system

Abstract

Provide a system. 【Solution means】 Data collection means, which is means for acquiring information from a plurality of information sources; means for preprocessing the acquired information to remove duplicates and noise; means for analyzing the preprocessed information to calculate the topic volume and its change rate; means for predicting the possibility of a trend and its reliability using the analyzed data; means for dynamically adjusting the price of an advertisement frame of a related website based on the predicted trend; means for notifying a user terminal of a proposal for advertisement placement; feedback means for collecting and analyzing result data of advertisement placement to improve a prediction model; A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional advertising publishing method, there is a problem that it is difficult for advertising staff or sales staff of advertising agencies to formulate an effective advertising strategy because they lack the knowledge to accurately predict trends. In addition, by missing the timing of trends, not only does the cost-effectiveness of advertising decrease, but cases where the decision on appropriate advertising publishing is delayed often occur. Due to such a situation, there has been a demand for improving the accuracy of trend grasping and the efficiency of advertising publishing in the advertising industry.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a data collection means that acquires information from multiple sources, analyzes it, and calculates the volume of topics and their rate of change. Furthermore, it provides a means for predicting the likelihood and reliability of trends based on the analyzed data, and for dynamically adjusting the price of advertising space based on the results. This means enables the rapid notification of advertising placement proposals to user terminals and builds a system that supports effective advertising strategies based on trends. In addition, by analyzing the results of advertising placements and continuously improving the prediction model through feedback, it is possible to further enhance prediction accuracy and advertising effectiveness.

[0006] "Data collection means" refers to devices or programs that have the function of acquiring information from multiple sources.

[0007] "Preprocessing" is a preparatory step that removes duplicate data and noise from collected information to facilitate analysis.

[0008] "Topic volume" refers to a numerical representation of the frequency of mentions of a particular keyword or theme.

[0009] "Rate of change" is an indicator that shows the rate at which the volume of topics or other numerical data changes over time.

[0010] "Potential for trending" is a concept that indicates the probability of a particular keyword or theme gaining attention in the future.

[0011] "Confidence level" is an indicator of how likely a prediction is to be accurate, and it is based on the accuracy of the data and the precision of the model.

[0012] "Dynamic adjustment" is a process that automatically changes parameters and settings according to the situation and data.

[0013] "Advertising space price" refers to the fee paid to place an advertisement on a specific page or medium on the internet.

[0014] The "user terminal" refers to digital devices such as personal computers, smartphones, tablets, etc. used by advertisers and other users.

[0015] The "feedback means" is a function or process that collects and analyzes data for improving the system based on actual results.

Brief Description of Drawings

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

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include 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.

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

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system for streamlining advertising placement and consists of dedicated software and hardware. An embodiment thereof is shown below.

[0038] 1. Information gathering and processing

[0039] The server automatically retrieves relevant data from various sources on the internet. These sources include news sites, social media, and e-commerce platforms. This is achieved through periodic queries via APIs. The collected data is preprocessed to prepare it for analysis.

[0040] 2. Data Analysis and Trend Forecasting

[0041] The server analyzes pre-processed data and calculates the volume of discussion for specific keywords and their rate of change. This information is used to predict trends using machine learning algorithms. The model learns from past data and predicts future trends with high accuracy.

[0042] 3. Dynamic setting of advertising strategy

[0043] The server adjusts the pricing of ad space on relevant websites based on the predicted confidence level of the trend. As confidence increases, prices rise, allowing for lower prices in the early stages of a trend. This enables users to place ads at a competitive time.

[0044] 4. Notifications and Interface

[0045] The user's device receives notifications from the server and displays information about recommended ad placements. This includes the target page, current pricing, and relevant keywords. Users can use the interface to make quick decisions about placing ads.

[0046] 5. Results Analysis and Feedback

[0047] The server collects data from implemented advertising campaigns and evaluates their effectiveness. Based on this, the analysis results are continuously fed back to improve the accuracy of the predictive model. By improving predictive accuracy, the system can always provide effective advertising strategies that are in line with the latest trends.

[0048] As a concrete example, when a new music album is released, this system can be used to place advertisements ahead of the trending music streaming sites and popular blogs. This embodiment allows users to deploy effective advertising strategies quickly and at low cost in a highly competitive advertising market.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The server periodically collects data from multiple sources, including news APIs, social media APIs, and e-commerce site APIs. Data collection is automated through scheduled queries.

[0052] Step 2:

[0053] The server preprocesses the collected data. This involves removing duplicate information and noise, and preparing the data for analysis. This process includes text cleaning and transformation operations.

[0054] Step 3:

[0055] The server analyzes pre-processed data and calculates the topic volume for each specified keyword. Furthermore, it models the rate of change to evaluate the increase or decrease in topic volume within a specific period.

[0056] Step 4:

[0057] The server predicts trends based on the analyzed data. It applies machine learning algorithms and utilizes models learned from historical data to calculate the likelihood and confidence level of keyword popularity.

[0058] Step 5:

[0059] The server dynamically adjusts the price of ad space on relevant websites based on predictions. If the reliability is high, the price of ad space will increase, making it possible to place ads at a lower price before competition intensifies.

[0060] Step 6:

[0061] The user's device receives notifications from the server and displays advertising placement suggestions. These suggestions include relevant websites, recommended keywords, and pricing information for ad slots.

[0062] Step 7:

[0063] Users review proposed ad placements and make decisions as appropriate through an interface on their device. This process is flexible, allowing users to optimize their ad placements based on set conditions.

[0064] Step 8:

[0065] The server collects the results of the implemented advertising campaigns and analyzes click-through rates and conversion rates. This data is then used as feedback to improve the predictive model. This feedback mechanism allows for continuous improvement of the model's accuracy.

[0066] (Example 1)

[0067] 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."

[0068] In today's rapidly changing information landscape, optimizing the timing and cost of advertising is a major challenge. Traditional methods require real-time data collection and analysis, as well as rapid decision-making, but performing these tasks manually is inefficient and costly. Furthermore, it is necessary to improve the accuracy of trend predictions based on historical data and to refine advertising strategies by feeding back the results of advertising campaigns.

[0069] 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.

[0070] In this invention, the server includes means for acquiring data from multiple information sources on the Internet and automatically performing data collection; means for preprocessing the acquired data, organizing unnecessary information and extracting features; and means for calculating the rate of change of information and analyzing the volume of topics based on the preprocessed data. This makes it possible to quickly and efficiently optimize the timing and price of advertising placement and accurately predict trends.

[0071] "Data collection methods" refer to methods of automatically acquiring data from multiple sources on the internet.

[0072] "Preprocessing" is the process of organizing acquired data, removing unnecessary information, and converting it into a format suitable for analysis.

[0073] "Feature extraction" is a technique that selects important information and attributes from data, forming the foundation for analysis.

[0074] "Rate of change" is an indicator that quantitatively measures the change in the volume of discussion surrounding a specific data point or keyword.

[0075] "Topic volume" is a quantitative measure that indicates the extent to which information about a particular theme or keyword is discussed in society.

[0076] "Trend forecasting" is the process of predicting future consumer and market trends based on past data patterns.

[0077] "Confidence level" is an indicator that shows the degree of confidence in the accuracy of the prediction results produced by a predictive model.

[0078] "Ad slot price adjustment" refers to the operation of changing the price of ad slots based on predicted trend data in order to achieve efficient ad placement.

[0079] "Analyzing the results of an advertising campaign" is the process of evaluating the effectiveness of the advertisements that have been placed and reflecting the results in the business strategy.

[0080] A "feedback mechanism" is a process that uses the results of advertising campaigns to improve predictive models and enable more accurate predictions.

[0081] This system implements a series of processes to streamline advertising placement, and its specific implementation is described below.

[0082] First, the server is responsible for acquiring data from multiple sources. Specifically, it acquires data via APIs from news portals and social media platforms on the internet. This process is automated, enabling real-time data collection. For example, it uses publicly available information APIs to periodically retrieve articles and posts related to specific keywords.

[0083] Next, the server preprocesses the acquired data. Here, natural language processing tools are used to remove noise and extract necessary features. For example, Python libraries such as NLTK and SpaCy are used to clean and tokenize the data.

[0084] Furthermore, the server analyzes the pre-processed data and applies a machine learning model to predict trends. This model learns from historical data and aims to accurately predict future trends. Common machine learning frameworks include Scikit-learn and TENSORFLOW®.

[0085] Subsequently, the server dynamically adjusts the price of the ad space based on the analysis results. Specifically, it optimizes user ad spending by increasing the price of ad space when the trend's credibility is high and setting a lower price when it is low.

[0086] The user's device receives notifications from the server. This displays information including which sites and media outlets to advertise on, current pricing, and relevant keywords. The user then uses this information to quickly decide on their advertising strategy.

[0087] As an example of a prompt, the AI ​​model is given the text, "Generate trend predictions related to the release of a new album on music streaming services and suggest the optimal timing for placing relevant ads." In this way, users can quickly grasp ever-changing trends and reflect that information in their advertising strategies.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The server collects data from multiple sources. The input consists of specified keywords and hashtags, which are used to retrieve information from news sites and social media platforms on the internet. The output is a collection of articles and posts that match the specified criteria. Specifically, the server uses APIs to accumulate data in real time while performing periodic queries.

[0091] Step 2:

[0092] The server preprocesses the acquired data. The input is the collected, unorganized data, which is then cleaned using natural language processing tools. Specifically, it removes unwanted noise and tokenizes the language. The output is a clean, analyzable dataset. This includes tasks such as removing special characters from text and splitting sentences into individual words.

[0093] Step 3:

[0094] The server analyzes pre-processed data and performs trend prediction. The input is a formatted dataset, to which machine learning algorithms are applied. Specifically, the server operates a model that predicts future trends based on past data patterns. The output is a predicted value of the future discussion volume for a specific keyword and its confidence level.

[0095] Step 4:

[0096] The server dynamically sets the advertising strategy based on the prediction results. The input is the result of the trend prediction, and the output is the adjusted pricing of the ad space. Specifically, the server increases the price when the confidence level is high and sets a lower price when the confidence level is low. This enables advertising to be placed at the optimal time and cost.

