from.

[0686] Step 6:

[0687] The server selects an advertising message and sends it to the user's device, presenting it to them. The user reviews the message and chooses the most suitable option from the provided choices.

[0688] Step 7:

[0689] The system provides feedback to the server regarding the ad messages selected by the user, including their opinions and evaluations.

[0690] Step 8:

[0691] The server stores user feedback in a database and uses this to improve the AI ​​model that generates messages. This allows for improved accuracy and effectiveness in future message generation.

[0692] (Example 1)

[0693] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0694] In advertising strategies, there is a need to quickly generate effective promotional messages tailored to the characteristics of the target group and continuously improve them based on the response. However, traditional methods are time-consuming and labor-intensive, and often fail to accurately respond to the interests and preferences of the target group. Therefore, there is a need for a system that generates precisely tailored promotional messages for the target group and incorporates the response as feedback to create even more effective messages.

[0695] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0696] In this invention, the server includes means for receiving characteristic information of a target group, means for collecting information related to the target group from a communication network, and means for analyzing the collected information using language analysis technology to extract the interests and tendencies of the target group. This enables the generation of promotional messages that are optimal for the target group and improvements based on feedback on their effectiveness.

[0697] A "target group" refers to a specific customer segment or market segment to which an advertising or promotional message is intended.

[0698] "Characteristic information" refers to data that includes attributes of the target group, such as age group, gender, interests, and regional information.

[0699] A "communication network" refers to the infrastructure used to collect and transmit data via the internet and various other networks.

[0700] "Information" refers to data collected from various sources related to the target group, including social media posts, online reviews, and search trends.

[0701] "Language analysis technology" refers to methods that use natural language processing techniques to analyze text data and understand and classify its content.

[0702] "Interests and trends" refer to information that indicates what kind of interest a target group shows in a particular topic or product, and what trends exist within that topic.

[0703] A "promotional message" refers to advertising copy or slogans created with the purpose of appealing to a target group and encouraging them to take action regarding a product or service.

[0704] "Response" refers to the evaluation or feedback that the target group gives to the proposed promotional message.

[0705] This invention is an advertising message generation system implemented using a server and a terminal.

[0706] Server: The server operates using programs installed on a cloud service. Upon receiving characteristic information of the target group, the server accesses publicly available data sources on the internet via a communication network. This includes social media APIs, review site APIs, and search engine trend information APIs. The collected information is analyzed by a natural language processing engine running on the server. This engine is used to extract keywords that indicate the interests and trends of the target group.

[0707] Generative AI Model: The server utilizes a generative AI model to generate promotional messages based on extracted keywords and sentiment scores. The generative AI model is built using machine learning libraries and is continuously improved by incorporating historical data and user feedback. By inputting prompts, the model generates specific advertising messages.

[0708] Terminals and Users: Terminals are devices that allow users to view advertising messages through an interface and provide feedback. Users evaluate the proposed promotional messages and provide feedback to the server. This feedback is also stored on the server and used to improve the generating AI model.

[0709] Specific example: As a specific example, if an apparel company were to run a campaign for new eco-friendly fashion items targeting women aged 18-24 living in urban areas, the target information would be "18-24 years old," "female," "fashion, environmental awareness," and "urban area." From the collected data, keywords such as "sustainable," "modal," and "casual chic" would be extracted. By inputting the prompt "Let's find your eco-friendly style" into the generating AI model, a message suitable for the target audience would be generated.

[0710] In this way, the system delivers messages tailored to the specific interests of the target group and enables more refined advertising strategies based on user feedback.

[0711] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0712] Step 1:

[0713] Users input characteristic information about the target group through their device. This data includes attribute information such as age group, gender, interests, and region. This information is then transmitted from the device to the server.

[0714] Step 2:

[0715] Based on the characteristics information of the target group received, the server accesses publicly available data sources via the communication network to collect relevant information. Specifically, it obtains posts, reviews, and search trends related to the target group through social media APIs, review site APIs, etc. The collected raw data is obtained as output.

