system

Abstract

We provide the system. [Solution] Means for collecting large amounts of information, A generation means for extracting user interests and trends from the aforementioned collected information, A decision-making tool for formulating operational strategies based on identified interests and trends, A means for generating and distributing advertisements based on the aforementioned operational strategy, A feedback means for measuring the effectiveness of the delivered advertisement and for improving the generation means and determination means, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In many companies, especially small-scale companies, there is a problem that it is difficult to grasp in-depth consumer insights and select an appropriate advertising strategy. With limited resources available to companies, it is difficult to extract meaningful insights from a vast amount of information and implement optimal advertising methods. As a result, many companies are unable to maximize the advertising effect, and there is a problem that the effect of the marketing strategy is limited.

Means for Solving the Problems

[0005] This invention solves the problem by providing a system that includes means for collecting information, means for generating information to extract user interests and trends, means for formulating operational strategies, means for generating and distributing advertisements, and means for measuring advertising effectiveness and providing feedback. Specifically, it enables the extraction of consumer insights in real time from a vast amount of information, and the formulation and implementation of personalized advertising strategies based on that insight. As a result, companies can efficiently reach their target audience and maximize the effectiveness of their advertising.

[0006] "Large-scale information" refers to a very large dataset obtained from multiple sources on the internet.

[0007] "Means of collection" refers to the technical means of obtaining data from various sources and recording it.

[0008] "Generation means" refers to technical means for processing acquired data and transforming it into a format suitable for a specific purpose.

[0009] "User interests and trends" refer to consumer preferences and behavioral patterns revealed through data analysis.

[0010] "Decision-making tools for formulating operational strategies" refers to the technical means used to select the optimal advertising measures based on the insights gained.

[0011] "Means of generating and delivering advertisements" refers to the technical means of creating advertising content for target users and delivering it at the optimal time.

[0012] "Means of measuring and providing feedback on the effectiveness of advertising" refers to technical means of analyzing the performance of delivered advertisements and reflecting the results in subsequent advertising strategies. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The present invention aims to efficiently collect and analyze large amounts of information, extract deep consumer insights, and formulate advertising strategies based on those insights. An embodiment of this system will be described in detail.

[0035] Data Acquisition and Preprocessing

[0036] The server automatically retrieves data from various sources on the internet, such as search engines, social media, and blogs. This data includes search queries and click data. The collected data is first structured and then preprocessed, including noise reduction and duplicate removal.

[0037] Insight generation

[0038] The server launches a generative AI model to analyze the pre-processed data. This model utilizes natural language processing techniques to extract user interests, trends, and emotions from the text data. These results are recorded as "insights."

[0039] Planning of operational strategies

[0040] The server develops advertising strategies based on extracted insights. It plans personalized advertising campaigns, taking into account factors such as ad placement, timing, and target audience.

[0041] Ad generation and delivery

[0042] The server generates specific advertising content based on the planned advertising strategy. Using generation AI, it creates various formats of text ads, banner ads, or video ads and delivers them in the most suitable format.

[0043] The device provides an optimal user experience by displaying appropriate advertisements at planned times on websites and applications that the user accesses.

[0044] Measuring effectiveness and improving strategies

[0045] The server continuously monitors metrics such as click-through rates, conversion rates, and time spent on the site to quantitatively evaluate the performance of delivered ads. This data is used to improve advertising strategies and fine-tune AI models.

[0046] As a concrete example, when an online store sells a new product, the server analyzes keywords such as "new product," "trend," and "purchase intent," and extracts insights that users are particularly interested in "eco-friendly products." The server then generates advertisements that highlight the features of eco-friendly products and delivers them to a specific target audience. Through this process, the online store can achieve a higher conversion rate.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server collects data from specified sources. This is an automated process using web crawlers and APIs, ingesting search queries and click data and storing it in a database.

[0050] Step 2:

[0051] The server performs a cleaning process on the collected data. This includes removing duplicate data, handling missing values, and filtering out noisy data, preparing the data for analysis.

[0052] Step 3:

[0053] The server launches a generative AI model to extract consumer insights from pre-processed data. Here, natural language processing algorithms are used to analyze user interests and trends from text data and generate insights.

[0054] Step 4:

[0055] The server develops advertising strategies based on the insights gained. This involves determining the target audience, appropriate media channels, and delivery timing for the ads, and is carried out using operational expertise.

[0056] Step 5:

[0057] The server generates advertising content based on the advertising strategy. It utilizes generation AI to create personalized ads and materialize them as text and visual content.

[0058] Step 6:

[0059] The device displays advertisements at appropriate times while the user is using websites and applications. These advertisements are personalized based on the user's profile and browsing history.

[0060] Step 7:

[0061] The server monitors the performance of delivered ads. It collects click-through rates, conversion rates, and engagement data and stores them in a database.

[0062] Step 8:

[0063] The server analyzes the collected performance data to optimize advertising strategies and generative models. This feedback loop improves the effectiveness of subsequent advertising campaigns.

[0064] (Example 1)

[0065] 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."

[0066] In recent years, a vast amount of information exists on the internet, and accurate data collection and analysis are essential for its efficient use. However, linking this data to advertisements based on user preferences requires significant computing resources and time using conventional methods, making it difficult to quickly formulate effective advertising strategies. To solve this problem, there is a need for more efficient and effective data processing and advertising strategy planning methods.

[0067] 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.

[0068] In this invention, the server includes means for acquiring a wide range of data from diverse information sources, preprocessing means for structuring the acquired data and performing noise reduction and duplicate removal, and generation means for extracting user interests and trends from the preprocessed data using natural language processing technology. This makes it possible to analyze large amounts of data quickly and accurately, and to efficiently formulate effective advertising strategies based on user preferences.

[0069] "Information source" refers to the underlying medium or platform from which data is obtained, including communication networks and computer networks on the Internet.

[0070] "Data" refers to various forms of information obtained from user actions and behaviors, specifically records such as search actions and click activities.

[0071] "Preprocessing" is the process of organizing acquired data into a state that can be analyzed, and includes data formatting such as noise reduction and duplicate removal.

[0072] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to extract user interests and trends.

[0073] "Generation means" refers to functions within a system that generate useful information from data, and in particular, play a role in extracting insights necessary for advertising strategies.

[0074] "Decision-making tools" refer to the processes and methods used to formulate advertising strategies based on generated information, determining the optimal advertising policy based on the insights gained.

[0075] An "advertising strategy" is a plan and guideline for optimizing the placement, content, and targeting of advertisements, designed based on user interests and trends.

[0076] "Feedback methods" refer to processes and technologies used to analyze the effectiveness of delivered advertisements and improve the entire system based on the results obtained.

[0077] In implementing this invention, the server first acquires data from a wide range of sources. Specifically, the server collects data from online platforms such as search engines, social media, and blogs on the internet. Such data includes user search behavior and click activity.

[0078] Next, the server preprocesses the acquired data. Preprocessing involves structuring the data and performing noise reduction and duplicate removal to prepare it for analysis. It is assumed that the Python Pandas library will be used for data processing.

[0079] Furthermore, the server utilizes natural language processing technology to extract user interests and behaviors from pre-processed data using generative AI models. This process generates insights derived from user behavior. Natural language processing libraries such as Hugging Face Transformers may be used in this part.

[0080] The server develops an advertising strategy based on the extracted insights. This strategy optimizes ad placement, timing, and target audience. Following this strategy, the server uses generative AI to generate ads in various formats and delivers text ads, banner ads, video ads, and more.

[0081] The generated advertisements are displayed on websites and applications that the user accesses via their device. This allows the device to provide a user experience optimized for the user.

[0082] As a concrete example, when an online store launches a new product, the server analyzes data based on keywords such as "new product," "trend," and "purchase intent," and extracts user interest, particularly in "eco-friendly products." It then generates advertisements highlighting the features of eco-friendly products and delivers these advertisements to specific target audiences. This system enables the online store to achieve a higher conversion rate.

[0083] An example of a prompt for a generative AI model is, "How can I analyze user interests and extract specific insights?"

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server collects data from various sources on the internet. This input includes search actions and click activity from online platforms such as search engines, social media, and blogs. The server connects to these sources, retrieves vast amounts of data via APIs, and obtains output by storing it in local storage. Specifically, the server schedules to periodically access these platforms to retrieve the latest data.

[0087] Step 2:

[0088] The server preprocesses the collected data. The input for this step is the raw data obtained in step 1. Preprocessing includes data structuring, noise reduction, and duplicate removal. The output is a clean dataset suitable for analysis. The server uses the Python Pandas library to filter the data and perform specific data manipulation such as filling in missing values.

[0089] Step 3:

[0090] The server performs analysis using pre-processed data to extract user interests and trends. The input for this step is the clean data generated in step 2. The server activates a generative AI model and uses natural language processing techniques to analyze the data, extracting user interests and trends, and outputting this as insights. Specifically, the server uses the Hugging Face Transformers library to input text data into the model and analyze the results.

[0091] Step 4:

[0092] The server develops an advertising strategy based on the extracted insights. The input for this step is the user insights obtained in step 3. The server designs the advertising campaign, taking into account the placement and timing of the ads and the target audience. In this process, it outputs customized ad details. Specifically, the server utilizes digital marketing management software to set multiple ad parameters.

[0093] Step 5:

[0094] The server generates specific advertising content based on the formulated advertising strategy. The input is the campaign parameters determined in step 4. The server uses a generation AI to generate multiple types of ads, such as text ads, banner ads, and video ads, and sends them to the ad delivery system for output. Specifically, the server launches the ad generation tool and prepares the materials for posting.

[0095] Step 6:

[0096] The device presents the generated advertisement to the user. The input for this step is the advertisement content generated in step 5. The device displays the advertisement at the appropriate time on the website or application the user is accessing and generates user engagement data as output. The device calls and renders the advertisement on the screen in real time during each user session. It also operates a function to record clicks and viewing time after the advertisement is displayed.

[0097] Step 7:

[0098] The server evaluates ad performance and receives feedback. The input for this step is the user engagement data obtained in step 6. The server analyzes this data and provides feedback on areas for improvement, resulting in output that adjusts the generative AI model and ad strategy. Specifically, the server uses analytics tools to calculate metrics such as click-through rates and conversion rates. This allows strategies to optimize ad effectiveness to be reflected in the next campaign.

[0099] (Application Example 1)

[0100] 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."

[0101] Traditional advertising strategies have faced challenges in adequately delivering ads based on individual user interests and behaviors. Furthermore, accurate measurement of advertising effectiveness has been lacking, making it difficult to improve strategies. Therefore, there is a need to maximize advertising effectiveness and improve the user experience.

[0102] 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.

[0103] In this invention, the server includes a device for collecting information, an unstructured data processing device for analyzing the user's interests and tendencies from the collected information, and a selection device for formulating a plan based on the extracted interests and tendencies. This enables the effective delivery of advertisements that match the individual interests of users and the accurate evaluation of the effectiveness of those advertisements, thereby optimizing the advertising strategy and improving the user experience.

[0104] A "device for collecting information" is a device that automatically acquires data on web pages and user behavior on the internet.

[0105] An "unstructured data processing device" is a device that analyzes acquired data to effectively extract users' interests and trends.

[0106] A "selection device" is a device that develops personalized plans based on the extracted interests and tendencies.

[0107] An "output device" is a device that generates advertising content based on a formulated plan and delivers it to each user in an optimized format.

[0108] A "return evaluation device" is a device used to evaluate the effectiveness of delivered advertisements and to improve the data analysis and planning processes.

[0109] "Advertising content" refers to data in media format that includes promotional material generated based on specific user attributes.

[0110] "Collected information" refers to digital data, including web search behavior and social network activity.

[0111] "Personalized advertising" refers to advertisements that contain personalized messages, generated based on a specific user's interests and behavioral history.

[0112] The system for implementing the present invention mainly consists of a server and a terminal. First, the server uses a device for collecting information. This device has the function of automatically acquiring data on web pages and user behavior on the internet. The data includes web search behavior and behavior on social networks.

[0113] Next, the server uses an unstructured data processing device to analyze the collected information. This device utilizes a generative AI model to effectively extract users' interests and tendencies. Based on the analysis results, the server activates a selection device and develops a personalized plan based on the extracted interests and tendencies.

[0114] Next, the server uses an output device to generate and distribute advertising content based on the formulated plan. This device has the function of displaying advertisements in a format optimized for each user. On the user's terminal, the delivered advertisements can be viewed in real time.

[0115] Furthermore, the server uses a return evaluation device to assess the effectiveness of the delivered advertisements. Based on the acquired evaluation results, this device generates feedback data to improve the processes of the unstructured data processing device and the selection device.

[0116] For example, if a user shows interest in eco-friendly products, the server generates personalized advertising content such as "Check out our new eco-friendly products!" and delivers it to that user.

[0117] A concrete example of a prompt using a generative AI model would be the instruction, "Create advertisements tailored to the user's interests based on the web pages they have recently visited."

[0118] By implementing such a system, advertisements tailored to individual user interests can be effectively delivered, optimizing strategies and improving the user experience.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] As an initial step in information gathering, the server acquires data on internet pages and user behavior. Using web search behavior and social network behavior data as input, the data collection process via agents begins. The output is raw data used for subsequent analysis.