[0097] Step 5:

[0098] The user's device receives ad placement notifications sent from the server. The input is notification information from the server, including recommended target audiences, pricing, and relevant keywords. The output is a visual presentation of information to the user. Specifically, the device displays information on its interface to support the user in quickly making ad placement decisions.

[0099] Step 6:

[0100] The server analyzes the results of advertising campaigns and provides feedback. The input is the results data of the implemented advertising campaigns, and the output is an improved machine learning model. Specifically, the server evaluates the collected performance metrics (click-through rate, conversion rate, etc.) and updates the model to improve the accuracy of predictions for the next campaign.

[0101] (Application Example 1)

[0102] 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."

[0103] Maximizing the effectiveness of advertising campaigns and enabling timely ad placement are crucial challenges for many companies. However, current systems lack sufficient real-time information gathering, analysis, and trend prediction capabilities, resulting in a failure to maximize advertising effectiveness.

[0104] 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.

[0105] In this invention, the server includes means for acquiring information, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the topic volume and its rate of change, means for providing advertising recommendations to a display device based on predicted trends, and feedback means for evaluating the effectiveness of advertising and improving the relevant numerical model. This enables advertising to be placed at the appropriate time.

[0106] "Means of acquiring information" refers to a system that automatically collects data from various information sources on the internet.

[0107] "Means for preprocessing and removing duplication and noise" refers to techniques that remove unnecessary information from collected data before analysis, preparing it for analysis.

[0108] "Means for calculating topic volume and its rate of change" refers to a method for calculating the frequency of occurrence and increase / decrease of specific keywords from collected information.

[0109] "Means of providing advertising recommendations to display devices based on predicted trends" refers to a technology that visually notifies users of the appropriate timing for advertising based on analysis results.

[0110] A "feedback mechanism for evaluating the effectiveness of advertising and improving related numerical models" is a system that analyzes actual advertising effectiveness and improves the accuracy of prediction algorithms accordingly.

[0111] To realize this invention, it is necessary to build a program in which a server integrates and performs functions such as information gathering, analysis, and dynamic setting of advertising strategies. The hardware used includes a server computer for analyzing and calculating data, and the software used is an API for data gathering and Python and TensorFlow for analysis.

[0112] Specifically, the server collects data from the internet via APIs, preprocesses that data, and removes duplicates and noise. This preprocessing phase optimizes the information so that it can be effectively used in the next analysis step. Next, the server calculates the frequency and rate of change of specific topics based on the collected information, and uses this to predict future trends. In this process, a generative AI model trained on vast amounts of historical data is utilized.

[0113] The user's device includes a display device that receives and displays signals from the server. This device notifies the user in real time of advertising recommendations based on the analysis results. This notification allows the user to place ads at the optimal time, giving them a competitive advantage in the market. For example, if the user is in a certain region, ads related to popular products in that region can be placed instantly.

[0114] As a result, the effectiveness of the implemented advertisements is reflected, and the server continuously improves its predictive model based on the collected advertising performance data. This enables even more accurate predictions for future advertising campaigns, providing advertisers with the optimal strategy.

[0115] An example of a prompt message would be: "Analyze the latest sales information in the shopping mall and generate recommendations for effective advertising."

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server retrieves information from news sites and social media on the internet. The input consists of data obtained from each information source via APIs, which the server collects and stores in a database. Its primary function is the collection of large amounts of text data on topics that arise on a daily basis.

[0119] Step 2:

[0120] The server preprocesses the collected data, removing duplicates and noise. The input is the raw data collected in step 1, and the output is the cleaned data. Specifically, natural language processing is used to clean the text and prepare the data for analysis.

[0121] Step 3:

[0122] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. The input is noise-free data, and the output is data showing the frequency and rate of change of specific keywords. Here, a specialized algorithm is used to calculate which topics increase or decrease over time.

[0123] Step 4:

[0124] The server uses a generative AI model based on the analysis results to predict the likelihood of an epidemic. The input is the analysis results obtained in step 3, and the output is future epidemic prediction data. Since the model predicts epidemics from patterns in past data, the results of learning from similar past datasets are immediately utilized.

[0125] Step 5:

[0126] The device receives advertising recommendations from the server and displays them to the user. The input is advertising strategy information based on trend forecasts sent from the server, and the output is advertising recommendations provided to the user. Specifically, the analysis results are displayed in real time on a display such as smart glasses and suggested to the user as a notification.

[0127] Step 6:

[0128] Users review ad placement recommendations displayed on their devices and place ads as needed. The input is the information displayed on the device, and the output is the user's decision to place ads. In this step, the user makes an instant decision based on the information provided to determine whether to run the ad campaign.

[0129] Step 7:

[0130] The server collects and re-analyzes the results data of the implemented advertising campaigns. The input is the advertising campaign results data, and the output is feedback for improving the next predictive model. The success or failure of the campaign is evaluated, and the analysis model is adjusted using the data as feedback.

[0131] 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.

[0132] This invention is an advertising support system incorporating an emotion engine, which automates the entire process from data collection and analysis to ad placement proposals and feedback. An embodiment of this system is shown below.

[0133] 1. Information gathering and emotion recognition

[0134] The server retrieves information from news sites, social media, e-commerce platforms, and other sources. This is done through periodic data queries via APIs.

[0135] The collected data is analyzed through an emotion engine to recognize user emotions, such as positive or negative. Emotional information is particularly effective in word-of-mouth and reviews.

[0136] 2. Data Preprocessing and Trend Analysis

[0137] The server cleans the acquired data, removing duplicates and noise. Furthermore, it calculates topic volume and evaluates sentiment tendencies.

[0138] Preprocessed data is analyzed to calculate the likelihood and confidence level of a trend, based on sentiment information, along with its topic volume and rate of change.

[0139] 3. Trend forecasting and optimization of advertising strategies

[0140] The server uses machine learning algorithms based on the analyzed data to predict trends.

[0141] Emotional information is used to adjust the timing and content of advertising campaigns. This allows for the creation of optimal advertising strategies that align with emotional trends.

[0142] 4. Proposals and Notifications

[0143] The user's device receives suggestions from the server and displays the provided advertising strategies. These suggestions include information such as the pages where the ads will be placed, keywords, and pricing.

[0144] Sentiment-based recommendations help users understand the situation better and support faster decision-making.

[0145] 5. Analysis of results and improvement of the model

[0146] The server analyzes data from implemented advertising campaigns in detail and evaluates the effectiveness of the ads. Emotion-based effectiveness measurement is also performed.

[0147] The resulting data is incorporated into the predictive model as a feedback loop, continuously improving the accuracy of predictions and the quality of advertising strategies for future attempts.

[0148] As a concrete example, when a food-related product becomes a hot topic on social media, this system can be used to detect positive consumer sentiment and place advertisements on cooking blogs and recipe websites related to that trend. In this way, this embodiment allows advertisers to effectively capture the market at a time that is appropriate for consumer sentiment.

[0149] The following describes the processing flow.

[0150] Step 1:

[0151] The server retrieves data from external news sites, social media platforms, and e-commerce sites. This data retrieval is performed through periodic requests using APIs, gathering the latest data from diverse information sources.

[0152] Step 2:

[0153] The server preprocesses the acquired raw data before feeding it into the sentiment engine. This step involves cleaning the data, removing duplicates and irrelevant information, and removing noise to generate data optimized for analysis.

[0154] Step 3:

[0155] The server passes the pre-processed data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing techniques to assign emotion labels such as positive, negative, and neutral to each data point.

[0156] Step 4:

[0157] The server uses sentiment analysis results to calculate the volume of a topic and its rate of change. This information is input into a machine learning model to predict the likelihood and confidence level of its popularity.

[0158] Step 5:

[0159] The server dynamically adjusts the price of ad space on relevant websites, taking sentiment information into account. The higher the popularity and credibility of a trend, the higher the price of the ad space, providing users with an early opportunity to place ads at a lower price.

[0160] Step 6:

[0161] The user's device receives ad placement proposals sent from the server and displays ad content, pricing, and recommendation strategies based on sentiment analysis. The user can then make an ad placement decision based on this information.

[0162] Step 7:

[0163] Users interact with their devices and plan effective advertising campaigns based on the displayed ad suggestions. Emotion-based information provides users with sophisticated and compelling advertising options.

[0164] Step 8:

[0165] The server collects data on the results of implemented advertising campaigns and performs advertising effectiveness analysis. Furthermore, it incorporates the obtained sentiment data to form a feedback loop that improves the accuracy of predictions and the quality of strategies for the next campaign.

[0166] (Example 2)

[0167] 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".

[0168] Traditional advertising systems made it difficult to create timely advertising strategies that reflected user emotions, resulting in a failure to maximize advertising effectiveness. Furthermore, there was a lack of mechanisms to fully utilize past advertising data and incorporate it into future strategies.

[0169] 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.

[0170] In this invention, the server includes means for acquiring information from multiple sources, means for recognizing and analyzing emotions using natural language processing techniques from the pre-processed information, and means for determining the optimal timing and content of advertisements. This enables the creation of effective advertising strategies that respond to user emotions and the continuous improvement of predictive models based on past data.

[0171] A "data collection method" is a system for obtaining necessary information from multiple sources.

[0172] "Preprocessing" refers to a series of processes that remove duplicates and noise from acquired information and prepare it for analysis.

[0173] "Natural language processing technology" is a technology that allows computers to understand, generate, and analyze human language, and is also used for recognizing emotions.

[0174] "Emotion recognition" is the process of determining a user's emotional state from text data and classifying it into categories such as positive, negative, and neutral.

[0175] "Trend forecasting" is the process of predicting topics and market trends that are likely to attract attention in the future, based on analyzed data.

[0176] An "advertising strategy" is a set of guidelines and plans for determining the time, place, and content of advertisements to be delivered effectively.

[0177] A "feedback mechanism" is a system that evaluates the effectiveness of advertising and uses the results to improve the system's predictive models and advertising strategies.

[0178] A "user terminal" is a device that receives information and notifications from a server and transmits them to the user.

[0179] The system of this invention consistently performs data collection from a wide range of sources, sentiment analysis, trend forecasting, and strategic optimization of advertising placements. Details are described below.

[0180] The server at the core of this system retrieves data in real time from news sites, social media, and online trading platforms when collecting information. Specific technologies used include continuous data queries via web APIs, enabling the system to continuously obtain the latest information.