[0716] Step 3:

[0717] A natural language processing engine runs on the server and analyzes the collected raw data. Morphological analysis and sentiment analysis are used to extract keywords and sentiment scores that indicate the interests and tendencies of the target group. The input is the collected raw data, and the output is the analyzed topics and keywords.

[0718] Step 4:

[0719] The server uses a generative AI model to generate promotional messages based on the analysis results. It takes prompts that consider keywords and sentiment scores obtained from the analysis as input, and the generative AI model creates advertising messages tailored to each target group. The output is the generated advertising message.

[0720] Step 5:

[0721] The server evaluates the multiple promotional messages generated. Using an evaluation algorithm, it selects messages that are predicted to be highly relevant and effective based on past data. The selected messages are then output.

[0722] Step 6:

[0723] The server sends the selected advertising message to the device and proposes it to the user. The user reviews multiple proposed messages through the device and chooses the one that best suits their purpose and context.

[0724] Step 7:

[0725] Users provide feedback on the promotional messages they have selected. This feedback includes evaluation comments and reasons for their selection. This feedback is sent from the device to the server.

[0726] Step 8:

[0727] The server records user feedback in a database. Based on this, it updates the generative AI model to improve the accuracy and effectiveness of future ad message generation. The output is the improved generative AI model.

[0728] (Application Example 1)

[0729] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0730] The problem that this invention aims to solve is to present optimal advertising messages to target audiences in real time, based on their individual attributes. Conventional advertising message generation systems can only provide advertisements based on static information, making it difficult to personalize based on dynamic environmental factors and real-time attribute analysis.

[0731] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0732] In this invention, the server includes means for receiving attribute information of the target audience, means for recognizing surrounding environmental information and inferring the age group and gender of the detected people, and means for presenting advertising messages to a visual display device in real time. This enables the real-time presentation of personalized advertising messages that adapt to dynamic environmental changes.

[0733] A "target audience" is a group of people who are targeted to receive a specific advertising message, and it includes attribute information such as age group, gender, interests, and location.

[0734] "Attribute information" refers to a collection of information such as age group, gender, interests, and region, used to identify a target audience and understand their characteristics and interests.

[0735] "Means of collecting data from the internet" refers to technologies that have the ability to obtain information related to a target audience from publicly available data sources.

[0736] "Natural language processing technology" is a technology that uses computers to understand, analyze, and generate responses to human language, and is used for analyzing collected text data.

[0737] A "generative AI model" is an artificial intelligence technology used to generate advertising messages based on collected data.

[0738] An "advertising message" is a collection of information intended to promote a specific product or service and is conveyed to a target audience.

[0739] A "visual display device" refers to a device used to visually present advertising messages to users, such as smart glasses.

[0740] "Means for recognizing surrounding environmental information" refers to technologies that use cameras or other visual display devices to detect and analyze the situation of surrounding objects and people.

[0741] "Feedback" refers to user reactions and evaluations of proposed advertising messages, and the system is improved based on this feedback.

[0742] To implement this invention, a system consisting of a server, a terminal, and a user is required. The system generates and presents advertising messages through several stages, as follows:

[0743] The terminal is a device that receives attribute information of the target audience from the user. This includes, for example, age group, gender, interests, and region. This attribute information is transmitted to the server via the network.

[0744] The server accesses publicly available data sources on the Internet to collect data relevant to the target audience. This data collection is carried out using API technology. The collected data may include social media posts, online reviews, search trends, or purchase history.

[0745] Next, the server uses natural language processing techniques to analyze the collected data. This analysis extracts sentiments and keywords that indicate the target audience's interests and trends. The software used in this process includes libraries for text analysis.

[0746] The generative AI model automatically generates advertising messages based on this extracted information. The generative AI model is used to generate these advertising messages, which are designed to be most relevant to the target audience.