[0122] Step 2:

[0123] The server feeds the collected raw data to an unstructured data processing unit for analysis. Using the collected data as input, a generative AI model is employed to identify the user's interests and tendencies. As a result of text analysis using natural language processing technology, the user's areas of interest and behavioral trends are output.

[0124] Step 3:

[0125] The server drives the selection mechanism based on the generated insights and formulates an advertising plan. The input is the user's interests and tendencies obtained in the previous step, and the output is the generation of personalized advertising messages and campaign plans. Specifically, it constructs prompt sentences based on specific user attributes and sends them to the generation AI model.

[0126] Step 4:

[0127] The server uses an output device to generate and deliver advertising content according to the formulated plan. The input is the advertising plan, which is the output in step 3, and the output is the advertising content formatted in the optimal format. In terms of delivery, the analyzed advertisement is displayed on the user's device in real time via Google® AdMob or other advertising platforms.

[0128] Step 5:

[0129] The server activates a feedback evaluation system to assess the effectiveness of the advertisement. The input received is user interaction data (e.g., ad click-through rate and time spent on the page), from which quantitative evaluation metrics are generated. The output is feedback data generated using data analysis techniques, which serves as a guideline for adjusting future advertising strategies to optimize them.

[0130] 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.

[0131] This invention relates to a system that uses an emotion engine, which is capable of collecting large amounts of information and recognizing users' interests, trends, and emotions, to formulate advertising strategies and generate and deliver personalized advertisements. In particular, this invention describes a form that enables more accurate ad delivery by combining it with an emotion engine.

[0132] Data collection and emotion recognition

[0133] The server collects data in real time from internet sources. In addition to search queries and click data, it also collects user-generated text and audio data. This data is stored in a database and then analyzed by a sentiment engine.

[0134] The emotion engine uses natural language processing technology to analyze text and audio data and extract the user's emotional state. This process provides information about the emotions the user is experiencing.

[0135] Insight generation and strategy formulation

[0136] The server integrates the emotional data extracted by the emotion engine with the interests and trends of other users to generate deeper insights. This provides advanced, emotion-based insights that go beyond mere interest observations.

[0137] Furthermore, we develop advertising strategies based on these insights. By considering emotional information and tailoring messages accordingly, we can deliver advertisements that resonate with users' feelings.

[0138] Ad generation and delivery

[0139] The server generates personalized ads that take emotions into account. The generation AI designs ads that include creative elements that match the target's emotions and delivers them through specific media channels.

[0140] The device displays emotion-based advertisements at the optimal time while the user is online. This allows users to receive content that resonates with their emotions.

[0141] Effectiveness measurement and feedback

[0142] The server analyzes the response and effectiveness of the delivered ads. Click-through rates, viewing time, and emotional response tracking data are used.

[0143] The collected performance data is used to optimize the entire system, and is cyclically utilized to improve the accuracy of the emotion engine and the effectiveness of advertising strategies.

[0144] As a concrete example, when an e-commerce platform sells new fashion items, the server not only analyzes search behavior and social media posts based on "fashion" and "trend" related data, but also uses an emotion engine to detect when users have positive emotions. The server then generates and delivers advertisements that evoke these positive emotions to users, further increasing their purchase intent. In this process, users become emotionally connected to the brand, which can lead to further improvements in conversion rates.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The server collects big data from internet sources. This includes search queries, click data, text messages, social media posts, and voice input. After collection, the data is organized into a database.

[0148] Step 2:

[0149] The server uses an emotion engine to analyze the user's emotions from the collected data. Specifically, it employs natural language processing and speech emotion analysis to extract the user's emotional state from text and audio data.

[0150] Step 3:

[0151] The server combines sentiment data and interest data to generate integrated insights. These insights are recorded to match the individual user's tendencies and emotions and are used as the basis for advertising strategies.

[0152] Step 4:

[0153] The server develops optimal advertising strategies based on integrated insights. It adjusts ad messages and creatives considering the emotional state of target users. The strategy also includes where and when ads are delivered.

[0154] Step 5:

[0155] The server generates personalized ads based on emotions. Using generative AI, it designs compelling ad creatives that match the user's emotional state.

[0156] Step 6:

[0157] The device displays ads at the appropriate time based on the user's online activity. Because the ads are aligned with the user's emotions, higher engagement can be expected.

[0158] Step 7:

[0159] The server monitors the effectiveness of advertisements and analyzes the collected data. It monitors various metrics, including click-through rates, conversion rates, and user engagement data.

[0160] Step 8:

[0161] Based on the analysis results, the server improves the overall advertising strategy and sentiment engine of the system through feedback. This makes it possible to enhance the effectiveness of the next advertising campaign.

[0162] (Example 2)

[0163] 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".

[0164] In today's information-saturated environment, accurately understanding users' emotions and interests and effectively delivering advertisements based on them is difficult, and building an effective feedback system presents challenges. Conventional systems have problems in that they cannot adequately generate personalized advertisements that take emotions into account, nor can they optimize the subsequent effectiveness of those advertisements.

[0165] 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.

[0166] In this invention, the server includes means for collecting large amounts of information, means for integrating emotional information and interest data to generate advanced insights, and means for generating and delivering personalized advertisements based on emotions. This makes it possible to deliver advertisements that match the user's emotions, and to continuously feed back the effects and optimize the entire system.

[0167] "Large-scale information" refers to a vast amount of data collected from diverse sources, including data formats such as text, audio, and images.

[0168] "Emotional processing means" refers to technologies that use natural language processing techniques to analyze and extract the emotional state of a user from text and audio data.

[0169] "Insight" refers to deep insights gained from collected data, and in particular, it means advanced knowledge based on users' emotions and interests.

[0170] An "advertising strategy" refers to a plan that determines how to design, target, and deliver advertisements based on the insights gained.

[0171] "Generation methods" refer to the technologies and processes used to generate creative advertising content based on users' emotions and interests.

[0172] "Feedback methods" refer to the process of analyzing the effectiveness of delivered advertisements, optimizing the entire system based on the data obtained, and making improvements.

[0173] "User-generated elements" refer to content and behavioral data generated by users on the internet, including social media posts and search queries.

[0174] "Personalized advertising" refers to advertisements that are individually customized according to the emotional state and interests of a particular user.

[0175] This invention is a system that collects large amounts of information and generates and delivers personalized advertisements based on users' emotions and interests. Specifically, it is configured as follows:

[0176] Data collection and analysis

[0177] First, the server collects data from various sources on the internet. This process utilizes APIs and web scraping techniques. The collected data includes search queries, click data, and user-generated elements such as text and audio data. This data is stored in a database as structured data and later analyzed.

[0178] Next, the server uses emotion recognition technology to analyze the user's emotional state from the accumulated data. This analysis employs natural language processing technology, with generative AI models such as BERT and GPT being used as specific examples.

[0179] Insight generation and ad generation

[0180] After sentiment analysis is complete, the server integrates sentiment information and interest data to generate insights for advertising operations. Based on these insights, the server uses a generative AI model to design sentiment-driven creative advertisements. At this time, the AI ​​model is given instructions such as, "Create an advertising message that evokes positive emotions in women in their 20s."

[0181] Ad delivery and performance measurement

[0182] The generated personalized ads are delivered to the user at the optimal time through their device. For example, ads are displayed when the user is online, providing an emotionally resonant advertising experience.

[0183] Subsequently, the server measures the effectiveness of the delivered ads and utilizes the feedback data to optimize the entire system. Data such as click-through rates, viewing time, and emotional responses are analyzed to improve ads and enhance the accuracy of the emotional engine. This cycle allows the system to continuously evolve and provide more effective advertising strategies.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The server collects data from diverse sources. As input, it uses APIs and scraping techniques to obtain data from websites, social media, search queries, and other sources. As output, the acquired data undergoes initial processing and is stored in a database. For example, to collect posts containing specific keywords, it uses the Twitter API to gather relevant tweets.

[0187] Step 2:

[0188] The server supplies accumulated data to the emotion engine and performs emotion analysis. Text and audio data extracted from the database are used as input. Metadata indicating the user's emotional state is generated as output. Specifically, natural language processing models such as BERT and GPT are used to extract emotion labels such as "happy" and "sad" from the text data.

[0189] Step 3:

[0190] The server integrates sentiment data with other user data to generate insights. It uses sentiment labels and user behavior data (e.g., browsing history) as input. The output is insight data that includes each user's interests and sentiment tendencies. For example, if it determines that a woman in her 20s has recently made many positive posts, the insight "increase in positive sentiment" is obtained.

[0191] Step 4:

[0192] The server designs personalized ads using a generative AI model. It uses insight data and predefined ad templates as input. The output is ad content optimized for individual users. Specifically, it generates an ad that matches the "increase in positive emotions," such as an ad for "enjoying new fashion items."

[0193] Step 5:

[0194] The device delivers generated personalized ads to the user at the appropriate time. Inputs include the user's online activity and schedule. Outputs include ad banners and videos displayed while the user is browsing. Specifically, ads are displayed in real time when the user is visiting a particular webpage.

[0195] Step 6:

[0196] The server measures the effectiveness of delivered advertisements and optimizes the system. It collects data such as ad click-through rates, viewing time, and user response as input. As output, this data is used as analytical results to improve advertising strategies. Specifically, it determines whether a particular ad message is achieving the expected results and incorporates the feedback into the system.

[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] Traditional advertising delivery systems primarily rely on ad targeting based on basic user interests and click data, and have not yet reached the point of personalizing ads by considering the user's emotional state. As a result, there is a challenge in that ads cannot be delivered in response to the user's emotions in real time, and the effectiveness of advertising cannot be maximized.

[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 collecting large amounts of data, a generation device for extracting user interests, trends, and emotions from the collected data, and a decision device for formulating advertising operation policies based on the extracted interests, trends, and emotions. This makes it possible to deliver advertisements at the optimal timing according to the user's emotional state.

[0202] "Large-scale data" refers to large amounts of information in any form collected from the internet or from users' devices.

[0203] A "generating device" refers to a system that analyzes users' interests, trends, and emotions from collected data and extracts necessary information.

[0204] A "decision-making device" refers to a system used to formulate advertising management policies based on data obtained from a generation device.

[0205] "Advertising management policy" refers to a personalized advertising strategy based on specific user attributes and emotions.

[0206] "Emotional state" refers to the psychological state a user is experiencing at a particular moment, and it is an important metric in the creation and delivery of advertisements.

[0207] "Delivery device" refers to equipment or systems used to deliver selected advertisements to the user's device.

[0208] To realize this invention, a server first collects large amounts of data in real time. The data to be collected includes user search queries, communication data, and voice data. This requires that the smartphone or computer is connected to the internet. By employing a data collection bot that operates using TENSORFLOW®, the server can efficiently collect diverse information.

[0209] The collected data is then processed by a generator on the server. This generator uses the Google Cloud Natural Language API to analyze the data and determine user interests, trends, and sentiments. The analyzed data is sent to a decision-making system that develops the operational strategy for advertising campaigns. Based on the insights gained by the sentiment engine, this decision-making system generates personalized ads tailored to specific user attributes.

[0210] Next, the generated advertisements are optimized by prompts from a generation AI model and delivered to the device. OpenAI's GPT model is used to formulate these prompts and generate the ad copy. The generated advertisements are then sent to the user's smartphone via a distribution device. This enables the delivery of advertisements at the optimal timing according to the user's emotional state. For example, when a user is relaxed, an advertisement for a new novel can be presented with creative content that matches their mood, stimulating their desire to purchase.

[0211] An example of a prompt would be, "Create promotional copy that appeals to users enjoying a relaxing afternoon and captures the essence of a new novel that resonates with their mood."

[0212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0213] Step 1:

[0214] The server collects large amounts of data from the internet and user devices. It takes search queries, communication data, and audio data as input. TensorFlow is used to transform the collected data into a structured format and store it in a database.

[0215] Step 2:

[0216] The server passes the collected data to the generator, which analyzes it using the Google Cloud Natural Language API. The input is the data collected in step 1. The generator uses natural language processing technology to extract user interests, trends, and emotions from the data and outputs the analysis results.

[0217] Step 3:

[0218] The server sends the analysis results to the decision-making unit. The decision-making unit uses the user's interests, trends, and sentiment data obtained as input to formulate advertising management policies. In this process, it outputs personalized policies based on specific user attributes.

[0219] Step 4:

[0220] The server generates ad copy using a generative AI model based on the determined advertising management policy. Here, the input is the policy formulated in step 3. Using OpenAI's GPT model and provided with prompt examples, it outputs the optimal ad content.

[0221] Step 5:

[0222] The device delivers the generated advertisement to the user's smartphone. The input is the advertisement copy created in step 4. The delivery device sends the advertisement in a way that is tailored to the user's emotional state and timing.

[0223] Step 6:

[0224] The server measures the effectiveness of delivered advertisements. The input is user behavior data after receiving the advertisement. It collects performance data such as click-through rates, viewing time, and additional feedback, and uses a feedback mechanism to optimize the entire system. Based on the collected data, more precise analysis and improvements to advertising strategies are made.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] [Second Embodiment]

[0229] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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".