[0181] The collected data undergoes sentiment analysis using natural language processing technology on the server. Specifically, the technology used extracts positive, negative, and neutral emotions from the text. This sentiment recognition is supported by a generative AI model and contributes to optimizing advertising strategies based on user emotions.

[0182] The analyzed sentiment data is then analyzed by a trend prediction algorithm to forecast future trends. Based on this forecast, advertising strategies are optimized. The server utilizes the collected data and its analysis results to determine the most effective timing, targeting, and content for advertising.

[0183] Subsequently, a notification is sent from the server to the user's terminal, and the proposed advertising strategy is displayed. As a concrete example, if a food-related product is trending positively on social media, it is possible to leverage consumer sentiment to effectively place advertisements related to that product on cooking blogs and recipe websites.

[0184] Furthermore, this system aggregates advertising results data and uses feedback mechanisms to further improve the predictive model on the server in order to evaluate its effectiveness. This process allows for continuous improvement of the accuracy and results of subsequent advertising strategies.

[0185] An example of a prompt used as input to the generative AI model is, "Please tell me the optimal timing for placing ads based on current sentiment trends." This prompt allows the system to generate an effective advertising strategy based on user sentiment and market trends.

[0186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0187] Step 1:

[0188] The server periodically retrieves data from news sites, social media, and e-commerce platforms via APIs. This input data may contain new trends and user sentiment. The retrieved data is stored for use in subsequent processing. Specifically, it performs processes such as aggregating articles and posts related to specific keywords.

[0189] Step 2:

[0190] The server preprocesses the acquired data. Since the input data is raw, it removes duplicates and noise to generate a clean dataset. Specifically, it removes HTML tags, deletes meaningless spaces, and filters out duplicate data. The output is formatted text data.

[0191] Step 3:

[0192] The server analyzes the formatted text data using natural language processing techniques to recognize user sentiment. In this step, it classifies the sentiment from the input text as positive, negative, or neutral. Specifically, it analyzes keywords and context within the text to calculate a sentiment score. The output is data with the sentiment classified.

[0193] Step 4:

[0194] The server performs trend analysis using machine learning algorithms based on data with classified sentiment. This step uses sentiment information and associated metadata as input data to calculate the volume of trending topics and their rate of change. Specifically, time-series analysis is used to predict the upward trend and peaks of topics. The output is data indicating the potential for future trends.

[0195] Step 5:

[0196] The server optimizes advertising strategies based on predicted trend information. Inputs at this stage include trend prediction data and sentiment information. This information is used to determine the optimal timing and content for ad placement. Specifically, it creates ad copy templates and selects appropriate ad slots. The output is the proposed advertising strategy.

[0197] Step 6:

[0198] The user's device receives advertising strategy proposals sent from the server and notifies the user. In this step, the acquired strategy information becomes the input information. The notification is displayed on the user's device, allowing the user to review the proposed strategy. Specifically, it displays information such as advertising targeting settings and the campaign schedule.

[0199] Step 7:

[0200] The server aggregates and analyzes the results data of implemented advertising campaigns. The input here is the performance data of the advertising campaigns. The server uses this data to measure advertising effectiveness and generate feedback that leads to improvements in the predictive model. Specific operations include calculating click-through rates and analyzing conversion rates. The output is the advertising performance and a newly tuned predictive model.

[0201] (Application Example 2)

[0202] 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".

[0203] In modern advertising strategies, accurately capturing consumer emotions and delivering optimized ads is crucial. However, while traditional systems can predict trends and dynamically adjust ad prices, they lack the ability to personalize ads based on individual user emotions. As a result, advertising effectiveness is not maximized, and potential opportunities are missed. To solve this problem, a new system is needed that incorporates emotional data and enhances the user experience.

[0204] 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.

[0205] In this invention, the server includes means for acquiring information from multiple sources, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the amount of topic and its rate of change, means for dynamically adjusting the price of advertising space on relevant websites based on predicted trends, means for dynamically optimizing and personalizing advertising content based on sentiment data acquired from personal information terminals, and means for collecting, analyzing, and providing feedback on advertising results data. This makes it possible to provide advertisements that meet the sentiment needs of individual users.

[0206] "Data collection means" refers to a device or system for acquiring information from multiple sources.

[0207] "Preprocessing means" refers to the process of organizing the collected information and removing duplication and noise.

[0208] A "topic volume calculation method" is a method for measuring how much attention a particular topic is receiving based on the analyzed information.

[0209] A "trend prediction tool" is a function that predicts future trends based on the data obtained.

[0210] An "ad space adjustment mechanism" is a system that changes the price of advertising space on a relevant website in response to fluctuations in demand.

[0211] "Personalization methods" refer to the process of optimizing ad content based on individual user sentiment data.

[0212] A "feedback mechanism" is a function that provides information to analyze the results of advertising campaigns and use it to help formulate future strategies.

[0213] This invention is an advertising support system that utilizes personal information terminals and servers, and provides a unique advertising experience by leveraging user emotional data.

[0214] The server first acquires information from multiple sources using data collection methods. This includes data from news sites, social media, and e-commerce platforms. The collected information is cleaned by pre-processing methods to remove duplication and noise. This allows for accurate calculation of topic volume and prediction of upcoming trends using trend prediction methods. Furthermore, based on these trend indicators, the advertising space prices on the website can be dynamically changed through advertising space adjustment methods.

[0215] Meanwhile, personal information terminals collect user sentiment information and send it to a server. Based on this sentiment data, the server dynamically optimizes ad content using personalization methods, providing ads optimized for each individual user. For example, if a user is interested in travel, travel-related ads will be displayed preferentially.

[0216] Ultimately, the server uses feedback mechanisms to collect and analyze data on the results of ad campaigns, continuously improving its predictive models for future campaigns. This enhances the accuracy and effectiveness of the advertising strategy.

[0217] For example, if a user posts on social media that they "want to go mountain climbing this weekend," this system can detect that positive emotion data and display advertisements for outdoor equipment.

[0218] An example of a prompt message might be: "Based on the user's feed, we've detected positive sentiment indicating interest in travel this weekend. Please suggest a strategy to display travel-related ads."

[0219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0220] Step 1:

[0221] The server periodically retrieves data from multiple sources, such as news sites, social media, and e-commerce platforms, using APIs. It receives data from the APIs as input and prepares it for storage within the server. The output is raw, unprocessed data.

[0222] Step 2:

[0223] The server preprocesses the acquired raw data to remove duplicates and noise. Specifically, it applies data cleaning algorithms to remove duplicates and unnecessary information. It takes raw data as input and produces a clean dataset as output.

[0224] Step 3:

[0225] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. Here, a data analysis algorithm is used to identify the current topic of interest and calculate its fluctuations. Clean data is used as input, and the analysis results are obtained as output.

[0226] Step 4:

[0227] The server uses the analysis results to predict trends. It analyzes data using a machine learning model and predicts the next likely trending topic. It uses the analyzed data as input and obtains trend prediction data as output.

[0228] Step 5:

[0229] The server dynamically adjusts the price of website ad space based on trend forecasts. It uses a price adjustment algorithm to re-evaluate the value of ad space in real time. It takes trend forecast data as input and outputs adjusted ad prices.

[0230] Step 6:

[0231] The device acquires user sentiment data and sends it to the server. Sentiment analysis tools are used to analyze user input (e.g., text posts) and calculate a sentiment score. User data is taken as input, and a sentiment score is obtained as output.

[0232] Step 7:

[0233] The server generates personalized ads based on sentiment data. It uses a generative AI model to create ad content that aligns with the sentiment score. The sentiment score is used as input, and the optimized ad is obtained as output.

[0234] Step 8:

[0235] The user receives personalized advertisements through their device. The user's device receives notifications from the server and displays the advertisements on the screen. It receives advertising data from the server as input and shows the displayed advertisements to the user as output.

[0236] Step 9:

[0237] The server collects data on the results of ad placements and provides feedback. It uses ad effectiveness measurement tools to analyze the level of response achieved. It receives data after ad display as input and obtains ad effectiveness analysis results as output.

[0238] Step 10:

[0239] The server improves the predictive model based on the collected results data. A feedback loop is formed to improve accuracy in subsequent runs. The results data is used as input, and the improved predictive model is obtained as output.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] [Second Embodiment]

[0244] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0245] 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.

[0246] 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).

[0247] 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.

[0248] 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.

[0249] 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).

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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".

[0256] This invention is a system for streamlining advertising placement and consists of dedicated software and hardware. An embodiment thereof is shown below.

[0257] 1. Information gathering and processing

[0258] The server automatically retrieves relevant data from various sources on the internet. These sources include news sites, social media, and e-commerce platforms. This is achieved through periodic queries via APIs. The collected data is preprocessed to prepare it for analysis.

[0259] 2. Data Analysis and Trend Forecasting

[0260] The server analyzes pre-processed data and calculates the volume of discussion for specific keywords and their rate of change. This information is used to predict trends using machine learning algorithms. The model learns from past data and predicts future trends with high accuracy.

[0261] 3. Dynamic setting of advertising strategy

[0262] The server adjusts the pricing of ad space on relevant websites based on the predicted confidence level of the trend. As confidence increases, prices rise, allowing for lower prices in the early stages of a trend. This enables users to place ads at a competitive time.

[0263] 4. Notifications and Interface

[0264] The user's device receives notifications from the server and displays information about recommended ad placements. This includes the target page, current pricing, and relevant keywords. Users can use the interface to make quick decisions about placing ads.

[0265] 5. Results Analysis and Feedback

[0266] The server collects data from implemented advertising campaigns and evaluates their effectiveness. Based on this, the analysis results are continuously fed back to improve the accuracy of the predictive model. By improving predictive accuracy, the system can always provide effective advertising strategies that are in line with the latest trends.

[0267] As a concrete example, when a new music album is released, this system can be used to place advertisements ahead of the trending music streaming sites and popular blogs. This embodiment allows users to deploy effective advertising strategies quickly and at low cost in a highly competitive advertising market.

[0268] The following describes the processing flow.

[0269] Step 1:

[0270] The server periodically collects data from multiple sources, including news APIs, social media APIs, and e-commerce site APIs. Data collection is automated through scheduled queries.

[0271] Step 2:

[0272] The server preprocesses the collected data. This involves removing duplicate information and noise, and preparing the data for analysis. This process includes text cleaning and transformation operations.