[0747] Furthermore, smart glasses are used to analyze visual information and recognize the surrounding environment. This enables the display of real-time advertisements based on the attributes of the detected individuals.

[0748] Real-time advertising messages are displayed via the visual display device of smart glasses. The displayed messages receive feedback from the user and are sent to the server. This feedback is used to improve the system.

[0749] As a concrete example, if a group of young people is detected in a shopping mall, the smart glasses will display an advertising message informing them of a special sale from a new fashion brand. An example of a prompt message to use would be, "Generate an advertisement highlighting the latest fashion trends for young people."

[0750] In this way, the system enables the delivery of dynamic and highly personalized advertising messages.

[0751] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0752] Step 1:

[0753] The user enters attribute information of the target audience into the device. Specifically, they fill in information such as age group, gender, interests, and region in a form. This input information becomes the basis for the next processing. The device sends the entered information to the server as digital data.

[0754] Step 2:

[0755] The server accesses publicly available data sources on the internet to collect relevant data based on the attribute information it receives. This process involves using APIs to retrieve data such as social media posts, online reviews, and search trends. The input is attribute information, and the output is the retrieved relevant data.

[0756] Step 3:

[0757] The server analyzes the collected data using natural language processing techniques. Through this analysis, it extracts keywords and sentiments that indicate the target audience's interests and trends. Specifically, it analyzes text data and identifies frequently used keywords. This process yields extracted information indicating interests and trends as output.

[0758] Step 4:

[0759] The server uses a generative AI model to generate advertising messages based on the extracted information. It is given a prompt in the form of, "Generate an advertising message suitable for the target audience based on the extracted keywords," and uses this instruction to construct the advertising content. The generated message is obtained as output.

[0760] Step 5:

[0761] The server recognizes the surrounding environment and estimates the age group and gender of people visually detected using smart glasses. Using visual information from the smart glasses' camera as input, it performs real-time attribute prediction and determines an appropriate advertising message. The output is an optimized advertising message.

[0762] Step 6:

[0763] The server presents optimized advertising messages to the user in real time through the visual display device of the smart glasses. This visually delivers advertisements that are appropriately customized to the target audience. The output is the displayed advertising message.

[0764] Step 7:

[0765] Users provide feedback on suggested ad messages, and this feedback is sent to the server via their device. This feedback is used as input to improve the generating AI model and is stored in a database to improve the accuracy of future ads.

[0766] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0767] By combining the advertising message generation system according to the present invention with an emotion engine, it becomes possible to generate advertising messages that take into account the emotions of the target audience. In this embodiment, the server, terminal, user, and emotion engine play central roles.

[0768] The process begins with users entering target audience attribute information via their devices and sending it to a server. This information may include age, gender, interests, and location. Based on this information, the server collects data relevant to the target audience from publicly available data sources on the internet. This collected data may include social media posts, online reviews, search trends, and purchase history.

[0769] On the server, natural language processing technology is used to perform text analysis on the collected data. This analysis extracts frequently occurring keywords and trends that indicate the emotions and preferences of the target audience. In addition, an emotion engine analyzes the user's state and acquires emotional data.

[0770] Next, the server utilizes a generative AI model to generate advertising messages based on the analysis results and the output of the emotion engine. Each message is structured to reflect the emotions of the target audience. From the generated set of advertising messages, the server selects the message optimized for the emotion data and proposes it effectively.

[0771] The server sends the selected advertising message to the device and displays it to the user. The user can review the message they received and provide feedback. Furthermore, sentiment data and feedback information are stored on the server and used to improve the AI ​​model for generating messages.

[0772] For example, when running a campaign for a youth fashion brand, the user's emotional engine might recognize feelings of excitement and anticipation. By incorporating this data into the analysis, emotionally appealing messages such as "Let's enjoy each day even more positively with a new style!" are generated and selected. This results in advertising messages that reflect the emotional state of the target audience.

[0773] The following describes the processing flow.