[0241] The present invention aims to efficiently collect and analyze large amounts of information, extract deep consumer insights, and formulate advertising strategies based on those insights. An embodiment of this system will be described in detail.

[0242] Data Acquisition and Preprocessing

[0243] The server automatically retrieves data from various sources on the internet, such as search engines, social media, and blogs. This data includes search queries and click data. The collected data is first structured and then preprocessed, including noise reduction and duplicate removal.

[0244] Insight generation

[0245] The server launches a generative AI model to analyze the pre-processed data. This model utilizes natural language processing techniques to extract user interests, trends, and emotions from the text data. These results are recorded as "insights."

[0246] Planning of operational strategies

[0247] The server develops advertising strategies based on extracted insights. It plans personalized advertising campaigns, taking into account factors such as ad placement, timing, and target audience.

[0248] Ad generation and delivery

[0249] The server generates specific advertising content based on the planned advertising strategy. Using generation AI, it creates various formats of text ads, banner ads, or video ads and delivers them in the most suitable format.

[0250] The device provides an optimal user experience by displaying appropriate advertisements at planned times on websites and applications that the user accesses.

[0251] Measuring effectiveness and improving strategies

[0252] The server continuously monitors metrics such as click-through rates, conversion rates, and time spent on the site to quantitatively evaluate the performance of delivered ads. This data is used to improve advertising strategies and fine-tune AI models.

[0253] As a concrete example, when an online store sells a new product, the server analyzes keywords such as "new product," "trend," and "purchase intent," and extracts insights that users are particularly interested in "eco-friendly products." The server then generates advertisements that highlight the features of eco-friendly products and delivers them to a specific target audience. Through this process, the online store can achieve a higher conversion rate.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The server collects data from specified sources. This is an automated process using web crawlers and APIs, ingesting search queries and click data and storing it in a database.

[0257] Step 2:

[0258] The server performs a cleaning process on the collected data. This includes removing duplicate data, handling missing values, and filtering out noisy data, preparing the data for analysis.

[0259] Step 3:

[0260] The server launches a generative AI model to extract consumer insights from pre-processed data. Here, natural language processing algorithms are used to analyze user interests and trends from text data and generate insights.

[0261] Step 4:

[0262] The server develops advertising strategies based on the insights gained. This involves determining the target audience, appropriate media channels, and delivery timing for the ads, and is carried out using operational expertise.

[0263] Step 5:

[0264] The server generates advertising content based on the advertising strategy. It utilizes generation AI to create personalized ads and materialize them as text and visual content.

[0265] Step 6:

[0266] The device displays advertisements at appropriate times while the user is using websites and applications. These advertisements are personalized based on the user's profile and browsing history.

[0267] Step 7:

[0268] The server monitors the performance of delivered ads. It collects click-through rates, conversion rates, and engagement data and stores them in a database.

[0269] Step 8:

[0270] The server analyzes the collected performance data to optimize advertising strategies and generative models. This feedback loop improves the effectiveness of subsequent advertising campaigns.

[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 recent years, a vast amount of information exists on the internet, and accurate data collection and analysis are essential for its efficient use. However, linking this data to advertisements based on user preferences requires significant computing resources and time using conventional methods, making it difficult to quickly formulate effective advertising strategies. To solve this problem, there is a need for more efficient and effective data processing and advertising strategy planning methods.

[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 acquiring a wide range of data from diverse information sources, preprocessing means for structuring the acquired data and performing noise reduction and duplicate removal, and generation means for extracting user interests and trends from the preprocessed data using natural language processing technology. This makes it possible to analyze large amounts of data quickly and accurately, and to efficiently formulate effective advertising strategies based on user preferences.

[0276] "Information source" refers to the underlying medium or platform from which data is obtained, including communication networks and computer networks on the Internet.

[0277] "Data" refers to various forms of information obtained from user actions and behaviors, specifically records such as search actions and click activities.

[0278] "Preprocessing" is the process of organizing acquired data into a state that can be analyzed, and includes data formatting such as noise reduction and duplicate removal.

[0279] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to extract user interests and trends.

[0280] "Generation means" refers to functions within a system that generate useful information from data, and in particular, play a role in extracting insights necessary for advertising strategies.

[0281] "Decision-making tools" refer to the processes and methods used to formulate advertising strategies based on generated information, determining the optimal advertising policy based on the insights gained.

[0282] The "advertising strategy" is a plan or guideline for optimizing the placement, content, and targeting of advertisements designed based on the interests and trends of users.

[0283] The "feedback means" refers to a process or technology for analyzing the effects of the delivered advertisements and improving the entire system based on the obtained results.

[0284] In implementing this invention, the server first widely acquires data from various information sources. Specifically, the server collects data from online platforms such as search engines, social media, and blogs on the Internet. Such data includes users' search behaviors and click activities.

[0285] Next, the server preprocesses the acquired data. In the preprocessing, the data is structured, and noise removal and duplicate removal are performed to prepare it in a form suitable for analysis. Here, it is assumed that the Pandas library of Python is used for data processing.

[0286] Furthermore, the server utilizes natural language processing technology and uses a generative AI model to extract users' interests and trends from the preprocessed data. Through this process, insights obtained from users' behaviors are generated. In this part, natural language processing libraries such as Hugging Face Transformers can be used.

[0287] The server formulates an advertising strategy based on the extracted insights. This advertising strategy aims to optimize the placement, timing, and target audience of advertisements. The server generates advertisements in various formats using generative AI according to this strategy and distributes text advertisements, banner advertisements, video advertisements, etc.

[0288] The generated advertisements are displayed on the websites or applications accessed by users through terminals. Thereby, the terminal provides a user experience optimized for users.

[0289] As a concrete example, when an online store launches a new product, the server analyzes data based on keywords such as "new product," "trend," and "purchase intent," and extracts user interest, particularly in "eco-friendly products." It then generates advertisements highlighting the features of eco-friendly products and delivers these advertisements to specific target audiences. This system enables the online store to achieve a higher conversion rate.

[0290] An example of a prompt for a generative AI model is, "How can I analyze user interests and extract specific insights?"

[0291] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0292] Step 1:

[0293] The server collects data from various sources on the internet. This input includes search actions and click activity from online platforms such as search engines, social media, and blogs. The server connects to these sources, retrieves vast amounts of data via APIs, and obtains output by storing it in local storage. Specifically, the server schedules to periodically access these platforms to retrieve the latest data.

[0294] Step 2:

[0295] The server preprocesses the collected data. The input for this step is the raw data obtained in step 1. Preprocessing includes data structuring, noise reduction, and duplicate removal. The output is a clean dataset suitable for analysis. The server uses the Python Pandas library to filter the data and perform specific data manipulation such as filling in missing values.

[0296] Step 3:

[0297] The server performs analysis using pre-processed data to extract user interests and trends. The input for this step is the clean data generated in step 2. The server activates a generative AI model and uses natural language processing techniques to analyze the data, extracting user interests and trends, and outputting this as insights. Specifically, the server uses the Hugging Face Transformers library to input text data into the model and analyze the results.

[0298] Step 4:

[0299] The server develops an advertising strategy based on the extracted insights. The input for this step is the user insights obtained in step 3. The server designs the advertising campaign, taking into account the placement and timing of the ads and the target audience. In this process, it outputs customized ad details. Specifically, the server utilizes digital marketing management software to set multiple ad parameters.

[0300] Step 5:

[0301] The server generates specific advertising content based on the formulated advertising strategy. The input is the campaign parameters determined in step 4. The server uses a generation AI to generate multiple types of ads, such as text ads, banner ads, and video ads, and sends them to the ad delivery system for output. Specifically, the server launches the ad generation tool and prepares the materials for posting.

[0302] Step 6:

[0303] The terminal presents the generated advertisement to the user. The input for this step is the advertisement content generated in step 5. The terminal displays the advertisement at an appropriate timing on the website or application accessed by the user, and generates user engagement data as output. The terminal calls the advertisement in real time during each user session and renders it on the screen. Also, a function to record clicks and viewing time after the advertisement is displayed operates.

[0304] Step 7:

[0305] The server evaluates the performance of the advertisement and obtains feedback. The input for this step is the user engagement data obtained in step 6. The server analyzes this and obtains output for adjusting the generation AI model and advertisement strategy by providing feedback on improvement points. As specific operations, the server uses analysis tools to calculate metrics such as click-through rate and conversion rate. Thereby, the strategy for optimizing the advertisement effect is reflected in the next campaign.

[0306] (Application Example 1)

[0307] 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".

[0308] In the conventional advertising strategy, there was a problem that advertising delivery based on the individual interests and behaviors of users was not sufficiently realized. Also, the effect measurement of advertisements was not accurately performed, and it was difficult to link it to the improvement of the strategy. As a result, it has been required to maximize the advertising effect and improve the user experience.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0310] In this invention, the server includes a device for collecting information, an unstructured data processing device for analyzing the user's interests and tendencies from the collected information, and a selection device for formulating a plan based on the extracted interests and tendencies. This enables the effective delivery of advertisements that match the individual interests of users and the accurate evaluation of the effectiveness of those advertisements, thereby optimizing the advertising strategy and improving the user experience.

[0311] A "device for collecting information" is a device that automatically acquires data on web pages and user behavior on the internet.

[0312] An "unstructured data processing device" is a device that analyzes acquired data to effectively extract users' interests and trends.

[0313] A "selection device" is a device that develops personalized plans based on the extracted interests and tendencies.

[0314] An "output device" is a device that generates advertising content based on a formulated plan and delivers it to each user in an optimized format.

[0315] A "return evaluation device" is a device used to evaluate the effectiveness of delivered advertisements and to improve the data analysis and planning processes.

[0316] "Advertising content" refers to data in media format that includes promotional material generated based on specific user attributes.

[0317] "Collected information" refers to digital data, including web search behavior and social network activity.

[0318] "Personalized advertising" refers to advertisements that contain personalized messages, generated based on a specific user's interests and behavioral history.

[0319] The system for implementing the present invention mainly consists of a server and a terminal. First, the server uses a device for collecting information. This device has the function of automatically acquiring data on web pages and user behavior on the internet. The data includes web search behavior and behavior on social networks.

[0320] Next, the server uses an unstructured data processing device to analyze the collected information. This device utilizes a generative AI model to effectively extract users' interests and tendencies. Based on the analysis results, the server activates a selection device and develops a personalized plan based on the extracted interests and tendencies.

[0321] Next, the server uses an output device to generate and distribute advertising content based on the formulated plan. This device has the function of displaying advertisements in a format optimized for each user. On the user's terminal, the delivered advertisements can be viewed in real time.

[0322] Furthermore, the server uses a return evaluation device to assess the effectiveness of the delivered advertisements. Based on the acquired evaluation results, this device generates feedback data to improve the processes of the unstructured data processing device and the selection device.

[0323] For example, if a user shows interest in eco-friendly products, the server generates personalized advertising content such as "Check out our new eco-friendly products!" and delivers it to that user.

[0324] A concrete example of a prompt using a generative AI model would be the instruction, "Create advertisements tailored to the user's interests based on the web pages they have recently visited."

[0325] By implementing such a system, advertisements tailored to individual user interests can be effectively delivered, optimizing strategies and improving the user experience.

[0326] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0327] Step 1:

[0328] As an initial step in information gathering, the server acquires data on internet pages and user behavior. Using web search behavior and social network behavior data as input, the data collection process via agents begins. The output is raw data used for subsequent analysis.

[0329] Step 2:

[0330] The server feeds the collected raw data to an unstructured data processing unit for analysis. Using the collected data as input, a generative AI model is employed to identify the user's interests and tendencies. As a result of text analysis using natural language processing technology, the user's areas of interest and behavioral trends are output.

[0331] Step 3:

[0332] The server drives the selection mechanism based on the generated insights and formulates an advertising plan. The input is the user's interests and tendencies obtained in the previous step, and the output is the generation of personalized advertising messages and campaign plans. Specifically, it constructs prompt sentences based on specific user attributes and sends them to the generation AI model.

[0333] Step 4:

[0334] The server uses an output device to generate and deliver advertising content according to the formulated plan. The input is the advertising plan, which is the output in step 3, and the output is the advertising content formatted in the optimal format. In terms of delivery, the analyzed advertisement is displayed on the user's device in real time via Google AdMob or other advertising platforms.

[0335] Step 5:

[0336] The server activates a feedback evaluation system to assess the effectiveness of the advertisement. The input received is user interaction data (e.g., ad click-through rate and time spent on the page), from which quantitative evaluation metrics are generated. The output is feedback data generated using data analysis techniques, which serves as a guideline for adjusting future advertising strategies to optimize them.

[0337] 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.

[0338] This invention relates to a system that uses an emotion engine, which is capable of collecting large amounts of information and recognizing users' interests, trends, and emotions, to formulate advertising strategies and generate and deliver personalized advertisements. In particular, this invention describes a form that enables more accurate ad delivery by combining it with an emotion engine.