[0273] Step 3:

[0274] The server analyzes pre-processed data and calculates the topic volume for each specified keyword. Furthermore, it models the rate of change to evaluate the increase or decrease in topic volume within a specific period.

[0275] Step 4:

[0276] The server predicts trends based on the analyzed data. It applies machine learning algorithms and utilizes models learned from historical data to calculate the likelihood and confidence level of keyword popularity.

[0277] Step 5:

[0278] The server dynamically adjusts the price of ad space on relevant websites based on predictions. If the reliability is high, the price of ad space will increase, making it possible to place ads at a lower price before competition intensifies.

[0279] Step 6:

[0280] The user terminal receives notifications from the server and displays proposals for ad submissions. The display content includes the corresponding website, recommended keywords, and price information for ad slots.

[0281] Step 7:

[0282] The user examines the proposed ad submissions through the interface on the terminal and makes decisions as appropriate. This process is flexible, and the user can optimize the submissions based on the set conditions.

[0283] Step 8:

[0284] The server collects the results of the executed ad campaign and analyzes the number of clicks and conversion rates. The data thus obtained is utilized as feedback to improve the prediction model. Through this feedback mechanism, the accuracy of the model is continuously improved.

[0285] (Example 1)

[0286] Next, 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".

[0287] In modern times where information changes rapidly, optimizing the timing and cost in ad submissions is a major challenge. In conventional methods, real-time data collection and analysis, as well as quick decision-making, are required, but doing this manually is inefficient and costly. Furthermore, it is also necessary to improve the accuracy of trend prediction based on past data and refine the ad strategy by feeding back the results of the ad campaign.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0289] In this invention, the server includes means for acquiring data from multiple information sources on the Internet and automatically performing data collection; means for preprocessing the acquired data, organizing unnecessary information and extracting features; and means for calculating the rate of change of information and analyzing the volume of topics based on the preprocessed data. This makes it possible to quickly and efficiently optimize the timing and price of advertising placement and accurately predict trends.

[0290] "Data collection methods" refer to methods of automatically acquiring data from multiple sources on the internet.

[0291] "Preprocessing" is the process of organizing acquired data, removing unnecessary information, and converting it into a format suitable for analysis.

[0292] "Feature extraction" is a technique that selects important information and attributes from data, forming the foundation for analysis.

[0293] "Rate of change" is an indicator that quantitatively measures the change in the volume of discussion surrounding a specific data point or keyword.

[0294] "Topic volume" is a quantitative measure that indicates the extent to which information about a particular theme or keyword is discussed in society.

[0295] "Trend forecasting" is the process of predicting future consumer and market trends based on past data patterns.

[0296] "Confidence level" is an indicator that shows the degree of confidence in the accuracy of the prediction results produced by a predictive model.

[0297] "Ad slot price adjustment" refers to the operation of changing the price of ad slots based on predicted trend data in order to achieve efficient ad placement.

[0298] "Analyzing the results of an advertising campaign" is the process of evaluating the effectiveness of the advertisements that have been placed and reflecting the results in the business strategy.

[0299] A "feedback mechanism" is a process that uses the results of advertising campaigns to improve predictive models and enable more accurate predictions.

[0300] This system implements a series of processes to streamline advertising placement, and its specific implementation is described below.

[0301] First, the server is responsible for acquiring data from multiple sources. Specifically, it acquires data via APIs from news portals and social media platforms on the internet. This process is automated, enabling real-time data collection. For example, it uses publicly available information APIs to periodically retrieve articles and posts related to specific keywords.

[0302] Next, the server preprocesses the acquired data. Here, natural language processing tools are used to remove noise and extract necessary features. For example, Python libraries such as NLTK and SpaCy are used to clean and tokenize the data.

[0303] Furthermore, the server analyzes the pre-processed data and applies a machine learning model to predict trends. This model learns from historical data and aims to accurately predict future trends. Common machine learning frameworks include Scikit-learn and TensorFlow.

[0304] Subsequently, the server dynamically adjusts the price of the ad space based on the analysis results. Specifically, it optimizes user ad spending by increasing the price of ad space when the trend's credibility is high and setting a lower price when it is low.

[0305] The user terminal plays a role in receiving notifications from the server. Here, information including which sites and media to publish advertisements on, current prices, and related keywords is displayed. Based on this information, the user can quickly determine an advertising strategy.

[0306] As an example of a prompt sentence, input the text "Generate a trend prediction related to the release of new albums on a music distribution service and propose a method to publish relevant advertisements at the optimal timing" into the text generation AI model. In this way, the user can always quickly catch changing trends and reflect that information in the advertising strategy.

[0307] The flow of the specific process in Example 1 will be described using FIG. 11.

[0308] Step 1:

[0309] The server collects data from multiple information sources. The input is specified keywords or hashtags, and based on this, information is obtained from news sites and social media platforms on the Internet. The output is a set of articles or posts that meet the specified conditions. As a specific operation, the server uses an API to accumulate data in real time while performing regular queries.

[0310] Step 2:

[0311] The server preprocesses the acquired data. The input is the collected unorganized data, and here, natural language processing tools are used to clean the data. Specifically, unnecessary noise is removed and language tokenization is performed. The output is a clean dataset that can be analyzed. For example, it includes the operation of removing special characters in the text and splitting the text into words.

[0312] Step 3:

[0313] The server analyzes pre-processed data and performs trend prediction. The input is a formatted dataset, to which machine learning algorithms are applied. Specifically, the server operates a model that predicts future trends based on past data patterns. The output is a predicted value of the future discussion volume for a specific keyword and its confidence level.

[0314] Step 4:

[0315] The server dynamically sets the advertising strategy based on the prediction results. The input is the result of the trend prediction, and the output is the adjusted pricing of the ad space. Specifically, the server increases the price when the confidence level is high and sets a lower price when the confidence level is low. This enables advertising to be placed at the optimal time and cost.

[0316] Step 5:

[0317] The user's device receives ad placement notifications sent from the server. The input is notification information from the server, including recommended target audiences, pricing, and relevant keywords. The output is a visual presentation of information to the user. Specifically, the device displays information on its interface to support the user in quickly making ad placement decisions.

[0318] Step 6:

[0319] The server analyzes the results of advertising campaigns and provides feedback. The input is the results data of the implemented advertising campaigns, and the output is an improved machine learning model. Specifically, the server evaluates the collected performance metrics (click-through rate, conversion rate, etc.) and updates the model to improve the accuracy of predictions for the next campaign.

[0320] (Application Example 1)

[0321] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0322] Maximizing the effectiveness of advertising campaigns and enabling timely ad placement are crucial challenges for many companies. However, current systems lack sufficient real-time information gathering, analysis, and trend prediction capabilities, resulting in a failure to maximize advertising effectiveness.

[0323] 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.

[0324] In this invention, the server includes means for acquiring information, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the topic volume and its rate of change, means for providing advertising recommendations to a display device based on predicted trends, and feedback means for evaluating the effectiveness of advertising and improving the relevant numerical model. This enables advertising to be placed at the appropriate time.

[0325] "Means of acquiring information" refers to a system that automatically collects data from various information sources on the internet.

[0326] "Means for preprocessing and removing duplication and noise" refers to techniques that remove unnecessary information from collected data before analysis, preparing it for analysis.

[0327] "Means for calculating topic volume and its rate of change" refers to a method for calculating the frequency of occurrence and increase / decrease of specific keywords from collected information.

[0328] "Means of providing advertising recommendations to display devices based on predicted trends" refers to a technology that visually notifies users of the appropriate timing for advertising based on analysis results.

[0329] A "feedback mechanism for evaluating the effectiveness of advertising and improving related numerical models" is a system that analyzes actual advertising effectiveness and improves the accuracy of prediction algorithms accordingly.

[0330] To realize this invention, it is necessary to build a program in which a server integrates and performs functions such as information gathering, analysis, and dynamic setting of advertising strategies. The hardware used includes a server computer for analyzing and calculating data, and the software used is an API for data gathering and Python and TensorFlow for analysis.

[0331] Specifically, the server collects data from the internet via APIs, preprocesses that data, and removes duplicates and noise. This preprocessing phase optimizes the information so that it can be effectively used in the next analysis step. Next, the server calculates the frequency and rate of change of specific topics based on the collected information, and uses this to predict future trends. In this process, a generative AI model trained on vast amounts of historical data is utilized.

[0332] The user's device includes a display device that receives and displays signals from the server. This device notifies the user in real time of advertising recommendations based on the analysis results. This notification allows the user to place ads at the optimal time, giving them a competitive advantage in the market. For example, if the user is in a certain region, ads related to popular products in that region can be placed instantly.

[0333] As a result, the effectiveness of the implemented advertisements is reflected, and the server continuously improves its predictive model based on the collected advertising performance data. This enables even more accurate predictions for future advertising campaigns, providing advertisers with the optimal strategy.

[0334] An example of a prompt message would be: "Analyze the latest sales information in the shopping mall and generate recommendations for effective advertising."

[0335] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0336] Step 1:

[0337] The server retrieves information from news sites and social media on the internet. The input consists of data obtained from each information source via APIs, which the server collects and stores in a database. Its primary function is the collection of large amounts of text data on topics that arise on a daily basis.

[0338] Step 2:

[0339] The server preprocesses the collected data, removing duplicates and noise. The input is the raw data collected in step 1, and the output is the cleaned data. Specifically, natural language processing is used to clean the text and prepare the data for analysis.

[0340] Step 3:

[0341] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. The input is noise-free data, and the output is data showing the frequency and rate of change of specific keywords. Here, a specialized algorithm is used to calculate which topics increase or decrease over time.

[0342] Step 4:

[0343] The server uses a generative AI model based on the analysis results to predict the likelihood of an epidemic. The input is the analysis results obtained in step 3, and the output is future epidemic prediction data. Since the model predicts epidemics from patterns in past data, the results of learning from similar past datasets are immediately utilized.

[0344] Step 5:

[0345] The device receives advertising recommendations from the server and displays them to the user. The input is advertising strategy information based on trend forecasts sent from the server, and the output is advertising recommendations provided to the user. Specifically, the analysis results are displayed in real time on a display such as smart glasses and suggested to the user as a notification.