[0774] Step 1:

[0775] The user enters attribute information for the target audience using their device. This attribute information includes basic characteristics such as age, gender, interests, and location. The entered information is sent from the device to the server.

[0776] Step 2:

[0777] Based on the attribute information received by the server, data relevant to the target audience is collected from publicly available data sources on the internet. This collection includes obtaining social media posts, online reviews, search trends, and purchase history via APIs.

[0778] Step 3:

[0779] The server uses an emotion engine to collect user emotion data. The emotion engine reads emotions from the user's facial expressions and tone of voice as they input information. This data is used to generate advertising messages.

[0780] Step 4:

[0781] The server analyzes target audience data and sentiment data collected using natural language processing technology. This analysis extracts information indicating the target audience's interests, trends, and emotional state, and extracts keywords optimized for that emotional state.

[0782] Step 5:

[0783] The server uses an AI model to generate advertising messages based on the analysis results. Because the generated messages take sentiment data into account, they are tailored to the emotions of the target audience.

[0784] Step 6:

[0785] The server evaluates multiple generated advertising messages and selects the optimal one. This evaluation process considers sentiment relevance and predicted effect as selection criteria.

[0786] Step 7:

[0787] The server selects an advertising message and sends it to the user's device for display. The user reviews the message and chooses the one that best suits the advertising campaign's objectives.

[0788] Step 8:

[0789] The system feeds back user feedback and evaluations of selected ad messages to the server. It also collects new user sentiment data.

[0790] Step 9:

[0791] The server collects feedback and sentiment data, which is used to improve the generating AI model. This increases the accuracy of future ad message generation.

[0792] (Example 2)

[0793] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0794] Current ad generation systems struggle to create messages that adequately consider the emotions and preferences of target audiences, making it difficult to develop effective advertising strategies. Furthermore, there is a lack of mechanisms to effectively utilize feedback on generated messages and appropriately improve the AI ​​model for message generation.

[0795] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0796] In this invention, the server includes means for receiving attribute information of the target audience, means for acquiring relevant information from a data network, means for analyzing the information using natural language processing technology, means for analyzing the user's emotions using emotion analysis means, means for generating ad copy using a generative AI model, means for evaluating and selecting ad copy, and means for receiving responses and improving the model. This enables the efficient generation of ad messages that are suitable for the emotions and preferences of the target audience, and the realization of an effective advertising strategy based on them.

[0797] A "target audience" refers to a group of people who have specific attributes (age, gender, interests, location, etc.) and are the recipients of an advertisement or message.

[0798] A "data network" refers to a distributed information system, including the internet, used for collecting and transmitting information.

[0799] "Natural language processing technology" refers to a set of technologies for computers to understand and generate human language, including text analysis and sentiment analysis.

[0800] "Emotional analysis means" refers to methods or devices that analyze a user's psychological state and emotions based on data and evaluate them numerically or categorically.

[0801] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates new content or messages based on input data.

[0802] A "prompt" refers to text input to a generative AI model that contains instructions or questions designed to elicit a specific output.

[0803] "Ad copy" refers to text messages designed to promote a product or service to a specific target audience.

[0804] "Responses" refer to user reactions and feedback information regarding the generated advertising messages.

[0805] This invention provides a means for generating effective advertisements based on the emotions and preferences of a target audience in an advertising message generation system.

[0806] First, the user uses their device to input attribute information of the target audience. This input information includes age, gender, interests, and location. The entered information is sent from the device to the server. After receiving this information, the server initiates a process to collect relevant data via the data network. In this process, it accesses various data sources such as social media posts, online reviews, and purchase history.

[0807] The server analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy). The purpose of this analysis is to extract key keywords and trends that indicate the interests and tendencies of the target audience. In addition to this analysis, the server uses sentiment analysis tools to understand the user's current emotional state. For example, it infers what emotions the user is experiencing based on user input and data from terminal sensors.