[0339] Data collection and emotion recognition

[0340] The server collects data in real time from internet sources. In addition to search queries and click data, it also collects user-generated text and audio data. This data is stored in a database and then analyzed by a sentiment engine.

[0341] The emotion engine uses natural language processing technology to analyze text and audio data and extract the user's emotional state. This process provides information about the emotions the user is experiencing.

[0342] Insight generation and strategy formulation

[0343] The server integrates the emotional data extracted by the emotion engine with the interests and trends of other users to generate deeper insights. This provides advanced, emotion-based insights that go beyond mere interest observations.

[0344] Furthermore, we develop advertising strategies based on these insights. By considering emotional information and tailoring messages accordingly, we can deliver advertisements that resonate with users' feelings.

[0345] Ad generation and delivery

[0346] The server generates personalized ads that take emotions into account. The generation AI designs ads that include creative elements that match the target's emotions and delivers them through specific media channels.

[0347] The device displays emotion-based advertisements at the optimal time while the user is online. This allows users to receive content that resonates with their emotions.

[0348] Effectiveness measurement and feedback

[0349] The server analyzes the response and effectiveness of the delivered ads. Click-through rates, viewing time, and emotional response tracking data are used.

[0350] The collected performance data is used to optimize the entire system, and is cyclically utilized to improve the accuracy of the emotion engine and the effectiveness of advertising strategies.

[0351] As a concrete example, when an e-commerce platform sells new fashion items, the server not only analyzes search behavior and social media posts based on "fashion" and "trend" related data, but also uses an emotion engine to detect when users have positive emotions. The server then generates and delivers advertisements that evoke these positive emotions to users, further increasing their purchase intent. In this process, users become emotionally connected to the brand, which can lead to further improvements in conversion rates.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The server collects big data from internet sources. This includes search queries, click data, text messages, social media posts, and voice input. After collection, the data is organized into a database.

[0355] Step 2:

[0356] The server uses an emotion engine to analyze the user's emotions from the collected data. Specifically, it employs natural language processing and speech emotion analysis to extract the user's emotional state from text and audio data.

[0357] Step 3:

[0358] The server combines sentiment data and interest data to generate integrated insights. These insights are recorded to match the individual user's tendencies and emotions and are used as the basis for advertising strategies.

[0359] Step 4:

[0360] The server develops optimal advertising strategies based on integrated insights. It adjusts ad messages and creatives considering the emotional state of target users. The strategy also includes where and when ads are delivered.

[0361] Step 5:

[0362] The server generates personalized ads based on emotions. Using generative AI, it designs compelling ad creatives that match the user's emotional state.

[0363] Step 6:

[0364] The device displays ads at the appropriate time based on the user's online activity. Because the ads are aligned with the user's emotions, higher engagement can be expected.

[0365] Step 7:

[0366] The server monitors the effectiveness of advertisements and analyzes the collected data. It monitors various metrics, including click-through rates, conversion rates, and user engagement data.

[0367] Step 8:

[0368] Based on the analysis results, the server improves the overall advertising strategy and sentiment engine of the system through feedback. This makes it possible to enhance the effectiveness of the next advertising campaign.

[0369] (Example 2)

[0370] 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".

[0371] In today's information-saturated environment, accurately understanding users' emotions and interests and effectively delivering advertisements based on them is difficult, and building an effective feedback system presents challenges. Conventional systems have problems in that they cannot adequately generate personalized advertisements that take emotions into account, nor can they optimize the subsequent effectiveness of those advertisements.

[0372] 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.

[0373] In this invention, the server includes means for collecting large amounts of information, means for integrating emotional information and interest data to generate advanced insights, and means for generating and delivering personalized advertisements based on emotions. This makes it possible to deliver advertisements that match the user's emotions, and to continuously feed back the effects and optimize the entire system.

[0374] "Large-scale information" refers to a vast amount of data collected from diverse sources, including data formats such as text, audio, and images.

[0375] "Emotional processing means" refers to technologies that use natural language processing techniques to analyze and extract the emotional state of a user from text and audio data.

[0376] "Insight" refers to deep insights gained from collected data, and in particular, it means advanced knowledge based on users' emotions and interests.

[0377] An "advertising strategy" refers to a plan that determines how to design, target, and deliver advertisements based on the insights gained.

[0378] "Generation methods" refer to the technologies and processes used to generate creative advertising content based on users' emotions and interests.

[0379] "Feedback methods" refer to the process of analyzing the effectiveness of delivered advertisements, optimizing the entire system based on the data obtained, and making improvements.

[0380] "User-generated elements" refer to content and behavioral data generated by users on the internet, including social media posts and search queries.

[0381] "Personalized advertising" refers to advertisements that are individually customized according to the emotional state and interests of a particular user.

[0382] This invention is a system that collects large amounts of information and generates and delivers personalized advertisements based on users' emotions and interests. Specifically, it is configured as follows:

[0383] Data collection and analysis

[0384] First, the server collects data from various sources on the internet. This process utilizes APIs and web scraping techniques. The collected data includes search queries, click data, and user-generated elements such as text and audio data. This data is stored in a database as structured data and later analyzed.

[0385] Next, the server uses emotion recognition technology to analyze the user's emotional state from the accumulated data. This analysis employs natural language processing technology, with generative AI models such as BERT and GPT being used as specific examples.

[0386] Insight generation and ad generation

[0387] After sentiment analysis is complete, the server integrates sentiment information and interest data to generate insights for advertising operations. Based on these insights, the server uses a generative AI model to design sentiment-driven creative advertisements. At this time, the AI ​​model is given instructions such as, "Create an advertising message that evokes positive emotions in women in their 20s."

[0388] Ad delivery and performance measurement

[0389] The generated personalized ads are delivered to the user at the optimal time through their device. For example, ads are displayed when the user is online, providing an emotionally resonant advertising experience.

[0390] Subsequently, the server measures the effectiveness of the delivered ads and utilizes the feedback data to optimize the entire system. Data such as click-through rates, viewing time, and emotional responses are analyzed to improve ads and enhance the accuracy of the emotional engine. This cycle allows the system to continuously evolve and provide more effective advertising strategies.

[0391] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0392] Step 1:

[0393] The server collects data from diverse sources. As input, it uses APIs and scraping techniques to obtain data from websites, social media, search queries, and other sources. As output, the acquired data undergoes initial processing and is stored in a database. For example, to collect posts containing specific keywords, it uses the Twitter API to gather relevant tweets.

[0394] Step 2:

[0395] The server supplies accumulated data to the emotion engine and performs emotion analysis. Text and audio data extracted from the database are used as input. Metadata indicating the user's emotional state is generated as output. Specifically, natural language processing models such as BERT and GPT are used to extract emotion labels such as "happy" and "sad" from the text data.

[0396] Step 3:

[0397] The server integrates sentiment data with other user data to generate insights. It uses sentiment labels and user behavior data (e.g., browsing history) as input. The output is insight data that includes each user's interests and sentiment tendencies. For example, if it determines that a woman in her 20s has recently made many positive posts, the insight "increase in positive sentiment" is obtained.

[0398] Step 4:

[0399] The server designs personalized ads using a generative AI model. It uses insight data and predefined ad templates as input. The output is ad content optimized for individual users. Specifically, it generates an ad that matches the "increase in positive emotions," such as an ad for "enjoying new fashion items."

[0400] Step 5:

[0401] The device delivers generated personalized ads to the user at the appropriate time. Inputs include the user's online activity and schedule. Outputs include ad banners and videos displayed while the user is browsing. Specifically, ads are displayed in real time when the user is visiting a particular webpage.

[0402] Step 6:

[0403] The server measures the effectiveness of delivered advertisements and optimizes the system. It collects data such as ad click-through rates, viewing time, and user response as input. As output, this data is used as analytical results to improve advertising strategies. Specifically, it determines whether a particular ad message is achieving the expected results and incorporates the feedback into the system.

[0404] (Application Example 2)

[0405] 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."

[0406] Traditional advertising delivery systems primarily rely on ad targeting based on basic user interests and click data, and have not yet reached the point of personalizing ads by considering the user's emotional state. As a result, there is a challenge in that ads cannot be delivered in response to the user's emotions in real time, and the effectiveness of advertising cannot be maximized.

[0407] 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.

[0408] In this invention, the server includes means for collecting large amounts of data, a generation device for extracting user interests, trends, and emotions from the collected data, and a decision device for formulating advertising operation policies based on the extracted interests, trends, and emotions. This makes it possible to deliver advertisements at the optimal timing according to the user's emotional state.

[0409] "Large-scale data" refers to large amounts of information in any form collected from the internet or from users' devices.

[0410] A "generating device" refers to a system that analyzes users' interests, trends, and emotions from collected data and extracts necessary information.

[0411] A "decision-making device" refers to a system used to formulate advertising management policies based on data obtained from a generation device.

[0412] "Advertising management policy" refers to a personalized advertising strategy based on specific user attributes and emotions.

[0413] "Emotional state" refers to the psychological state a user is experiencing at a particular moment, and it is an important metric in the creation and delivery of advertisements.

[0414] "Delivery device" refers to equipment or systems used to deliver selected advertisements to the user's device.

[0415] To realize this invention, a server first collects large amounts of data in real time. The data to be collected includes user search queries, communication data, and voice data. This requires that the smartphone or computer is connected to the internet. By employing a data collection bot that runs using TensorFlow, the server can efficiently collect diverse information.

[0416] The collected data is then processed by a generator on the server. This generator uses the Google Cloud Natural Language API to analyze the data and determine user interests, trends, and sentiments. The analyzed data is sent to a decision-making system that develops the operational strategy for advertising campaigns. Based on the insights gained by the sentiment engine, this decision-making system generates personalized ads tailored to specific user attributes.

[0417] Next, the generated advertisements are optimized by prompts from a generation AI model and delivered to the device. OpenAI's GPT model is used to formulate these prompts and generate the ad copy. The generated advertisements are then sent to the user's smartphone via a distribution device. This enables the delivery of advertisements at the optimal timing based on the user's emotional state. For example, when a user is relaxed, an advertisement for a new novel can be presented with creative content that matches their mood, stimulating their desire to purchase.

[0418] An example of a prompt would be, "Create promotional copy that appeals to users enjoying a relaxing afternoon and captures the essence of a new novel that resonates with their mood."

[0419] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0420] Step 1:

[0421] The server collects large amounts of data from the internet and user devices. It takes search queries, communication data, and audio data as input. TensorFlow is used to transform the collected data into a structured format and store it in a database.

[0422] Step 2:

[0423] The server passes the collected data to the generator, which analyzes it using the Google Cloud Natural Language API. The input is the data collected in step 1. The generator uses natural language processing technology to extract user interests, trends, and emotions from the data and outputs the analysis results.

[0424] Step 3:

[0425] The server sends the analysis results to the decision-making unit. The decision-making unit uses the user's interests, trends, and sentiment data obtained as input to formulate advertising management policies. In this process, it outputs personalized policies based on specific user attributes.

[0426] Step 4:

[0427] The server generates ad copy using a generative AI model based on the determined advertising management policy. Here, the input is the policy formulated in step 3. Using OpenAI's GPT model and provided with prompt examples, it outputs the optimal ad content.

[0428] Step 5:

[0429] The device delivers the generated advertisement to the user's smartphone. The input is the advertisement copy created in step 4. The delivery device sends the advertisement in a way that is tailored to the user's emotional state and timing.

[0430] Step 6:

[0431] The server measures the effectiveness of delivered advertisements. The input is user behavior data after receiving the advertisement. It collects performance data such as click-through rates, viewing time, and additional feedback, and uses a feedback mechanism to optimize the entire system. Based on the collected data, more precise analysis and improvements to advertising strategies are made.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] [Third Embodiment]

[0436] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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".

[0448] The present invention aims to efficiently collect and analyze large amounts of information, extract deep consumer insights, and formulate advertising strategies based on those insights. An embodiment of this system will be described in detail.

[0449] Data Acquisition and Preprocessing

[0450] The server automatically retrieves data from various sources on the internet, such as search engines, social media, and blogs. This data includes search queries and click data. The collected data is first structured and then preprocessed, including noise reduction and duplicate removal.

[0451] Insight generation

[0452] The server launches a generative AI model to analyze the pre-processed data. This model utilizes natural language processing techniques to extract user interests, trends, and emotions from the text data. These results are recorded as "insights."

[0453] Planning of operational strategies

[0454] The server develops advertising strategies based on extracted insights. It plans personalized advertising campaigns, taking into account factors such as ad placement, timing, and target audience.

[0455] Ad generation and delivery

[0456] The server generates specific advertising content based on the planned advertising strategy. Using generation AI, it creates various formats of text ads, banner ads, or video ads and delivers them in the most suitable format.

[0457] The device provides an optimal user experience by displaying appropriate advertisements at planned times on websites and applications that the user accesses.

[0458] Measuring effectiveness and improving strategies

[0459] The server continuously monitors metrics such as click-through rates, conversion rates, and time spent on the site to quantitatively evaluate the performance of delivered ads. This data is used to improve advertising strategies and fine-tune AI models.