[0346] Step 6:

[0347] Users review ad placement recommendations displayed on their devices and place ads as needed. The input is the information displayed on the device, and the output is the user's decision to place ads. In this step, the user makes an instant decision based on the information provided to determine whether to run the ad campaign.

[0348] Step 7:

[0349] The server collects and re-analyzes the results data of the implemented advertising campaigns. The input is the advertising campaign results data, and the output is feedback for improving the next predictive model. The success or failure of the campaign is evaluated, and the analysis model is adjusted using the data as feedback.

[0350] 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.

[0351] This invention is an advertising support system incorporating an emotion engine, which automates the entire process from data collection and analysis to ad placement proposals and feedback. An embodiment of this system is shown below.

[0352] 1. Information gathering and emotion recognition

[0353] The server retrieves information from news sites, social media, e-commerce platforms, and other sources. This is done through periodic data queries via APIs.

[0354] The collected data is analyzed through an emotion engine to recognize user emotions, such as positive or negative. Emotional information is particularly effective in word-of-mouth and reviews.

[0355] 2. Data Preprocessing and Trend Analysis

[0356] The server cleans the acquired data, removing duplicates and noise. Furthermore, it calculates topic volume and evaluates sentiment tendencies.

[0357] Preprocessed data is analyzed to calculate the likelihood and confidence level of a trend, based on sentiment information, along with its topic volume and rate of change.

[0358] 3. Trend forecasting and optimization of advertising strategies

[0359] The server uses machine learning algorithms based on the analyzed data to predict trends.

[0360] Emotional information is used to adjust the timing and content of advertising campaigns. This allows for the creation of optimal advertising strategies that align with emotional trends.

[0361] 4. Proposals and Notifications

[0362] The user's device receives suggestions from the server and displays the provided advertising strategies. These suggestions include information such as the pages where the ads will be placed, keywords, and pricing.

[0363] Sentiment-based recommendations help users understand the situation better and support faster decision-making.

[0364] 5. Analysis of results and improvement of the model

[0365] The server analyzes data from implemented advertising campaigns in detail and evaluates the effectiveness of the ads. Emotion-based effectiveness measurement is also performed.

[0366] The resulting data is incorporated into the predictive model as a feedback loop, continuously improving the accuracy of predictions and the quality of advertising strategies for future attempts.

[0367] As a concrete example, when a food-related product becomes a hot topic on social media, this system can be used to detect positive consumer sentiment and place advertisements on cooking blogs and recipe websites related to that trend. In this way, this embodiment allows advertisers to effectively capture the market at a time that is appropriate for consumer sentiment.

[0368] The following describes the processing flow.

[0369] Step 1:

[0370] The server retrieves data from external news sites, social media platforms, and e-commerce sites. This data retrieval is performed through periodic requests using APIs, gathering the latest data from diverse information sources.

[0371] Step 2:

[0372] The server preprocesses the acquired raw data before feeding it into the sentiment engine. This step involves cleaning the data, removing duplicates and irrelevant information, and removing noise to generate data optimized for analysis.

[0373] Step 3:

[0374] The server passes the pre-processed data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing techniques to assign emotion labels such as positive, negative, and neutral to each data point.

[0375] Step 4:

[0376] The server uses sentiment analysis results to calculate the volume of a topic and its rate of change. This information is input into a machine learning model to predict the likelihood and confidence level of its popularity.

[0377] Step 5:

[0378] The server dynamically adjusts the price of ad space on relevant websites, taking sentiment information into account. The higher the popularity and credibility of a trend, the higher the price of the ad space, providing users with an early opportunity to place ads at a lower price.

[0379] Step 6:

[0380] The user's device receives ad placement proposals sent from the server and displays ad content, pricing, and recommendation strategies based on sentiment analysis. The user can then make an ad placement decision based on this information.

[0381] Step 7:

[0382] Users interact with their devices and plan effective advertising campaigns based on the displayed ad suggestions. Emotion-based information provides users with sophisticated and compelling advertising options.

[0383] Step 8:

[0384] The server collects data on the results of implemented advertising campaigns and performs advertising effectiveness analysis. Furthermore, it incorporates the obtained sentiment data to form a feedback loop that improves the accuracy of predictions and the quality of strategies for the next campaign.

[0385] (Example 2)

[0386] 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".

[0387] Traditional advertising systems made it difficult to create timely advertising strategies that reflected user emotions, resulting in a failure to maximize advertising effectiveness. Furthermore, there was a lack of mechanisms to fully utilize past advertising data and incorporate it into future strategies.

[0388] 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.

[0389] In this invention, the server includes means for acquiring information from multiple sources, means for recognizing and analyzing emotions using natural language processing techniques from the pre-processed information, and means for determining the optimal timing and content of advertisements. This enables the creation of effective advertising strategies that respond to user emotions and the continuous improvement of predictive models based on past data.

[0390] A "data collection method" is a system for obtaining necessary information from multiple sources.

[0391] "Preprocessing" refers to a series of processes that remove duplicates and noise from acquired information and prepare it for analysis.

[0392] "Natural language processing technology" is a technology that allows computers to understand, generate, and analyze human language, and is also used for recognizing emotions.

[0393] "Emotion recognition" is the process of determining a user's emotional state from text data and classifying it into categories such as positive, negative, and neutral.

[0394] "Trend forecasting" is the process of predicting topics and market trends that are likely to attract attention in the future, based on analyzed data.

[0395] An "advertising strategy" is a set of guidelines and plans for determining the time, place, and content of advertisements to be delivered effectively.

[0396] A "feedback mechanism" is a system that evaluates the effectiveness of advertising and uses the results to improve the system's predictive models and advertising strategies.

[0397] A "user terminal" is a device that receives information and notifications from a server and transmits them to the user.

[0398] The system of this invention consistently performs data collection from a wide range of sources, sentiment analysis, trend forecasting, and strategic optimization of advertising placements. Details are described below.

[0399] The server at the core of this system retrieves data in real time from news sites, social media, and online trading platforms when collecting information. Specific technologies used include continuous data queries via web APIs, enabling the system to continuously obtain the latest information.

[0400] The collected data undergoes sentiment analysis using natural language processing technology on the server. Specifically, the technology used extracts positive, negative, and neutral emotions from the text. This sentiment recognition is supported by a generative AI model and contributes to optimizing advertising strategies based on user emotions.

[0401] The analyzed sentiment data is then analyzed by a trend prediction algorithm to forecast future trends. Based on this forecast, advertising strategies are optimized. The server utilizes the collected data and its analysis results to determine the most effective timing, targeting, and content for advertising.

[0402] Subsequently, a notification is sent from the server to the user's terminal, and the proposed advertising strategy is displayed. As a concrete example, if a food-related product is trending positively on social media, it is possible to leverage consumer sentiment to effectively place advertisements related to that product on cooking blogs and recipe websites.

[0403] Furthermore, this system aggregates advertising results data and uses feedback mechanisms to further improve the predictive model on the server in order to evaluate its effectiveness. This process allows for continuous improvement of the accuracy and results of subsequent advertising strategies.

[0404] An example of a prompt used as input to the generative AI model is, "Please tell me the optimal timing for placing ads based on current sentiment trends." This prompt allows the system to generate an effective advertising strategy based on user sentiment and market trends.

[0405] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0406] Step 1:

[0407] The server periodically retrieves data from news sites, social media, and e-commerce platforms via APIs. This input data may contain new trends and user sentiment. The retrieved data is stored for use in subsequent processing. Specifically, it performs processes such as aggregating articles and posts related to specific keywords.

[0408] Step 2:

[0409] The server preprocesses the acquired data. Since the input data is raw, it removes duplicates and noise to generate a clean dataset. Specifically, it removes HTML tags, deletes meaningless spaces, and filters out duplicate data. The output is formatted text data.

[0410] Step 3:

[0411] The server analyzes the formatted text data using natural language processing techniques to recognize user sentiment. In this step, it classifies the sentiment from the input text as positive, negative, or neutral. Specifically, it analyzes keywords and context within the text to calculate a sentiment score. The output is data with the sentiment classified.

[0412] Step 4:

[0413] The server performs trend analysis using machine learning algorithms based on data with classified sentiment. This step uses sentiment information and associated metadata as input data to calculate the volume of trending topics and their rate of change. Specifically, time-series analysis is used to predict the upward trend and peaks of topics. The output is data indicating the potential for future trends.

[0414] Step 5:

[0415] The server optimizes advertising strategies based on predicted trend information. Inputs at this stage include trend prediction data and sentiment information. This information is used to determine the optimal timing and content for ad placement. Specifically, it creates ad copy templates and selects appropriate ad slots. The output is the proposed advertising strategy.

[0416] Step 6:

[0417] The user's device receives advertising strategy proposals sent from the server and notifies the user. In this step, the acquired strategy information becomes the input information. The notification is displayed on the user's device, allowing the user to review the proposed strategy. Specifically, it displays information such as advertising targeting settings and the campaign schedule.

[0418] Step 7:

[0419] The server aggregates and analyzes the results data of implemented advertising campaigns. The input here is the performance data of the advertising campaigns. The server uses this data to measure advertising effectiveness and generate feedback that leads to improvements in the predictive model. Specific operations include calculating click-through rates and analyzing conversion rates. The output is the advertising performance and a newly tuned predictive model.

[0420] (Application Example 2)

[0421] 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."

[0422] In modern advertising strategies, accurately capturing consumer emotions and delivering optimized ads is crucial. However, while traditional systems can predict trends and dynamically adjust ad prices, they lack the ability to personalize ads based on individual user emotions. As a result, advertising effectiveness is not maximized, and potential opportunities are missed. To solve this problem, a new system is needed that incorporates emotional data and enhances the user experience.

[0423] 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.

[0424] In this invention, the server includes means for acquiring information from multiple sources, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the amount of topic and its rate of change, means for dynamically adjusting the price of advertising space on relevant websites based on predicted trends, means for dynamically optimizing and personalizing advertising content based on sentiment data acquired from personal information terminals, and means for collecting, analyzing, and providing feedback on advertising results data. This makes it possible to provide advertisements that meet the sentiment needs of individual users.

[0425] "Data collection means" refers to a device or system for acquiring information from multiple sources.

[0426] "Preprocessing means" refers to the process of organizing the collected information and removing duplication and noise.