[0808] Next, the server uses a generative AI model to create a prompt, and then generates ad copy based on that. The generated ad copy is then adjusted to match the sentiment of the target audience. For example, in an advertising campaign about youth fashion, the server might generate a prompt such as, "Youth Fashion Ads: Create Messages that Convey Excitement."

[0809] Multiple generated ad copy is evaluated by the server, and the best one is selected. The server sends the selected ad copy to the device and displays it to the user. The user responds to the received ad copy through the device, and this response is stored on the server as feedback. This feedback information is used to improve the generation AI model and is reflected in the new ad copy generation process.

[0810] In this way, the system of the present invention can generate advertising messages that accurately reflect the emotions and preferences of the target audience, thereby maximizing the effectiveness of the advertising.

[0811] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0812] Step 1:

[0813] The user uses a device to input attribute information of the target audience. This attribute information includes age, gender, interests, and location. This information is entered by the user into the device and sent as input data to the server. As output, a dataset of attribute information is generated.

[0814] Step 2:

[0815] The server retrieves relevant information from the data network based on the received attribute information. At this stage, it collects data relevant to the target audience from data sources such as social media, online reviews, and purchase history. The input is attribute information, and the output is the collected relevant dataset. This process includes data retrieval using specific APIs.

[0816] Step 3:

[0817] The server uses natural language processing techniques to analyze the collected data. Specifically, it uses Python's NLTK and spaCy libraries to analyze text data and extract keywords and trends that indicate the target audience's sentiments and interests. The input is the collected dataset, and the output is information about keywords and sentiments obtained through the analysis.

[0818] Step 4:

[0819] The server analyzes the user's emotional state using emotion analysis tools. It executes a specific algorithm to calculate an emotion score based on past data and sensor information entered by the user. The input is the user's past data, and the output is the user's emotion score.

[0820] Step 5:

[0821] The server utilizes a generative AI model to create prompts and generate ad copy. These prompts include specific examples such as "Youth-oriented fashion advertising: Create a message that conveys excitement." By inputting prompts into the model, the corresponding ad copy is generated and output.

[0822] Step 6:

[0823] The server evaluates multiple generated ad copy and selects the most suitable one. Here, an evaluation algorithm based on sentiment scores is applied to determine the selected message. The input consists of multiple generated ad copy and their sentiment scores, while the output is the selected ad copy.

[0824] Step 7:

[0825] The server sends the selected ad copy to the device and displays it to the user. The user uses the device to respond to the displayed ad copy. The input is the selected ad copy, and the output is the user's response.

[0826] Step 8:

[0827] The user's response is sent to the server as feedback information, which the server stores. Based on the response, the parameters of the AI ​​model are adjusted as needed. As a result, the model's performance is improved, and feedback information is obtained as output that can be used to improve future ad generation.

[0828] (Application Example 2)

[0829] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0830] While there is a need to generate advertising messages that appropriately consider the emotions of the target audience, conventional methods make it difficult to create messages that adequately reflect their emotional state. Furthermore, there is a lack of feedback mechanisms to measure the effectiveness of the generated messages and to continuously improve them. As a result, there is a problem in providing advertising messages that effectively appeal to the target audience.

[0831] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0832] In this invention, the server includes means for receiving attribute information of the target audience, means for analyzing the emotional state of the target audience using an emotion engine, and means for generating advertising messages based on the emotional state of the target audience using a generative AI model. This enables the generation of effective advertising messages that take into account the emotions of the target audience, and their continuous improvement.

[0833] A "target audience" is a group of consumers designated as the recipients of advertisements and information for a specific product or service.

[0834] "Attribute information" refers to characteristics related to the target audience, and includes data such as age, gender, interests, and geographical information.

[0835] "Collecting data from the internet" refers to the process of obtaining relevant information from data sources that are publicly available online.

[0836] "Natural language processing technology" refers to the technology that enables computers to understand, process, and generate human language.

[0837] An "emotion engine" is a technology or system for analyzing and evaluating the emotional state of users or target audiences.