[0460] As a concrete example, when an online store sells a new product, the server analyzes keywords such as "new product," "trend," and "purchase intent," and extracts insights that users are particularly interested in "eco-friendly products." The server then generates advertisements that highlight the features of eco-friendly products and delivers them to a specific target audience. Through this process, the online store can achieve a higher conversion rate.

[0461] The following describes the processing flow.

[0462] Step 1:

[0463] The server collects data from specified sources. This is an automated process using web crawlers and APIs, ingesting search queries and click data and storing it in a database.

[0464] Step 2:

[0465] The server performs a cleaning process on the collected data. This includes removing duplicate data, handling missing values, and filtering out noisy data, preparing the data for analysis.

[0466] Step 3:

[0467] The server launches a generative AI model to extract consumer insights from pre-processed data. Here, natural language processing algorithms are used to analyze user interests and trends from text data and generate insights.

[0468] Step 4:

[0469] The server develops advertising strategies based on the insights gained. This involves determining the target audience, appropriate media channels, and delivery timing for the ads, and is carried out using operational expertise.

[0470] Step 5:

[0471] The server generates advertising content based on the advertising strategy. It utilizes generation AI to create personalized ads and materialize them as text and visual content.

[0472] Step 6:

[0473] The device displays advertisements at appropriate times while the user is using websites and applications. These advertisements are personalized based on the user's profile and browsing history.

[0474] Step 7:

[0475] The server monitors the performance of delivered ads. It collects click-through rates, conversion rates, and engagement data and stores them in a database.

[0476] Step 8:

[0477] The server analyzes the collected performance data to optimize advertising strategies and generative models. This feedback loop improves the effectiveness of subsequent advertising campaigns.

[0478] (Example 1)

[0479] 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."

[0480] In recent years, a vast amount of information exists on the internet, and accurate data collection and analysis are essential for its efficient use. However, linking this data to advertisements based on user preferences requires significant computing resources and time using conventional methods, making it difficult to quickly formulate effective advertising strategies. To solve this problem, there is a need for more efficient and effective data processing and advertising strategy planning methods.

[0481] 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.

[0482] In this invention, the server includes means for acquiring a wide range of data from diverse information sources, preprocessing means for structuring the acquired data and performing noise reduction and duplicate removal, and generation means for extracting user interests and trends from the preprocessed data using natural language processing technology. This makes it possible to analyze large amounts of data quickly and accurately, and to efficiently formulate effective advertising strategies based on user preferences.

[0483] "Information source" refers to the underlying medium or platform from which data is obtained, including communication networks and computer networks on the Internet.

[0484] "Data" refers to various forms of information obtained from user actions and behaviors, specifically records such as search actions and click activities.

[0485] "Preprocessing" is the process of organizing acquired data into a state that can be analyzed, and includes data formatting such as noise reduction and duplicate removal.

[0486] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to extract user interests and trends.

[0487] "Generation means" refers to functions within a system that generate useful information from data, and in particular, play a role in extracting insights necessary for advertising strategies.

[0488] "Decision-making tools" refer to the processes and methods used to formulate advertising strategies based on generated information, determining the optimal advertising policy based on the insights gained.

[0489] An "advertising strategy" is a plan and guideline for optimizing the placement, content, and targeting of advertisements, designed based on user interests and trends.

[0490] "Feedback methods" refer to processes and technologies used to analyze the effectiveness of delivered advertisements and improve the entire system based on the results obtained.

[0491] In implementing this invention, the server first acquires data from a wide range of sources. Specifically, the server collects data from online platforms such as search engines, social media, and blogs on the internet. Such data includes user search behavior and click activity.

[0492] Next, the server preprocesses the acquired data. Preprocessing involves structuring the data and performing noise reduction and duplicate removal to prepare it for analysis. It is assumed that the Python Pandas library will be used for data processing.

[0493] Furthermore, the server utilizes natural language processing technology to extract user interests and behaviors from pre-processed data using generative AI models. This process generates insights derived from user behavior. Natural language processing libraries such as Hugging Face Transformers may be used in this part.

[0494] The server develops an advertising strategy based on the extracted insights. This strategy optimizes ad placement, timing, and target audience. Following this strategy, the server uses generative AI to generate ads in various formats and delivers text ads, banner ads, video ads, and more.

[0495] The generated advertisements are displayed on websites and applications that the user accesses via their device. This allows the device to provide a user experience optimized for the user.

[0496] As a concrete example, when an online store launches a new product, the server analyzes data based on keywords such as "new product," "trend," and "purchase intent," and extracts user interest, particularly in "eco-friendly products." It then generates advertisements highlighting the features of eco-friendly products and delivers these advertisements to specific target audiences. This system enables the online store to achieve a higher conversion rate.

[0497] An example of a prompt for a generative AI model is, "How can I analyze user interests and extract specific insights?"

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The server collects data from various sources on the internet. This input includes search actions and click activity from online platforms such as search engines, social media, and blogs. The server connects to these sources, retrieves vast amounts of data via APIs, and obtains output by storing it in local storage. Specifically, the server schedules to periodically access these platforms to retrieve the latest data.

[0501] Step 2:

[0502] The server preprocesses the collected data. The input for this step is the raw data obtained in step 1. Preprocessing includes data structuring, noise reduction, and duplicate removal. The output is a clean dataset suitable for analysis. The server uses the Python Pandas library to filter the data and perform specific data manipulation such as filling in missing values.

[0503] Step 3:

[0504] The server performs analysis using pre-processed data to extract user interests and trends. The input for this step is the clean data generated in step 2. The server activates a generative AI model and uses natural language processing techniques to analyze the data, extracting user interests and trends, and outputting this as insights. Specifically, the server uses the Hugging Face Transformers library to input text data into the model and analyze the results.

[0505] Step 4:

[0506] The server develops an advertising strategy based on the extracted insights. The input for this step is the user insights obtained in step 3. The server designs the advertising campaign, taking into account the placement and timing of the ads and the target audience. In this process, it outputs customized ad details. Specifically, the server utilizes digital marketing management software to set multiple ad parameters.

[0507] Step 5:

[0508] The server generates specific advertising content based on the formulated advertising strategy. The input is the campaign parameters determined in step 4. The server uses a generation AI to generate multiple types of ads, such as text ads, banner ads, and video ads, and sends them to the ad delivery system for output. Specifically, the server launches the ad generation tool and prepares the materials for posting.

[0509] Step 6:

[0510] The device presents the generated advertisement to the user. The input for this step is the advertisement content generated in step 5. The device displays the advertisement at the appropriate time on the website or application the user is accessing and generates user engagement data as output. The device calls and renders the advertisement on the screen in real time during each user session. It also operates a function to record clicks and viewing time after the advertisement is displayed.

[0511] Step 7:

[0512] The server evaluates ad performance and receives feedback. The input for this step is the user engagement data obtained in step 6. The server analyzes this data and provides feedback on areas for improvement, resulting in output that adjusts the generative AI model and ad strategy. Specifically, the server uses analytics tools to calculate metrics such as click-through rates and conversion rates. This allows strategies to optimize ad effectiveness to be reflected in the next campaign.

[0513] (Application Example 1)

[0514] 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."

[0515] Traditional advertising strategies have faced challenges in adequately delivering ads based on individual user interests and behaviors. Furthermore, accurate measurement of advertising effectiveness has been lacking, making it difficult to improve strategies. Therefore, there is a need to maximize advertising effectiveness and improve the user experience.

[0516] 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.

[0517] In this invention, the server includes a device for collecting information, an unstructured data processing device for analyzing the user's interests and tendencies from the collected information, and a selection device for formulating a plan based on the extracted interests and tendencies. This enables the effective delivery of advertisements that match the individual interests of users and the accurate evaluation of the effectiveness of those advertisements, thereby optimizing the advertising strategy and improving the user experience.

[0518] A "device for collecting information" is a device that automatically acquires data on web pages and user behavior on the internet.

[0519] An "unstructured data processing device" is a device that analyzes acquired data to effectively extract users' interests and trends.

[0520] A "selection device" is a device that develops personalized plans based on the extracted interests and tendencies.

[0521] An "output device" is a device that generates advertising content based on a formulated plan and delivers it to each user in an optimized format.

[0522] A "return evaluation device" is a device used to evaluate the effectiveness of delivered advertisements and to improve the data analysis and planning processes.

[0523] "Advertising content" refers to data in media format that includes promotional material generated based on specific user attributes.

[0524] "Collected information" refers to digital data, including web search behavior and social network activity.

[0525] "Personalized advertising" refers to advertisements that contain personalized messages, generated based on a specific user's interests and behavioral history.

[0526] The system for implementing the present invention mainly consists of a server and a terminal. First, the server uses a device for collecting information. This device has the function of automatically acquiring data on web pages and user behavior on the internet. The data includes web search behavior and behavior on social networks.

[0527] Next, the server uses an unstructured data processing device to analyze the collected information. This device utilizes a generative AI model to effectively extract users' interests and tendencies. Based on the analysis results, the server activates a selection device and develops a personalized plan based on the extracted interests and tendencies.

[0528] Next, the server uses an output device to generate and distribute advertising content based on the formulated plan. This device has the function of displaying advertisements in a format optimized for each user. On the user's terminal, the delivered advertisements can be viewed in real time.

[0529] Furthermore, the server uses a return evaluation device to assess the effectiveness of the delivered advertisements. Based on the acquired evaluation results, this device generates feedback data to improve the processes of the unstructured data processing device and the selection device.

[0530] For example, if a user shows interest in eco-friendly products, the server generates personalized advertising content such as "Check out our new eco-friendly products!" and delivers it to that user.

[0531] A concrete example of a prompt using a generative AI model would be the instruction, "Create advertisements tailored to the user's interests based on the web pages they have recently visited."

[0532] By implementing such a system, advertisements tailored to individual user interests can be effectively delivered, optimizing strategies and improving the user experience.

[0533] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0534] Step 1:

[0535] As an initial step in information gathering, the server acquires data on internet pages and user behavior. Using web search behavior and social network behavior data as input, the data collection process via agents begins. The output is raw data used for subsequent analysis.

[0536] Step 2:

[0537] The server feeds the collected raw data to an unstructured data processing unit for analysis. Using the collected data as input, a generative AI model is employed to identify the user's interests and tendencies. As a result of text analysis using natural language processing technology, the user's areas of interest and behavioral trends are output.

[0538] Step 3:

[0539] The server drives the selection mechanism based on the generated insights and formulates an advertising plan. The input is the user's interests and tendencies obtained in the previous step, and the output is the generation of personalized advertising messages and campaign plans. Specifically, it constructs prompt sentences based on specific user attributes and sends them to the generation AI model.

[0540] Step 4:

[0541] The server uses an output device to generate and deliver advertising content according to the formulated plan. The input is the advertising plan, which is the output in step 3, and the output is the advertising content formatted in the optimal format. In terms of delivery, the analyzed advertisement is displayed on the user's device in real time via Google AdMob or other advertising platforms.

[0542] Step 5:

[0543] The server activates a feedback evaluation system to assess the effectiveness of the advertisement. The input received is user interaction data (e.g., ad click-through rate and time spent on the page), from which quantitative evaluation metrics are generated. The output is feedback data generated using data analysis techniques, which serves as a guideline for adjusting future advertising strategies to optimize them.

[0544] 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.

[0545] This invention relates to a system that uses an emotion engine, which is capable of collecting large amounts of information and recognizing users' interests, trends, and emotions, to formulate advertising strategies and generate and deliver personalized advertisements. In particular, this invention describes a form that enables more accurate ad delivery by combining it with an emotion engine.

[0546] Data collection and emotion recognition

[0547] The server collects data in real time from internet sources. In addition to search queries and click data, it also collects user-generated text and audio data. This data is stored in a database and then analyzed by a sentiment engine.

[0548] The emotion engine uses natural language processing technology to analyze text and audio data and extract the user's emotional state. This process provides information about the emotions the user is experiencing.

[0549] Insight generation and strategy formulation

[0550] The server integrates the emotional data extracted by the emotion engine with the interests and trends of other users to generate deeper insights. This provides advanced, emotion-based insights that go beyond mere interest observations.

[0551] Furthermore, we develop advertising strategies based on these insights. By considering emotional information and tailoring messages accordingly, we can deliver advertisements that resonate with users' feelings.

[0552] Ad generation and delivery

[0553] The server generates personalized ads that take emotions into account. The generation AI designs ads that include creative elements that match the target's emotions and delivers them through specific media channels.

[0554] The device displays emotion-based advertisements at the optimal time while the user is online. This allows users to receive content that resonates with their emotions.

[0555] Effectiveness measurement and feedback

[0556] The server analyzes the response and effectiveness of the delivered ads. Click-through rates, viewing time, and emotional response tracking data are used.

[0557] The collected performance data is used to optimize the entire system, and is cyclically utilized to improve the accuracy of the emotion engine and the effectiveness of advertising strategies.

[0558] As a concrete example, when an e-commerce platform sells new fashion items, the server not only analyzes search behavior and social media posts based on "fashion" and "trend" related data, but also uses an emotion engine to detect when users have positive emotions. The server then generates and delivers advertisements that evoke these positive emotions to users, further increasing their purchase intent. In this process, users become emotionally connected to the brand, which can lead to further improvements in conversion rates.