[0427] A "topic volume calculation method" is a method for measuring how much attention a particular topic is receiving based on the analyzed information.

[0428] A "trend prediction tool" is a function that predicts future trends based on the data obtained.

[0429] An "ad space adjustment mechanism" is a system that changes the price of advertising space on a relevant website in response to fluctuations in demand.

[0430] "Personalization methods" refer to the process of optimizing ad content based on individual user sentiment data.

[0431] A "feedback mechanism" is a function that provides information to analyze the results of advertising campaigns and use it to help formulate future strategies.

[0432] This invention is an advertising support system that utilizes personal information terminals and servers, and provides a unique advertising experience by leveraging user emotional data.

[0433] The server first acquires information from multiple sources using data collection methods. This includes data from news sites, social media, and e-commerce platforms. The collected information is cleaned by pre-processing methods to remove duplication and noise. This allows for accurate calculation of topic volume and prediction of upcoming trends using trend prediction methods. Furthermore, based on these trend indicators, the advertising space prices on the website can be dynamically changed through advertising space adjustment methods.

[0434] Meanwhile, personal information terminals collect user sentiment information and send it to a server. Based on this sentiment data, the server dynamically optimizes ad content using personalization methods, providing ads optimized for each individual user. For example, if a user is interested in travel, travel-related ads will be displayed preferentially.

[0435] Ultimately, the server uses feedback mechanisms to collect and analyze data on the results of ad campaigns, continuously improving its predictive models for future campaigns. This enhances the accuracy and effectiveness of the advertising strategy.

[0436] For example, if a user posts on social media that they "want to go mountain climbing this weekend," this system can detect that positive emotion data and display advertisements for outdoor equipment.

[0437] An example of a prompt message might be: "Based on the user's feed, we've detected positive sentiment indicating interest in travel this weekend. Please suggest a strategy to display travel-related ads."

[0438] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0439] Step 1:

[0440] The server periodically retrieves data from multiple sources, such as news sites, social media, and e-commerce platforms, using APIs. It receives data from the APIs as input and prepares it for storage within the server. The output is raw, unprocessed data.

[0441] Step 2:

[0442] The server preprocesses the acquired raw data to remove duplicates and noise. Specifically, it applies data cleaning algorithms to remove duplicates and unnecessary information. It takes raw data as input and produces a clean dataset as output.

[0443] Step 3:

[0444] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. Here, a data analysis algorithm is used to identify the current topic of interest and calculate its fluctuations. Clean data is used as input, and the analysis results are obtained as output.

[0445] Step 4:

[0446] The server uses the analysis results to predict trends. It analyzes data using a machine learning model and predicts the next likely trending topic. It uses the analyzed data as input and obtains trend prediction data as output.

[0447] Step 5:

[0448] The server dynamically adjusts the price of website ad space based on trend forecasts. It uses a price adjustment algorithm to re-evaluate the value of ad space in real time. It takes trend forecast data as input and outputs adjusted ad prices.

[0449] Step 6:

[0450] The device acquires user sentiment data and sends it to the server. Sentiment analysis tools are used to analyze user input (e.g., text posts) and calculate a sentiment score. User data is taken as input, and a sentiment score is obtained as output.

[0451] Step 7:

[0452] The server generates personalized ads based on sentiment data. It uses a generative AI model to create ad content that aligns with the sentiment score. The sentiment score is used as input, and the optimized ad is obtained as output.

[0453] Step 8:

[0454] The user receives personalized advertisements through their device. The user's device receives notifications from the server and displays the advertisements on the screen. It receives advertising data from the server as input and shows the displayed advertisements to the user as output.

[0455] Step 9:

[0456] The server collects data on the results of ad placements and provides feedback. It uses ad effectiveness measurement tools to analyze the level of response achieved. It receives data after ad display as input and obtains ad effectiveness analysis results as output.

[0457] Step 10:

[0458] The server improves the predictive model based on the collected results data. A feedback loop is formed to improve accuracy in subsequent runs. The results data is used as input, and the improved predictive model is obtained as output.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] [Third Embodiment]

[0463] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] 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".

[0475] This invention is a system for streamlining advertising placement and consists of dedicated software and hardware. An embodiment thereof is shown below.

[0476] 1. Information gathering and processing

[0477] The server automatically retrieves relevant data from various sources on the internet. These sources include news sites, social media, and e-commerce platforms. This is achieved through periodic queries via APIs. The collected data is preprocessed to prepare it for analysis.

[0478] 2. Data Analysis and Trend Forecasting

[0479] The server analyzes pre-processed data and calculates the volume of discussion for specific keywords and their rate of change. This information is used to predict trends using machine learning algorithms. The model learns from past data and predicts future trends with high accuracy.

[0480] 3. Dynamic setting of advertising strategy

[0481] The server adjusts the pricing of ad space on relevant websites based on the predicted confidence level of the trend. As confidence increases, prices rise, allowing for lower prices in the early stages of a trend. This enables users to place ads at a competitive time.

[0482] 4. Notifications and Interface

[0483] The user's device receives notifications from the server and displays information about recommended ad placements. This includes the target page, current pricing, and relevant keywords. Users can use the interface to make quick decisions about placing ads.

[0484] 5. Results Analysis and Feedback

[0485] The server collects data from implemented advertising campaigns and evaluates their effectiveness. Based on this, the analysis results are continuously fed back to improve the accuracy of the predictive model. By improving predictive accuracy, the system can always provide effective advertising strategies that are in line with the latest trends.

[0486] As a concrete example, when a new music album is released, this system can be used to place advertisements ahead of the trending music streaming sites and popular blogs. This embodiment allows users to deploy effective advertising strategies quickly and at low cost in a highly competitive advertising market.

[0487] The following describes the processing flow.

[0488] Step 1:

[0489] The server periodically collects data from multiple sources, including news APIs, social media APIs, and e-commerce site APIs. Data collection is automated through scheduled queries.

[0490] Step 2:

[0491] The server preprocesses the collected data. This involves removing duplicate information and noise, and preparing the data for analysis. This process includes text cleaning and transformation operations.

[0492] Step 3:

[0493] The server analyzes pre-processed data and calculates the topic volume for each specified keyword. Furthermore, it models the rate of change to evaluate the increase or decrease in topic volume within a specific period.

[0494] Step 4:

[0495] The server predicts trends based on the analyzed data. It applies machine learning algorithms and utilizes models learned from historical data to calculate the likelihood and confidence level of keyword popularity.

[0496] Step 5:

[0497] The server dynamically adjusts the price of ad space on relevant websites based on predictions. If the reliability is high, the price of ad space will increase, making it possible to place ads at a lower price before competition intensifies.

[0498] Step 6:

[0499] The user's device receives notifications from the server and displays advertising placement suggestions. These suggestions include relevant websites, recommended keywords, and pricing information for ad slots.

[0500] Step 7:

[0501] Users review proposed ad placements and make decisions as appropriate through an interface on their device. This process is flexible, allowing users to optimize their ad placements based on set conditions.

[0502] Step 8:

[0503] The server collects the results of the implemented advertising campaigns and analyzes click-through rates and conversion rates. This data is then used as feedback to improve the predictive model. This feedback mechanism allows for continuous improvement of the model's accuracy.

[0504] (Example 1)

[0505] 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."

[0506] In today's rapidly changing information landscape, optimizing the timing and cost of advertising is a major challenge. Traditional methods require real-time data collection and analysis, as well as rapid decision-making, but performing these tasks manually is inefficient and costly. Furthermore, it is necessary to improve the accuracy of trend predictions based on historical data and to refine advertising strategies by feeding back the results of advertising campaigns.

[0507] 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.

[0508] In this invention, the server includes means for acquiring data from multiple information sources on the Internet and automatically performing data collection; means for preprocessing the acquired data, organizing unnecessary information and extracting features; and means for calculating the rate of change of information and analyzing the volume of topics based on the preprocessed data. This makes it possible to quickly and efficiently optimize the timing and price of advertising placement and accurately predict trends.

[0509] "Data collection methods" refer to methods of automatically acquiring data from multiple sources on the internet.

[0510] "Preprocessing" is the process of organizing acquired data, removing unnecessary information, and converting it into a format suitable for analysis.

[0511] "Feature extraction" is a technique that selects important information and attributes from data, forming the foundation for analysis.

[0512] "Rate of change" is an indicator that quantitatively measures the change in the volume of discussion surrounding a specific data point or keyword.

[0513] "Topic volume" is a quantitative measure that indicates the extent to which information about a particular theme or keyword is discussed in society.

[0514] "Trend forecasting" is the process of predicting future consumer and market trends based on past data patterns.

[0515] "Confidence level" is an indicator that shows the degree of confidence in the accuracy of the prediction results produced by a predictive model.

[0516] "Ad slot price adjustment" refers to the operation of changing the price of ad slots based on predicted trend data in order to achieve efficient ad placement.

[0517] "Analyzing the results of an advertising campaign" is the process of evaluating the effectiveness of the advertisements that have been placed and reflecting the results in the business strategy.

[0518] A "feedback mechanism" is a process that uses the results of advertising campaigns to improve predictive models and enable more accurate predictions.

[0519] This system implements a series of processes to streamline advertising placement, and its specific implementation is described below.

[0520] First, the server is responsible for acquiring data from multiple sources. Specifically, it acquires data via APIs from news portals and social media platforms on the internet. This process is automated, enabling real-time data collection. For example, it uses publicly available information APIs to periodically retrieve articles and posts related to specific keywords.

[0521] Next, the server preprocesses the acquired data. Here, natural language processing tools are used to remove noise and extract necessary features. For example, Python libraries such as NLTK and SpaCy are used to clean and tokenize the data.

[0522] Furthermore, the server analyzes the pre-processed data and applies a machine learning model to predict trends. This model learns from historical data and aims to accurately predict future trends. Common machine learning frameworks include Scikit-learn and TensorFlow.

[0523] Subsequently, the server dynamically adjusts the price of the ad space based on the analysis results. Specifically, it optimizes user ad spending by increasing the price of ad space when the trend's credibility is high and setting a lower price when it is low.

[0524] The user's device receives notifications from the server. This displays information including which sites and media outlets to advertise on, current pricing, and relevant keywords. The user then uses this information to quickly decide on their advertising strategy.