[0838] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text or other forms of data.

[0839] "Feedback" refers to information about evaluations and reactions to generated advertising messages, and is data used to improve models and systems.

[0840] This invention provides a system for generating advertising messages that take into account the emotions of a target audience. The server receives attribute information of the target audience from the user and collects relevant data from the internet. This data includes social media posts, online reviews, search trends, and purchase history.

[0841] The server analyzes the collected data using natural language processing techniques to extract the emotions and preferences of the target audience. This analysis utilizes Python and the natural language processing library NLTK. Furthermore, the server uses an emotion engine to analyze the emotional state of users and the target audience in detail.

[0842] Based on the analysis results and sentiment data, a generative AI model creates advertising messages. This model uses TensorFlow to generate messages that match the sentiment of the target audience. The server then suggests the most effective message from among those generated.

[0843] Users can view suggested advertising messages through their devices and provide feedback. This feedback is sent to the server and used to improve the AI ​​model that generates the ads.

[0844] As a concrete example, consider a fashion advertisement targeting women in their 20s who are sensitive to new trends. In this case, an example prompt phrase would be "Women in their 20s, sensitive to new trends, interested in Scandinavian style," and the AI ​​model could generate an emotionally appealing message such as "Let's enjoy each day even more positively with a new style!"

[0845] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0846] Step 1:

[0847] Users input attribute information, interests, and location information of their target audience via their device and send it to the server. This inputs data about the attributes of the target audience.

[0848] Step 2:

[0849] The server collects data related to the target audience from the internet based on the attribute information it receives. This data includes social media posts, online reviews, search trends, and purchase history. This process outputs data about the target audience's interests and trends.

[0850] Step 3:

[0851] The server uses natural language processing techniques to analyze the collected data. Through this analysis, it extracts frequently occurring keywords and current trends, and identifies the sentiments and preferences of the target audience. As a result, analytical information, including sentiment data, is output.

[0852] Step 4:

[0853] The server uses an emotion engine to analyze the emotional state of the target audience set by the user. Based on the input text data, the emotion engine generates an emotion score and outputs a detailed description of that emotional state.

[0854] Step 5:

[0855] The server generates advertising messages using a generative AI model based on the collected data and emotional states obtained from the emotion engine. Python and TensorFlow are used here to output emotionally appealing messages.

[0856] Step 6:

[0857] The server evaluates multiple generated ad messages and selects and proposes the message optimized for the target audience's emotional state. The proposed ad message is then displayed on the device.

[0858] Step 7:

[0859] Users review the suggested advertising messages on their devices and provide feedback on their effectiveness and impression. This feedback generates data to evaluate the message's effectiveness.

[0860] Step 8:

[0861] The server stores user feedback and sentiment data, which is used to improve the generative AI model. This process enhances the model's performance, and these improvements are reflected in future advertising message generation.

[0862] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0863] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0864] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0865] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0866] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0867] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0868] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0869] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0870] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0871] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0872] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0873] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0874] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0875] 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.

[0876] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0877] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0878] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0879] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0880] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0881] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0882] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0883] The following is further disclosed regarding the embodiments described above.

[0884] (Claim 1)

[0885] Means of receiving attribute information of the target audience,

[0886] Means of collecting data related to the target audience from the internet,

[0887] A method for analyzing data collected using natural language processing technology to extract the interests and trends of the target audience,

[0888] A means of generating advertising messages using a generative AI model,

[0889] A means of evaluating multiple generated advertising messages and suggesting the optimal advertising message,

[0890] A means of receiving feedback on the proposed advertising message,

[0891] A means of accumulating the feedback received and improving the generative AI model,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1 for analyzing the preferences of a target audience.

[0895] (Claim 3)

[0896] The system according to claim 1 for modifying the generated AI model based on feedback.