[0559] The following describes the processing flow.

[0560] Step 1:

[0561] The server collects big data from internet sources. This includes search queries, click data, text messages, social media posts, and voice input. After collection, the data is organized into a database.

[0562] Step 2:

[0563] The server uses an emotion engine to analyze the user's emotions from the collected data. Specifically, it employs natural language processing and speech emotion analysis to extract the user's emotional state from text and audio data.

[0564] Step 3:

[0565] The server combines sentiment data and interest data to generate integrated insights. These insights are recorded to match the individual user's tendencies and emotions and are used as the basis for advertising strategies.

[0566] Step 4:

[0567] The server develops optimal advertising strategies based on integrated insights. It adjusts ad messages and creatives considering the emotional state of target users. The strategy also includes where and when ads are delivered.

[0568] Step 5:

[0569] The server generates personalized ads based on emotions. Using generative AI, it designs compelling ad creatives that match the user's emotional state.

[0570] Step 6:

[0571] The device displays ads at the appropriate time based on the user's online activity. Because the ads are aligned with the user's emotions, higher engagement can be expected.

[0572] Step 7:

[0573] The server monitors the effectiveness of advertisements and analyzes the collected data. It monitors various metrics, including click-through rates, conversion rates, and user engagement data.

[0574] Step 8:

[0575] Based on the analysis results, the server improves the overall advertising strategy and sentiment engine of the system through feedback. This makes it possible to enhance the effectiveness of the next advertising campaign.

[0576] (Example 2)

[0577] 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."

[0578] In today's information-saturated environment, accurately understanding users' emotions and interests and effectively delivering advertisements based on them is difficult, and building an effective feedback system presents challenges. Conventional systems have problems in that they cannot adequately generate personalized advertisements that take emotions into account, nor can they optimize the subsequent effectiveness of those advertisements.

[0579] 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.

[0580] In this invention, the server includes means for collecting large amounts of information, means for integrating emotional information and interest data to generate advanced insights, and means for generating and delivering personalized advertisements based on emotions. This makes it possible to deliver advertisements that match the user's emotions, and to continuously feed back the effects and optimize the entire system.

[0581] "Large-scale information" refers to a vast amount of data collected from diverse sources, including data formats such as text, audio, and images.

[0582] "Emotional processing means" refers to technologies that use natural language processing techniques to analyze and extract the emotional state of a user from text and audio data.

[0583] "Insight" refers to deep insights gained from collected data, and in particular, it means advanced knowledge based on users' emotions and interests.

[0584] An "advertising strategy" refers to a plan that determines how to design, target, and deliver advertisements based on the insights gained.

[0585] "Generation methods" refer to the technologies and processes used to generate creative advertising content based on users' emotions and interests.

[0586] "Feedback methods" refer to the process of analyzing the effectiveness of delivered advertisements, optimizing the entire system based on the data obtained, and making improvements.

[0587] "User-generated elements" refer to content and behavioral data generated by users on the internet, including social media posts and search queries.

[0588] "Personalized advertising" refers to advertisements that are individually customized according to the emotional state and interests of a particular user.

[0589] This invention is a system that collects large amounts of information and generates and delivers personalized advertisements based on users' emotions and interests. Specifically, it is configured as follows:

[0590] Data collection and analysis

[0591] First, the server collects data from various sources on the internet. This process utilizes APIs and web scraping techniques. The collected data includes search queries, click data, and user-generated elements such as text and audio data. This data is stored in a database as structured data and later analyzed.

[0592] Next, the server uses emotion recognition technology to analyze the user's emotional state from the accumulated data. This analysis employs natural language processing technology, with generative AI models such as BERT and GPT being used as specific examples.

[0593] Insight generation and ad generation

[0594] After sentiment analysis is complete, the server integrates sentiment information and interest data to generate insights for advertising operations. Based on these insights, the server uses a generative AI model to design sentiment-driven creative advertisements. At this time, the AI ​​model is given instructions such as, "Create an advertising message that evokes positive emotions in women in their 20s."

[0595] Ad delivery and performance measurement

[0596] The generated personalized ads are delivered to the user at the optimal time through their device. For example, ads are displayed when the user is online, providing an emotionally resonant advertising experience.

[0597] Subsequently, the server measures the effectiveness of the delivered ads and utilizes the feedback data to optimize the entire system. Data such as click-through rates, viewing time, and emotional responses are analyzed to improve ads and enhance the accuracy of the emotional engine. This cycle allows the system to continuously evolve and provide more effective advertising strategies.

[0598] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0599] Step 1:

[0600] The server collects data from diverse sources. As input, it uses APIs and scraping techniques to obtain data from websites, social media, search queries, and other sources. As output, the acquired data undergoes initial processing and is stored in a database. For example, to collect posts containing specific keywords, it uses the Twitter API to gather relevant tweets.

[0601] Step 2:

[0602] The server supplies accumulated data to the emotion engine and performs emotion analysis. Text and audio data extracted from the database are used as input. Metadata indicating the user's emotional state is generated as output. Specifically, natural language processing models such as BERT and GPT are used to extract emotion labels such as "happy" and "sad" from the text data.

[0603] Step 3:

[0604] The server integrates sentiment data with other user data to generate insights. It uses sentiment labels and user behavior data (e.g., browsing history) as input. The output is insight data that includes each user's interests and sentiment tendencies. For example, if it determines that a woman in her 20s has recently made many positive posts, the insight "increase in positive sentiment" is obtained.

[0605] Step 4:

[0606] The server designs personalized ads using a generative AI model. It uses insight data and predefined ad templates as input. The output is ad content optimized for individual users. Specifically, it generates an ad that matches the "increase in positive emotions," such as an ad for "enjoying new fashion items."

[0607] Step 5:

[0608] The device delivers generated personalized ads to the user at the appropriate time. Inputs include the user's online activity and schedule. Outputs include ad banners and videos displayed while the user is browsing. Specifically, ads are displayed in real time when the user is visiting a particular webpage.

[0609] Step 6:

[0610] The server measures the effectiveness of delivered advertisements and optimizes the system. It collects data such as ad click-through rates, viewing time, and user response as input. As output, this data is used as analytical results to improve advertising strategies. Specifically, it determines whether a particular ad message is achieving the expected results and incorporates the feedback into the system.

[0611] (Application Example 2)

[0612] 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."

[0613] Traditional advertising delivery systems primarily rely on ad targeting based on basic user interests and click data, and have not yet reached the point of personalizing ads by considering the user's emotional state. As a result, there is a challenge in that ads cannot be delivered in response to the user's emotions in real time, and the effectiveness of advertising cannot be maximized.

[0614] 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.

[0615] In this invention, the server includes means for collecting large amounts of data, a generation device for extracting user interests, trends, and emotions from the collected data, and a decision device for formulating advertising operation policies based on the extracted interests, trends, and emotions. This makes it possible to deliver advertisements at the optimal timing according to the user's emotional state.

[0616] "Large-scale data" refers to large amounts of information in any form collected from the internet or from users' devices.

[0617] A "generating device" refers to a system that analyzes users' interests, trends, and emotions from collected data and extracts necessary information.

[0618] A "decision-making device" refers to a system used to formulate advertising management policies based on data obtained from a generation device.

[0619] "Advertising management policy" refers to a personalized advertising strategy based on specific user attributes and emotions.

[0620] "Emotional state" refers to the psychological state a user is experiencing at a particular moment, and it is an important metric in the creation and delivery of advertisements.

[0621] "Delivery device" refers to equipment or systems used to deliver selected advertisements to the user's device.

[0622] To realize this invention, a server first collects large amounts of data in real time. The data to be collected includes user search queries, communication data, and voice data. This requires that the smartphone or computer is connected to the internet. By employing a data collection bot that runs using TensorFlow, the server can efficiently collect diverse information.

[0623] The collected data is then processed by a generator on the server. This generator uses the Google Cloud Natural Language API to analyze the data and determine user interests, trends, and sentiments. The analyzed data is sent to a decision-making system that develops the operational strategy for advertising campaigns. Based on the insights gained by the sentiment engine, this decision-making system generates personalized ads tailored to specific user attributes.

[0624] Next, the generated advertisements are optimized by prompts from a generation AI model and delivered to the device. OpenAI's GPT model is used to formulate these prompts and generate the ad copy. The generated advertisements are then sent to the user's smartphone via a distribution device. This enables the delivery of advertisements at the optimal timing based on the user's emotional state. For example, when a user is relaxed, an advertisement for a new novel can be presented with creative content that matches their mood, stimulating their desire to purchase.

[0625] An example of a prompt would be, "Create promotional copy that appeals to users enjoying a relaxing afternoon and captures the essence of a new novel that resonates with their mood."

[0626] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0627] Step 1:

[0628] The server collects large amounts of data from the internet and user devices. It takes search queries, communication data, and audio data as input. TensorFlow is used to transform the collected data into a structured format and store it in a database.

[0629] Step 2:

[0630] The server passes the collected data to the generator, which analyzes it using the Google Cloud Natural Language API. The input is the data collected in step 1. The generator uses natural language processing technology to extract user interests, trends, and emotions from the data and outputs the analysis results.

[0631] Step 3:

[0632] The server sends the analysis results to the decision-making unit. The decision-making unit uses the user's interests, trends, and sentiment data obtained as input to formulate advertising management policies. In this process, it outputs personalized policies based on specific user attributes.

[0633] Step 4:

[0634] The server generates ad copy using a generative AI model based on the determined advertising management policy. Here, the input is the policy formulated in step 3. Using OpenAI's GPT model and provided with prompt examples, it outputs the optimal ad content.

[0635] Step 5:

[0636] The device delivers the generated advertisement to the user's smartphone. The input is the advertisement copy created in step 4. The delivery device sends the advertisement in a way that is tailored to the user's emotional state and timing.

[0637] Step 6:

[0638] The server measures the effectiveness of delivered advertisements. The input is user behavior data after receiving the advertisement. It collects performance data such as click-through rates, viewing time, and additional feedback, and uses a feedback mechanism to optimize the entire system. Based on the collected data, more precise analysis and improvements to advertising strategies are made.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] [Fourth Embodiment]

[0643] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0644] 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.

[0645] 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).

[0646] 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.

[0647] 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.

[0648] 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).

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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".

[0656] The present invention aims to efficiently collect and analyze large amounts of information, extract deep consumer insights, and formulate advertising strategies based on those insights. An embodiment of this system will be described in detail.

[0657] Data Acquisition and Preprocessing

[0658] The server automatically retrieves data from various sources on the internet, such as search engines, social media, and blogs. This data includes search queries and click data. The collected data is first structured and then preprocessed, including noise reduction and duplicate removal.

[0659] Insight generation

[0660] The server launches a generative AI model to analyze the pre-processed data. This model utilizes natural language processing techniques to extract user interests, trends, and emotions from the text data. These results are recorded as "insights."

[0661] Planning of operational strategies

[0662] The server develops advertising strategies based on extracted insights. It plans personalized advertising campaigns, taking into account factors such as ad placement, timing, and target audience.

[0663] Ad generation and delivery

[0664] The server generates specific advertising content based on the planned advertising strategy. Using generation AI, it creates various formats of text ads, banner ads, or video ads and delivers them in the most suitable format.

[0665] The device provides an optimal user experience by displaying appropriate advertisements at planned times on websites and applications that the user accesses.

[0666] Measuring effectiveness and improving strategies

[0667] The server continuously monitors metrics such as click-through rates, conversion rates, and time spent on the site to quantitatively evaluate the performance of delivered ads. This data is used to improve advertising strategies and fine-tune AI models.

[0668] As a concrete example, when an online store sells a new product, the server analyzes keywords such as "new product," "trend," and "purchase intent," and extracts insights that users are particularly interested in "eco-friendly products." The server then generates advertisements that highlight the features of eco-friendly products and delivers them to a specific target audience. Through this process, the online store can achieve a higher conversion rate.

[0669] The following describes the processing flow.

[0670] Step 1:

[0671] The server collects data from specified sources. This is an automated process using web crawlers and APIs, ingesting search queries and click data and storing it in a database.

[0672] Step 2:

[0673] The server performs a cleaning process on the collected data. This includes removing duplicate data, handling missing values, and filtering out noisy data, preparing the data for analysis.

[0674] Step 3:

[0675] The server launches a generative AI model to extract consumer insights from pre-processed data. Here, natural language processing algorithms are used to analyze user interests and trends from text data and generate insights.

[0676] Step 4:

[0677] The server develops advertising strategies based on the insights gained. This involves determining the target audience, appropriate media channels, and delivery timing for the ads, and is carried out using operational expertise.

[0678] Step 5:

[0679] The server generates advertising content based on the advertising strategy. It utilizes generation AI to create personalized ads and materialize them as text and visual content.

[0680] Step 6:

[0681] The device displays advertisements at appropriate times while the user is using websites and applications. These advertisements are personalized based on the user's profile and browsing history.