[0525] As an example of a prompt, the AI ​​model is given the text, "Generate trend predictions related to the release of a new album on music streaming services and suggest the optimal timing for placing relevant ads." In this way, users can quickly grasp ever-changing trends and reflect that information in their advertising strategies.

[0526] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0527] Step 1:

[0528] The server collects data from multiple sources. The input consists of specified keywords and hashtags, which are used to retrieve information from news sites and social media platforms on the internet. The output is a collection of articles and posts that match the specified criteria. Specifically, the server uses APIs to accumulate data in real time while performing periodic queries.

[0529] Step 2:

[0530] The server preprocesses the acquired data. The input is the collected, unorganized data, which is then cleaned using natural language processing tools. Specifically, it removes unwanted noise and tokenizes the language. The output is a clean, analyzable dataset. This includes tasks such as removing special characters from text and splitting sentences into individual words.

[0531] Step 3:

[0532] The server analyzes pre-processed data and performs trend prediction. The input is a formatted dataset, to which machine learning algorithms are applied. Specifically, the server operates a model that predicts future trends based on past data patterns. The output is a predicted value of the future discussion volume for a specific keyword and its confidence level.

[0533] Step 4:

[0534] The server dynamically sets the advertising strategy based on the prediction results. The input is the result of the trend prediction, and the output is the adjusted pricing of the ad space. Specifically, the server increases the price when the confidence level is high and sets a lower price when the confidence level is low. This enables advertising to be placed at the optimal time and cost.

[0535] Step 5:

[0536] The user's device receives ad placement notifications sent from the server. The input is notification information from the server, including recommended target audiences, pricing, and relevant keywords. The output is a visual presentation of information to the user. Specifically, the device displays information on its interface to support the user in quickly making ad placement decisions.

[0537] Step 6:

[0538] The server analyzes the results of advertising campaigns and provides feedback. The input is the results data of the implemented advertising campaigns, and the output is an improved machine learning model. Specifically, the server evaluates the collected performance metrics (click-through rate, conversion rate, etc.) and updates the model to improve the accuracy of predictions for the next campaign.

[0539] (Application Example 1)

[0540] 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."

[0541] Maximizing the effectiveness of advertising campaigns and enabling timely ad placement are crucial challenges for many companies. However, current systems lack sufficient real-time information gathering, analysis, and trend prediction capabilities, resulting in a failure to maximize advertising effectiveness.

[0542] 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.

[0543] In this invention, the server includes means for acquiring information, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the topic volume and its rate of change, means for providing advertising recommendations to a display device based on predicted trends, and feedback means for evaluating the effectiveness of advertising and improving the relevant numerical model. This enables advertising to be placed at the appropriate time.

[0544] "Means of acquiring information" refers to a system that automatically collects data from various information sources on the internet.

[0545] "Means for preprocessing and removing duplication and noise" refers to techniques that remove unnecessary information from collected data before analysis, preparing it for analysis.

[0546] "Means for calculating topic volume and its rate of change" refers to a method for calculating the frequency of occurrence and increase / decrease of specific keywords from collected information.

[0547] "Means of providing advertising recommendations to display devices based on predicted trends" refers to a technology that visually notifies users of the appropriate timing for advertising based on analysis results.

[0548] A "feedback mechanism for evaluating the effectiveness of advertising and improving related numerical models" is a system that analyzes actual advertising effectiveness and improves the accuracy of prediction algorithms accordingly.

[0549] To realize this invention, it is necessary to build a program in which a server integrates and performs functions such as information gathering, analysis, and dynamic setting of advertising strategies. The hardware used includes a server computer for analyzing and calculating data, and the software used is an API for data gathering and Python and TensorFlow for analysis.

[0550] Specifically, the server collects data from the internet via APIs, preprocesses that data, and removes duplicates and noise. This preprocessing phase optimizes the information so that it can be effectively used in the next analysis step. Next, the server calculates the frequency and rate of change of specific topics based on the collected information, and uses this to predict future trends. In this process, a generative AI model trained on vast amounts of historical data is utilized.

[0551] The user's device includes a display device that receives and displays signals from the server. This device notifies the user in real time of advertising recommendations based on the analysis results. This notification allows the user to place ads at the optimal time, giving them a competitive advantage in the market. For example, if the user is in a certain region, ads related to popular products in that region can be placed instantly.

[0552] As a result, the effectiveness of the implemented advertisements is reflected, and the server continuously improves its predictive model based on the collected advertising performance data. This enables even more accurate predictions for future advertising campaigns, providing advertisers with the optimal strategy.

[0553] An example of a prompt message would be: "Analyze the latest sales information in the shopping mall and generate recommendations for effective advertising."

[0554] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0555] Step 1:

[0556] The server retrieves information from news sites and social media on the internet. The input consists of data obtained from each information source via APIs, which the server collects and stores in a database. Its primary function is the collection of large amounts of text data on topics that arise on a daily basis.

[0557] Step 2:

[0558] The server preprocesses the collected data, removing duplicates and noise. The input is the raw data collected in step 1, and the output is the cleaned data. Specifically, natural language processing is used to clean the text and prepare the data for analysis.

[0559] Step 3:

[0560] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. The input is noise-free data, and the output is data showing the frequency and rate of change of specific keywords. Here, a specialized algorithm is used to calculate which topics increase or decrease over time.

[0561] Step 4:

[0562] The server uses a generative AI model based on the analysis results to predict the likelihood of an epidemic. The input is the analysis results obtained in step 3, and the output is future epidemic prediction data. Since the model predicts epidemics from patterns in past data, the results of learning from similar past datasets are immediately utilized.

[0563] Step 5:

[0564] The device receives advertising recommendations from the server and displays them to the user. The input is advertising strategy information based on trend forecasts sent from the server, and the output is advertising recommendations provided to the user. Specifically, the analysis results are displayed in real time on a display such as smart glasses and suggested to the user as a notification.

[0565] Step 6:

[0566] Users review ad placement recommendations displayed on their devices and place ads as needed. The input is the information displayed on the device, and the output is the user's decision to place ads. In this step, the user makes an instant decision based on the information provided to determine whether to run the ad campaign.

[0567] Step 7:

[0568] The server collects and re-analyzes the results data of the implemented advertising campaigns. The input is the advertising campaign results data, and the output is feedback for improving the next predictive model. The success or failure of the campaign is evaluated, and the analysis model is adjusted using the data as feedback.

[0569] 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.

[0570] This invention is an advertising support system incorporating an emotion engine, which automates the entire process from data collection and analysis to ad placement proposals and feedback. An embodiment of this system is shown below.

[0571] 1. Information gathering and emotion recognition

[0572] The server retrieves information from news sites, social media, e-commerce platforms, and other sources. This is done through periodic data queries via APIs.

[0573] The collected data is analyzed through an emotion engine to recognize user emotions, such as positive or negative. Emotional information is particularly effective in word-of-mouth and reviews.

[0574] 2. Data Preprocessing and Trend Analysis

[0575] The server cleans the acquired data, removing duplicates and noise. Furthermore, it calculates topic volume and evaluates sentiment tendencies.

[0576] Preprocessed data is analyzed to calculate the likelihood and confidence level of a trend, based on sentiment information, along with its topic volume and rate of change.

[0577] 3. Trend forecasting and optimization of advertising strategies

[0578] The server uses machine learning algorithms based on the analyzed data to predict trends.

[0579] Emotional information is used to adjust the timing and content of advertising campaigns. This allows for the creation of optimal advertising strategies that align with emotional trends.

[0580] 4. Proposals and Notifications

[0581] The user's device receives suggestions from the server and displays the provided advertising strategies. These suggestions include information such as the pages where the ads will be placed, keywords, and pricing.

[0582] Sentiment-based recommendations help users understand the situation better and support faster decision-making.

[0583] 5. Analysis of results and improvement of the model

[0584] The server analyzes data from implemented advertising campaigns in detail and evaluates the effectiveness of the ads. Emotion-based effectiveness measurement is also performed.

[0585] The resulting data is incorporated into the predictive model as a feedback loop, continuously improving the accuracy of predictions and the quality of advertising strategies for future attempts.

[0586] As a concrete example, when a food-related product becomes a hot topic on social media, this system can be used to detect positive consumer sentiment and place advertisements on cooking blogs and recipe websites related to that trend. In this way, this embodiment allows advertisers to effectively capture the market at a time that is appropriate for consumer sentiment.

[0587] The following describes the processing flow.

[0588] Step 1:

[0589] The server retrieves data from external news sites, social media platforms, and e-commerce sites. This data retrieval is performed through periodic requests using APIs, gathering the latest data from diverse information sources.

[0590] Step 2:

[0591] The server preprocesses the acquired raw data before feeding it into the sentiment engine. This step involves cleaning the data, removing duplicates and irrelevant information, and removing noise to generate data optimized for analysis.

[0592] Step 3:

[0593] The server passes the pre-processed data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing techniques to assign emotion labels such as positive, negative, and neutral to each data point.

[0594] Step 4:

[0595] The server uses sentiment analysis results to calculate the volume of a topic and its rate of change. This information is input into a machine learning model to predict the likelihood and confidence level of its popularity.

[0596] Step 5:

[0597] The server dynamically adjusts the price of ad space on relevant websites, taking sentiment information into account. The higher the popularity and credibility of a trend, the higher the price of the ad space, providing users with an early opportunity to place ads at a lower price.

[0598] Step 6:

[0599] The user's device receives ad placement proposals sent from the server and displays ad content, pricing, and recommendation strategies based on sentiment analysis. The user can then make an ad placement decision based on this information.

[0600] Step 7:

[0601] Users interact with their devices and plan effective advertising campaigns based on the displayed ad suggestions. Emotion-based information provides users with sophisticated and compelling advertising options.

[0602] Step 8:

[0603] The server collects data on the results of implemented advertising campaigns and performs advertising effectiveness analysis. Furthermore, it incorporates the obtained sentiment data to form a feedback loop that improves the accuracy of predictions and the quality of strategies for the next campaign.

[0604] (Example 2)

[0605] 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."

[0606] Traditional advertising systems made it difficult to create timely advertising strategies that reflected user emotions, resulting in a failure to maximize advertising effectiveness. Furthermore, there was a lack of mechanisms to fully utilize past advertising data and incorporate it into future strategies.

[0607] 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.