[0897] "Example 1"

[0898] (Claim 1)

[0899] Means of receiving characteristic information of the target group,

[0900] Means for collecting information related to a target group from a communication network,

[0901] A method for analyzing information collected using language analysis technology to extract the interests and tendencies of a target group,

[0902] A means of generating promotional messages using a generative model,

[0903] A means of evaluating multiple generated promotional messages and suggesting the optimal promotional message,

[0904] A means of receiving responses to the proposed promotional message,

[0905] A means of accumulating the received responses and improving the generative model,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1 for analyzing the preferences of a target group.

[0909] (Claim 3)

[0910] The system according to claim 1, which modifies the generation model based on the reaction.

[0911] "Application Example 1"

[0912] (Claim 1)

[0913] Means of receiving attribute information of the target audience,

[0914] Means of collecting data related to the target audience from the internet,

[0915] A method for analyzing data collected using natural language processing technology to extract the interests and trends of the target audience,

[0916] A means of generating advertising messages using a generative AI model,

[0917] A means of evaluating multiple generated advertising messages and suggesting the optimal advertising message,

[0918] A means of receiving feedback on the proposed advertising message,

[0919] A means of accumulating the feedback received and improving the generative AI model,

[0920] A means for recognizing surrounding environmental information and inferring the age group and gender of detected people,

[0921] A means of displaying advertising messages on a visual display device in real time,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, which analyzes the preferences of a target audience and adjusts advertising messages based on real-time display.

[0925] (Claim 3)

[0926] The system according to claim 1, which modifies the generated AI model based on feedback to improve the accuracy of real-time advertising message presentation.

[0927] "Example 2 of combining an emotion engine"

[0928] (Claim 1)

[0929] A means of receiving attribute information of the target audience,

[0930] A means of obtaining information related to the target audience from a data network,

[0931] A method for analyzing information obtained using natural language processing technology to extract the interests and trends of the target audience,

[0932] A means of analyzing a user's emotions using emotion analysis tools,

[0933] A method for generating prompt text and advertising copy using a generative AI model,

[0934] A means for evaluating multiple generated ad copy and selecting the appropriate ad copy,

[0935] A means for receiving responses regarding selected ad copy,

[0936] A means of saving received responses and improving the generative AI model,

[0937] A system that includes this.

[0938] (Claim 2)

[0939] The system according to claim 1, which adjusts ad copy based on the preferences and emotions of the target audience.

[0940] (Claim 3)

[0941] The system according to claim 1, which modifies the parameters of the generated AI model based on the response.

[0942] "Application example 2 when combining with an emotional engine"

[0943] (Claim 1)

[0944] Means of receiving attribute information of the target audience,

[0945] Means of collecting data related to the target audience from the internet,

[0946] A method for analyzing data collected using natural language processing technology to extract the interests and trends of the target audience,

[0947] A method for analyzing the emotional state of a target audience using an emotion engine,

[0948] A means of generating advertising messages based on the emotional state of the target audience using a generative AI model,

[0949] A means of evaluating multiple generated ad messages and suggesting ad messages optimized for the emotional state of the target audience,

[0950] A means of receiving feedback on the proposed advertising message,

[0951] A means to improve the generative AI model by accumulating the feedback and emotional data received,

[0952] A system that includes this.

[0953] (Claim 2)

[0954] The system according to claim 1 for analyzing the preferences and emotions of a target audience.

[0955] (Claim 3)

[0956] The system according to claim 1 for modifying a generated AI model based on feedback and sentiment data. [Explanation of Symbols]

[0957] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of receiving attribute information of the target audience, Means of collecting data related to the target audience from the internet, A method for analyzing data collected using natural language processing technology to extract the interests and trends of the target audience, A means of generating advertising messages using a generative AI model, A means of evaluating multiple generated advertising messages and suggesting the optimal advertising message, A means of receiving feedback on the proposed advertising message, A means of accumulating the feedback received and improving the generative AI model, A system that includes this.

2. The system according to claim 1 for analyzing the preferences of a target audience.

3. The system according to claim 1, which modifies the generated AI model based on feedback.

Images