[0682] Step 7:

[0683] The server monitors the performance of delivered ads. It collects click-through rates, conversion rates, and engagement data and stores them in a database.

[0684] Step 8:

[0685] The server analyzes the collected performance data to optimize advertising strategies and generative models. This feedback loop improves the effectiveness of subsequent advertising campaigns.

[0686] (Example 1)

[0687] 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".

[0688] In recent years, a vast amount of information exists on the internet, and accurate data collection and analysis are essential for its efficient use. However, linking this data to advertisements based on user preferences requires significant computing resources and time using conventional methods, making it difficult to quickly formulate effective advertising strategies. To solve this problem, there is a need for more efficient and effective data processing and advertising strategy planning methods.

[0689] 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.

[0690] In this invention, the server includes means for acquiring a wide range of data from diverse information sources, preprocessing means for structuring the acquired data and performing noise reduction and duplicate removal, and generation means for extracting user interests and trends from the preprocessed data using natural language processing technology. This makes it possible to analyze large amounts of data quickly and accurately, and to efficiently formulate effective advertising strategies based on user preferences.

[0691] "Information source" refers to the underlying medium or platform from which data is obtained, including communication networks and computer networks on the Internet.

[0692] "Data" refers to various forms of information obtained from user actions and behaviors, specifically records such as search actions and click activities.

[0693] "Preprocessing" is the process of organizing acquired data into a state that can be analyzed, and includes data formatting such as noise reduction and duplicate removal.

[0694] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to extract user interests and trends.

[0695] "Generation means" refers to functions within a system that generate useful information from data, and in particular, play a role in extracting insights necessary for advertising strategies.

[0696] "Decision-making tools" refer to the processes and methods used to formulate advertising strategies based on generated information, determining the optimal advertising policy based on the insights gained.

[0697] An "advertising strategy" is a plan and guideline for optimizing the placement, content, and targeting of advertisements, designed based on user interests and trends.

[0698] "Feedback methods" refer to processes and technologies used to analyze the effectiveness of delivered advertisements and improve the entire system based on the results obtained.

[0699] In implementing this invention, the server first acquires data from a wide range of sources. Specifically, the server collects data from online platforms such as search engines, social media, and blogs on the internet. Such data includes user search behavior and click activity.

[0700] Next, the server preprocesses the acquired data. Preprocessing involves structuring the data and performing noise reduction and duplicate removal to prepare it for analysis. It is assumed that the Python Pandas library will be used for data processing.

[0701] Furthermore, the server utilizes natural language processing technology to extract user interests and behaviors from pre-processed data using generative AI models. This process generates insights derived from user behavior. Natural language processing libraries such as Hugging Face Transformers may be used in this part.

[0702] The server develops an advertising strategy based on the extracted insights. This strategy optimizes ad placement, timing, and target audience. Following this strategy, the server uses generative AI to generate ads in various formats and delivers text ads, banner ads, video ads, and more.

[0703] The generated advertisements are displayed on websites and applications that the user accesses via their device. This allows the device to provide a user experience optimized for the user.

[0704] As a concrete example, when an online store launches a new product, the server analyzes data based on keywords such as "new product," "trend," and "purchase intent," and extracts user interest, particularly in "eco-friendly products." It then generates advertisements highlighting the features of eco-friendly products and delivers these advertisements to specific target audiences. This system enables the online store to achieve a higher conversion rate.

[0705] An example of a prompt for a generative AI model is, "How can I analyze user interests and extract specific insights?"

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] The server collects data from various sources on the internet. This input includes search actions and click activity from online platforms such as search engines, social media, and blogs. The server connects to these sources, retrieves vast amounts of data via APIs, and obtains output by storing it in local storage. Specifically, the server schedules to periodically access these platforms to retrieve the latest data.

[0709] Step 2:

[0710] The server preprocesses the collected data. The input for this step is the raw data obtained in step 1. Preprocessing includes data structuring, noise reduction, and duplicate removal. The output is a clean dataset suitable for analysis. The server uses the Python Pandas library to filter the data and perform specific data manipulation such as filling in missing values.

[0711] Step 3:

[0712] The server performs analysis using pre-processed data to extract user interests and trends. The input for this step is the clean data generated in step 2. The server activates a generative AI model and uses natural language processing techniques to analyze the data, extracting user interests and trends, and outputting this as insights. Specifically, the server uses the Hugging Face Transformers library to input text data into the model and analyze the results.

[0713] Step 4:

[0714] The server develops an advertising strategy based on the extracted insights. The input for this step is the user insights obtained in step 3. The server designs the advertising campaign, taking into account the placement and timing of the ads and the target audience. In this process, it outputs customized ad details. Specifically, the server utilizes digital marketing management software to set multiple ad parameters.

[0715] Step 5:

[0716] The server generates specific advertising content based on the formulated advertising strategy. The input is the campaign parameters determined in step 4. The server uses a generation AI to generate multiple types of ads, such as text ads, banner ads, and video ads, and sends them to the ad delivery system for output. Specifically, the server launches the ad generation tool and prepares the materials for posting.

[0717] Step 6:

[0718] The device presents the generated advertisement to the user. The input for this step is the advertisement content generated in step 5. The device displays the advertisement at the appropriate time on the website or application the user is accessing and generates user engagement data as output. The device calls and renders the advertisement on the screen in real time during each user session. It also operates a function to record clicks and viewing time after the advertisement is displayed.

[0719] Step 7:

[0720] The server evaluates ad performance and receives feedback. The input for this step is the user engagement data obtained in step 6. The server analyzes this data and provides feedback on areas for improvement, resulting in output that adjusts the generative AI model and ad strategy. Specifically, the server uses analytics tools to calculate metrics such as click-through rates and conversion rates. This allows strategies to optimize ad effectiveness to be reflected in the next campaign.

[0721] (Application Example 1)

[0722] 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".

[0723] Traditional advertising strategies have faced challenges in adequately delivering ads based on individual user interests and behaviors. Furthermore, accurate measurement of advertising effectiveness has been lacking, making it difficult to improve strategies. Therefore, there is a need to maximize advertising effectiveness and improve the user experience.

[0724] 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.

[0725] In this invention, the server includes a device for collecting information, an unstructured data processing device for analyzing the user's interests and tendencies from the collected information, and a selection device for formulating a plan based on the extracted interests and tendencies. This enables the effective delivery of advertisements that match the individual interests of users and the accurate evaluation of the effectiveness of those advertisements, thereby optimizing the advertising strategy and improving the user experience.

[0726] A "device for collecting information" is a device that automatically acquires data on web pages and user behavior on the internet.

[0727] An "unstructured data processing device" is a device that analyzes acquired data to effectively extract users' interests and trends.

[0728] A "selection device" is a device that develops personalized plans based on the extracted interests and tendencies.

[0729] An "output device" is a device that generates advertising content based on a formulated plan and delivers it to each user in an optimized format.

[0730] A "return evaluation device" is a device used to evaluate the effectiveness of delivered advertisements and to improve the data analysis and planning processes.

[0731] "Advertising content" refers to data in media format that includes promotional material generated based on specific user attributes.

[0732] "Collected information" refers to digital data, including web search behavior and social network activity.

[0733] "Personalized advertising" refers to advertisements that contain personalized messages, generated based on a specific user's interests and behavioral history.

[0734] The system for implementing the present invention mainly consists of a server and a terminal. First, the server uses a device for collecting information. This device has the function of automatically acquiring data on web pages and user behavior on the internet. The data includes web search behavior and behavior on social networks.

[0735] Next, the server uses an unstructured data processing device to analyze the collected information. This device utilizes a generative AI model to effectively extract users' interests and tendencies. Based on the analysis results, the server activates a selection device and develops a personalized plan based on the extracted interests and tendencies.

[0736] Next, the server uses an output device to generate and distribute advertising content based on the formulated plan. This device has the function of displaying advertisements in a format optimized for each user. On the user's terminal, the delivered advertisements can be viewed in real time.

[0737] Furthermore, the server uses a return evaluation device to assess the effectiveness of the delivered advertisements. Based on the acquired evaluation results, this device generates feedback data to improve the processes of the unstructured data processing device and the selection device.

[0738] For example, if a user shows interest in eco-friendly products, the server generates personalized advertising content such as "Check out our new eco-friendly products!" and delivers it to that user.

[0739] A concrete example of a prompt using a generative AI model would be the instruction, "Create advertisements tailored to the user's interests based on the web pages they have recently visited."

[0740] By implementing such a system, advertisements tailored to individual user interests can be effectively delivered, optimizing strategies and improving the user experience.

[0741] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0742] Step 1:

[0743] As an initial step in information gathering, the server acquires data on internet pages and user behavior. Using web search behavior and social network behavior data as input, the data collection process via agents begins. The output is raw data used for subsequent analysis.

[0744] Step 2:

[0745] The server feeds the collected raw data to an unstructured data processing unit for analysis. Using the collected data as input, a generative AI model is employed to identify the user's interests and tendencies. As a result of text analysis using natural language processing technology, the user's areas of interest and behavioral trends are output.

[0746] Step 3:

[0747] The server drives the selection mechanism based on the generated insights and formulates an advertising plan. The input is the user's interests and tendencies obtained in the previous step, and the output is the generation of personalized advertising messages and campaign plans. Specifically, it constructs prompt sentences based on specific user attributes and sends them to the generation AI model.

[0748] Step 4:

[0749] The server uses an output device to generate and deliver advertising content according to the formulated plan. The input is the advertising plan, which is the output in step 3, and the output is the advertising content formatted in the optimal format. In terms of delivery, the analyzed advertisement is displayed on the user's device in real time via Google AdMob or other advertising platforms.

[0750] Step 5:

[0751] The server activates a feedback evaluation system to assess the effectiveness of the advertisement. The input received is user interaction data (e.g., ad click-through rate and time spent on the page), from which quantitative evaluation metrics are generated. The output is feedback data generated using data analysis techniques, which serves as a guideline for adjusting future advertising strategies to optimize them.

[0752] 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.

[0753] This invention relates to a system that uses an emotion engine, which is capable of collecting large amounts of information and recognizing users' interests, trends, and emotions, to formulate advertising strategies and generate and deliver personalized advertisements. In particular, this invention describes a form that enables more accurate ad delivery by combining it with an emotion engine.

[0754] Data collection and emotion recognition

[0755] The server collects data in real time from internet sources. In addition to search queries and click data, it also collects user-generated text and audio data. This data is stored in a database and then analyzed by a sentiment engine.

[0756] The emotion engine uses natural language processing technology to analyze text and audio data and extract the user's emotional state. This process provides information about the emotions the user is experiencing.

[0757] Insight generation and strategy formulation

[0758] The server integrates the emotional data extracted by the emotion engine with the interests and trends of other users to generate deeper insights. This provides advanced, emotion-based insights that go beyond mere interest observations.

[0759] Furthermore, we develop advertising strategies based on these insights. By considering emotional information and tailoring messages accordingly, we can deliver advertisements that resonate with users' feelings.

[0760] Ad generation and delivery

[0761] The server generates personalized ads that take emotions into account. The generation AI designs ads that include creative elements that match the target's emotions and delivers them through specific media channels.

[0762] The device displays emotion-based advertisements at the optimal time while the user is online. This allows users to receive content that resonates with their emotions.

[0763] Effectiveness measurement and feedback

[0764] The server analyzes the response and effectiveness of the delivered ads. Click-through rates, viewing time, and emotional response tracking data are used.

[0765] The collected performance data is used to optimize the entire system, and is cyclically utilized to improve the accuracy of the emotion engine and the effectiveness of advertising strategies.

[0766] As a concrete example, when an e-commerce platform sells new fashion items, the server not only analyzes search behavior and social media posts based on "fashion" and "trend" related data, but also uses an emotion engine to detect when users have positive emotions. The server then generates and delivers advertisements that evoke these positive emotions to users, further increasing their purchase intent. In this process, users become emotionally connected to the brand, which can lead to further improvements in conversion rates.

[0767] The following describes the processing flow.

[0768] Step 1:

[0769] The server collects big data from internet sources. This includes search queries, click data, text messages, social media posts, and voice input. After collection, the data is organized into a database.

[0770] Step 2:

[0771] The server uses an emotion engine to analyze the user's emotions from the collected data. Specifically, it employs natural language processing and speech emotion analysis to extract the user's emotional state from text and audio data.

[0772] Step 3:

[0773] The server combines sentiment data and interest data to generate integrated insights. These insights are recorded to match the individual user's tendencies and emotions and are used as the basis for advertising strategies.

[0774] Step 4:

[0775] The server develops optimal advertising strategies based on integrated insights. It adjusts ad messages and creatives considering the emotional state of target users. The strategy also includes where and when ads are delivered.

[0776] Step 5:

[0777] The server generates personalized ads based on emotions. Using generative AI, it designs compelling ad creatives that match the user's emotional state.

[0778] Step 6:

[0779] The device displays ads at the appropriate time based on the user's online activity. Because the ads are aligned with the user's emotions, higher engagement can be expected.

[0780] Step 7:

[0781] The server monitors the effectiveness of advertisements and analyzes the collected data. It monitors various metrics, including click-through rates, conversion rates, and user engagement data.

[0782] Step 8:

[0783] Based on the analysis results, the server improves the overall advertising strategy and sentiment engine of the system through feedback. This makes it possible to enhance the effectiveness of the next advertising campaign.

[0784] (Example 2)

[0785] 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".

[0786] In today's information-saturated environment, accurately understanding users' emotions and interests and effectively delivering advertisements based on them is difficult, and building an effective feedback system presents challenges. Conventional systems have problems in that they cannot adequately generate personalized advertisements that take emotions into account, nor can they optimize the subsequent effectiveness of those advertisements.

[0787] 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.

[0788] In this invention, the server includes means for collecting large amounts of information, means for integrating emotional information and interest data to generate advanced insights, and means for generating and delivering personalized advertisements based on emotions. This makes it possible to deliver advertisements that match the user's emotions, and to continuously feed back the effects and optimize the entire system.

[0789] "Large-scale information" refers to a vast amount of data collected from diverse sources, including data formats such as text, audio, and images.

[0790] "Emotional processing means" refers to technologies that use natural language processing techniques to analyze and extract the emotional state of a user from text and audio data.

[0791] "Insight" refers to deep insights gained from collected data, and in particular, it means advanced knowledge based on users' emotions and interests.

[0792] An "advertising strategy" refers to a plan that determines how to design, target, and deliver advertisements based on the insights gained.

[0793] "Generation methods" refer to the technologies and processes used to generate creative advertising content based on users' emotions and interests.

[0794] "Feedback methods" refer to the process of analyzing the effectiveness of delivered advertisements, optimizing the entire system based on the data obtained, and making improvements.

[0795] "User-generated elements" refer to content and behavioral data generated by users on the internet, including social media posts and search queries.

[0796] "Personalized advertising" refers to advertisements that are individually customized according to the emotional state and interests of a particular user.

[0797] This invention is a system that collects large amounts of information and generates and delivers personalized advertisements based on users' emotions and interests. Specifically, it is configured as follows:

[0798] Data collection and analysis

[0799] First, the server collects data from various sources on the internet. This process utilizes APIs and web scraping techniques. The collected data includes search queries, click data, and user-generated elements such as text and audio data. This data is stored in a database as structured data and later analyzed.

[0800] Next, the server uses emotion recognition technology to analyze the user's emotional state from the accumulated data. This analysis employs natural language processing technology, with generative AI models such as BERT and GPT being used as specific examples.

[0801] Insight generation and ad generation

[0802] After sentiment analysis is complete, the server integrates sentiment information and interest data to generate insights for advertising operations. Based on these insights, the server uses a generative AI model to design sentiment-driven creative advertisements. At this time, the AI ​​model is given instructions such as, "Create an advertising message that evokes positive emotions in women in their 20s."

[0803] Ad delivery and performance measurement

[0804] The generated personalized ads are delivered to the user at the optimal time through their device. For example, ads are displayed when the user is online, providing an emotionally resonant advertising experience.

[0805] Subsequently, the server measures the effectiveness of the delivered ads and utilizes the feedback data to optimize the entire system. Data such as click-through rates, viewing time, and emotional responses are analyzed to improve ads and enhance the accuracy of the emotional engine. This cycle allows the system to continuously evolve and provide more effective advertising strategies.

[0806] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0807] Step 1:

[0808] The server collects data from diverse sources. As input, it uses APIs and scraping techniques to obtain data from websites, social media, search queries, and other sources. As output, the acquired data undergoes initial processing and is stored in a database. For example, to collect posts containing specific keywords, it uses the Twitter API to gather relevant tweets.

[0809] Step 2:

[0810] The server supplies accumulated data to the emotion engine and performs emotion analysis. Text and audio data extracted from the database are used as input. Metadata indicating the user's emotional state is generated as output. Specifically, natural language processing models such as BERT and GPT are used to extract emotion labels such as "happy" and "sad" from the text data.

[0811] Step 3:

[0812] The server integrates sentiment data with other user data to generate insights. It uses sentiment labels and user behavior data (e.g., browsing history) as input. The output is insight data that includes each user's interests and sentiment tendencies. For example, if it determines that a woman in her 20s has recently made many positive posts, the insight "increase in positive sentiment" is obtained.

[0813] Step 4:

[0814] The server designs personalized ads using a generative AI model. It uses insight data and predefined ad templates as input. The output is ad content optimized for individual users. Specifically, it generates an ad that matches the "increase in positive emotions," such as an ad for "enjoying new fashion items."

[0815] Step 5:

[0816] The device delivers generated personalized ads to the user at the appropriate time. Inputs include the user's online activity and schedule. Outputs include ad banners and videos displayed while the user is browsing. Specifically, ads are displayed in real time when the user is visiting a particular webpage.

[0817] Step 6:

[0818] The server measures the effectiveness of delivered advertisements and optimizes the system. It collects data such as ad click-through rates, viewing time, and user response as input. As output, this data is used as analytical results to improve advertising strategies. Specifically, it determines whether a particular ad message is achieving the expected results and incorporates the feedback into the system.

[0819] (Application Example 2)

[0820] 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".

[0821] Traditional advertising delivery systems primarily rely on ad targeting based on basic user interests and click data, and have not yet reached the point of personalizing ads by considering the user's emotional state. As a result, there is a challenge in that ads cannot be delivered in response to the user's emotions in real time, and the effectiveness of advertising cannot be maximized.

[0822] 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.

[0823] In this invention, the server includes means for collecting large amounts of data, a generation device for extracting user interests, trends, and emotions from the collected data, and a decision device for formulating advertising operation policies based on the extracted interests, trends, and emotions. This makes it possible to deliver advertisements at the optimal timing according to the user's emotional state.

[0824] "Large-scale data" refers to large amounts of information in any form collected from the internet or from users' devices.

[0825] A "generating device" refers to a system that analyzes users' interests, trends, and emotions from collected data and extracts necessary information.

[0826] A "decision-making device" refers to a system used to formulate advertising management policies based on data obtained from a generation device.

[0827] "Advertising management policy" refers to a personalized advertising strategy based on specific user attributes and emotions.

[0828] "Emotional state" refers to the psychological state a user is experiencing at a particular moment, and it is an important metric in the creation and delivery of advertisements.

[0829] "Delivery device" refers to equipment or systems used to deliver selected advertisements to the user's device.

[0830] To realize this invention, a server first collects large amounts of data in real time. The data to be collected includes user search queries, communication data, and voice data. This requires that the smartphone or computer is connected to the internet. By employing a data collection bot that runs using TensorFlow, the server can efficiently collect diverse information.

[0831] The collected data is then processed by a generator on the server. This generator uses the Google Cloud Natural Language API to analyze the data and determine user interests, trends, and sentiments. The analyzed data is sent to a decision-making system that develops the operational strategy for advertising campaigns. Based on the insights gained by the sentiment engine, this decision-making system generates personalized ads tailored to specific user attributes.

[0832] Next, the generated advertisements are optimized by prompts from a generation AI model and delivered to the device. OpenAI's GPT model is used to formulate these prompts and generate the ad copy. The generated advertisements are then sent to the user's smartphone via a distribution device. This enables the delivery of advertisements at the optimal timing based on the user's emotional state. For example, when a user is relaxed, an advertisement for a new novel can be presented with creative content that matches their mood, stimulating their desire to purchase.

[0833] An example of a prompt would be, "Create promotional copy that appeals to users enjoying a relaxing afternoon and captures the essence of a new novel that resonates with their mood."

[0834] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0835] Step 1:

[0836] The server collects large amounts of data from the internet and user devices. It takes search queries, communication data, and audio data as input. TensorFlow is used to transform the collected data into a structured format and store it in a database.

[0837] Step 2:

[0838] The server passes the collected data to the generator, which analyzes it using the Google Cloud Natural Language API. The input is the data collected in step 1. The generator uses natural language processing technology to extract user interests, trends, and emotions from the data and outputs the analysis results.

[0839] Step 3:

[0840] The server sends the analysis results to the decision-making unit. The decision-making unit uses the user's interests, trends, and sentiment data obtained as input to formulate advertising management policies. In this process, it outputs personalized policies based on specific user attributes.

[0841] Step 4:

[0842] The server generates ad copy using a generative AI model based on the determined advertising management policy. Here, the input is the policy formulated in step 3. Using OpenAI's GPT model and provided with prompt examples, it outputs the optimal ad content.

[0843] Step 5:

[0844] The device delivers the generated advertisement to the user's smartphone. The input is the advertisement copy created in step 4. The delivery device sends the advertisement in a way that is tailored to the user's emotional state and timing.

[0845] Step 6:

[0846] The server measures the effectiveness of delivered advertisements. The input is user behavior data after receiving the advertisement. It collects performance data such as click-through rates, viewing time, and additional feedback, and uses a feedback mechanism to optimize the entire system. Based on the collected data, more precise analysis and improvements to advertising strategies are made.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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."

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0868] The following is further disclosed regarding the embodiments described above.

[0869] (Claim 1)

[0870] Means for collecting large amounts of information,

[0871] A generation means for extracting user interests and trends from the aforementioned collected information,

[0872] A decision-making tool for formulating operational strategies based on identified interests and trends,

[0873] A means for generating and distributing advertisements based on the aforementioned operational strategy,

[0874] A feedback means for measuring the effectiveness of the delivered advertisement and for improving the generation means and determination means,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, wherein the information includes search queries and click data.

[0878] (Claim 3)

[0879] The system according to claim 1, wherein the operational strategy is to create personalized advertisements based on specific user profiles.

[0880] "Example 1"

[0881] (Claim 1)

[0882] Means of obtaining a wide range of data from diverse sources,

[0883] The acquired data is structured and preprocessed to remove noise and duplicates,

[0884] A generation means for extracting user interests and trends from the pre-processed data using natural language processing technology,

[0885] A decision-making mechanism for formulating advertising strategies based on the interests and trends of extracted users,

[0886] A means for generating and delivering advertisements in various formats based on the generated strategy,

[0887] A feedback means for evaluating the delivered advertisements and improving the generation means and determination means,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, wherein the data includes search operation data and user operation data obtained from a communication network.

[0891] (Claim 3)

[0892] The system according to claim 1, wherein the advertising strategy generates customized advertisements based on user attribute information.

[0893] "Application Example 1"

[0894] (Claim 1)

[0895] A device for collecting information,

[0896] An unstructured data processing device for analyzing user interests and trends from the collected information,

[0897] A selection device for formulating a plan based on extracted interests and trends,

[0898] An output device for automatically generating and distributing advertising content based on the aforementioned plan,

[0899] A return evaluation device for evaluating the effectiveness of the delivered advertisement and for improving the unstructured data processing device and selection device,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, wherein the aforementioned information includes web search behavior and social network behavior data.

[0903] (Claim 3)

[0904] The system according to claim 1, wherein the plan generates personalized advertisements based on specific user attributes.

[0905] "Example 2 of combining an emotion engine"

[0906] (Claim 1)

[0907] Means for collecting large amounts of information,

[0908] An emotion processing means for analyzing the user's emotional state from the information collected above,

[0909] A means of integrating emotional information and interest data to generate advanced insights,

[0910] A decision-making mechanism for formulating an advertising operation strategy based on the aforementioned insights,

[0911] A generation method for generating and delivering personalized advertisements based on emotions,

[0912] A feedback mechanism to analyze the response to delivered advertisements and optimize the entire system,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, wherein the aforementioned information includes user-generated elements.

[0916] (Claim 3)

[0917] The system according to claim 1, wherein the advertising operation strategy creates personalized advertisements that match the emotions of a specific user group.

[0918] "Application example 2 when combining with an emotional engine"

[0919] (Claim 1)

[0920] Means for collecting large amounts of data,

[0921] A generation device for extracting user interests, trends, and emotions from the aforementioned collected data,

[0922] A decision-making mechanism for formulating advertising operational policies based on extracted interests, trends, and emotions,

[0923] A device that generates and delivers advertisements based on the aforementioned advertising management policy,

[0924] A feedback device for measuring the effectiveness of the delivered advertisement and for improving the generation device and the decision device,

[0925] A means of analyzing the user's emotional state in real time and displaying advertisements on the user's device at the optimal time based on the results,

[0926] A system that includes this.

[0927] (Claim 2)

[0928] The system according to claim 1, wherein the data includes communication data and voice data.

[0929] (Claim 3)

[0930] The system according to claim 1, wherein the advertising operation policy creates personalized advertisements based on specific user attributes, and generates advertising content that responds to emotions using a generative AI. [Explanation of Symbols]

[0931] 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 for collecting large amounts of information, A generation means for extracting user interests and trends from the aforementioned collected information, A decision-making tool for formulating operational strategies based on identified interests and trends, A means for generating and distributing advertisements based on the aforementioned operational strategy, A feedback means for measuring the effectiveness of the delivered advertisement and for improving the generation means and determination means, A system that includes this.

2. The system according to claim 1, wherein the aforementioned information includes search queries and click data.

3. The system according to claim 1, wherein the operational strategy is to create personalized advertisements based on specific user profiles.

Images