[0608] In this invention, the server includes means for acquiring information from multiple sources, means for recognizing and analyzing emotions using natural language processing techniques from the pre-processed information, and means for determining the optimal timing and content of advertisements. This enables the creation of effective advertising strategies that respond to user emotions and the continuous improvement of predictive models based on past data.

[0609] A "data collection method" is a system for obtaining necessary information from multiple sources.

[0610] "Preprocessing" refers to a series of processes that remove duplicates and noise from acquired information and prepare it for analysis.

[0611] "Natural language processing technology" is a technology that allows computers to understand, generate, and analyze human language, and is also used for recognizing emotions.

[0612] "Emotion recognition" is the process of determining a user's emotional state from text data and classifying it into categories such as positive, negative, and neutral.

[0613] "Trend forecasting" is the process of predicting topics and market trends that are likely to attract attention in the future, based on analyzed data.

[0614] An "advertising strategy" is a set of guidelines and plans for determining the time, place, and content of advertisements to be delivered effectively.

[0615] A "feedback mechanism" is a system that evaluates the effectiveness of advertising and uses the results to improve the system's predictive models and advertising strategies.

[0616] A "user terminal" is a device that receives information and notifications from a server and transmits them to the user.

[0617] The system of this invention consistently performs data collection from a wide range of sources, sentiment analysis, trend forecasting, and strategic optimization of advertising placements. Details are described below.

[0618] The server at the core of this system retrieves data in real time from news sites, social media, and online trading platforms when collecting information. Specific technologies used include continuous data queries via web APIs, enabling the system to continuously obtain the latest information.

[0619] The collected data undergoes sentiment analysis using natural language processing technology on the server. Specifically, the technology used extracts positive, negative, and neutral emotions from the text. This sentiment recognition is supported by a generative AI model and contributes to optimizing advertising strategies based on user emotions.

[0620] The analyzed sentiment data is then analyzed by a trend prediction algorithm to forecast future trends. Based on this forecast, advertising strategies are optimized. The server utilizes the collected data and its analysis results to determine the most effective timing, targeting, and content for advertising.

[0621] Subsequently, a notification is sent from the server to the user's terminal, and the proposed advertising strategy is displayed. As a concrete example, if a food-related product is trending positively on social media, it is possible to leverage consumer sentiment to effectively place advertisements related to that product on cooking blogs and recipe websites.

[0622] Furthermore, this system aggregates advertising results data and uses feedback mechanisms to further improve the predictive model on the server in order to evaluate its effectiveness. This process allows for continuous improvement of the accuracy and results of subsequent advertising strategies.

[0623] An example of a prompt used as input to the generative AI model is, "Please tell me the optimal timing for placing ads based on current sentiment trends." This prompt allows the system to generate an effective advertising strategy based on user sentiment and market trends.

[0624] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0625] Step 1:

[0626] The server periodically retrieves data from news sites, social media, and e-commerce platforms via APIs. This input data may contain new trends and user sentiment. The retrieved data is stored for use in subsequent processing. Specifically, it performs processes such as aggregating articles and posts related to specific keywords.

[0627] Step 2:

[0628] The server preprocesses the acquired data. Since the input data is raw, it removes duplicates and noise to generate a clean dataset. Specifically, it removes HTML tags, deletes meaningless spaces, and filters out duplicate data. The output is formatted text data.

[0629] Step 3:

[0630] The server analyzes the formatted text data using natural language processing techniques to recognize user sentiment. In this step, it classifies the sentiment from the input text as positive, negative, or neutral. Specifically, it analyzes keywords and context within the text to calculate a sentiment score. The output is data with the sentiment classified.

[0631] Step 4:

[0632] The server performs trend analysis using machine learning algorithms based on data with classified sentiment. This step uses sentiment information and associated metadata as input data to calculate the volume of trending topics and their rate of change. Specifically, time-series analysis is used to predict the upward trend and peaks of topics. The output is data indicating the potential for future trends.

[0633] Step 5:

[0634] The server optimizes advertising strategies based on predicted trend information. Inputs at this stage include trend prediction data and sentiment information. This information is used to determine the optimal timing and content for ad placement. Specifically, it creates ad copy templates and selects appropriate ad slots. The output is the proposed advertising strategy.

[0635] Step 6:

[0636] The user's device receives advertising strategy proposals sent from the server and notifies the user. In this step, the acquired strategy information becomes the input information. The notification is displayed on the user's device, allowing the user to review the proposed strategy. Specifically, it displays information such as advertising targeting settings and the campaign schedule.

[0637] Step 7:

[0638] The server aggregates and analyzes the results data of implemented advertising campaigns. The input here is the performance data of the advertising campaigns. The server uses this data to measure advertising effectiveness and generate feedback that leads to improvements in the predictive model. Specific operations include calculating click-through rates and analyzing conversion rates. The output is the advertising performance and a newly tuned predictive model.

[0639] (Application Example 2)

[0640] 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."

[0641] In modern advertising strategies, accurately capturing consumer emotions and delivering optimized ads is crucial. However, while traditional systems can predict trends and dynamically adjust ad prices, they lack the ability to personalize ads based on individual user emotions. As a result, advertising effectiveness is not maximized, and potential opportunities are missed. To solve this problem, a new system is needed that incorporates emotional data and enhances the user experience.

[0642] 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.

[0643] In this invention, the server includes means for acquiring information from multiple sources, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the amount of topic and its rate of change, means for dynamically adjusting the price of advertising space on relevant websites based on predicted trends, means for dynamically optimizing and personalizing advertising content based on sentiment data acquired from personal information terminals, and means for collecting, analyzing, and providing feedback on advertising results data. This makes it possible to provide advertisements that meet the sentiment needs of individual users.

[0644] "Data collection means" refers to a device or system for acquiring information from multiple sources.

[0645] "Preprocessing means" refers to the process of organizing the collected information and removing duplication and noise.

[0646] A "topic volume calculation method" is a method for measuring how much attention a particular topic is receiving based on the analyzed information.

[0647] A "trend prediction tool" is a function that predicts future trends based on the data obtained.

[0648] An "ad space adjustment mechanism" is a system that changes the price of advertising space on a relevant website in response to fluctuations in demand.

[0649] "Personalization methods" refer to the process of optimizing ad content based on individual user sentiment data.

[0650] A "feedback mechanism" is a function that provides information to analyze the results of advertising campaigns and use it to help formulate future strategies.

[0651] This invention is an advertising support system that utilizes personal information terminals and servers, and provides a unique advertising experience by leveraging user emotional data.

[0652] The server first acquires information from multiple sources using data collection methods. This includes data from news sites, social media, and e-commerce platforms. The collected information is cleaned by pre-processing methods to remove duplication and noise. This allows for accurate calculation of topic volume and prediction of upcoming trends using trend prediction methods. Furthermore, based on these trend indicators, the advertising space prices on the website can be dynamically changed through advertising space adjustment methods.

[0653] Meanwhile, personal information terminals collect user sentiment information and send it to a server. Based on this sentiment data, the server dynamically optimizes ad content using personalization methods, providing ads optimized for each individual user. For example, if a user is interested in travel, travel-related ads will be displayed preferentially.

[0654] Ultimately, the server uses feedback mechanisms to collect and analyze data on the results of ad campaigns, continuously improving its predictive models for future campaigns. This enhances the accuracy and effectiveness of the advertising strategy.

[0655] For example, if a user posts on social media that they "want to go mountain climbing this weekend," this system can detect that positive emotion data and display advertisements for outdoor equipment.

[0656] An example of a prompt message might be: "Based on the user's feed, we've detected positive sentiment indicating interest in travel this weekend. Please suggest a strategy to display travel-related ads."

[0657] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0658] Step 1:

[0659] The server periodically retrieves data from multiple sources, such as news sites, social media, and e-commerce platforms, using APIs. It receives data from the APIs as input and prepares it for storage within the server. The output is raw, unprocessed data.

[0660] Step 2:

[0661] The server preprocesses the acquired raw data to remove duplicates and noise. Specifically, it applies data cleaning algorithms to remove duplicates and unnecessary information. It takes raw data as input and produces a clean dataset as output.

[0662] Step 3:

[0663] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. Here, a data analysis algorithm is used to identify the current topic of interest and calculate its fluctuations. Clean data is used as input, and the analysis results are obtained as output.

[0664] Step 4:

[0665] The server uses the analysis results to predict trends. It analyzes data using a machine learning model and predicts the next likely trending topic. It uses the analyzed data as input and obtains trend prediction data as output.

[0666] Step 5:

[0667] The server dynamically adjusts the price of website ad space based on trend forecasts. It uses a price adjustment algorithm to re-evaluate the value of ad space in real time. It takes trend forecast data as input and outputs adjusted ad prices.

[0668] Step 6:

[0669] The device acquires user sentiment data and sends it to the server. Sentiment analysis tools are used to analyze user input (e.g., text posts) and calculate a sentiment score. User data is taken as input, and a sentiment score is obtained as output.

[0670] Step 7:

[0671] The server generates personalized ads based on sentiment data. It uses a generative AI model to create ad content that aligns with the sentiment score. The sentiment score is used as input, and the optimized ad is obtained as output.

[0672] Step 8:

[0673] The user receives personalized advertisements through their device. The user's device receives notifications from the server and displays the advertisements on the screen. It receives advertising data from the server as input and shows the displayed advertisements to the user as output.

[0674] Step 9:

[0675] The server collects data on the results of ad placements and provides feedback. It uses ad effectiveness measurement tools to analyze the level of response achieved. It receives data after ad display as input and obtains ad effectiveness analysis results as output.

[0676] Step 10:

[0677] The server improves the predictive model based on the collected results data. A feedback loop is formed to improve accuracy in subsequent runs. The results data is used as input, and the improved predictive model is obtained as output.

[0678] 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.

[0679] 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.

[0680] 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.

[0681] [Fourth Embodiment]

[0682] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0683] 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.

[0684] 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).

[0685] 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.

[0686] 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.

[0687] 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).

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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".

[0695] This invention is a system for streamlining advertising placement and consists of dedicated software and hardware. An embodiment thereof is shown below.

[0696] 1. Information gathering and processing

[0697] The server automatically retrieves relevant data from various sources on the internet. These sources include news sites, social media, and e-commerce platforms. This is achieved through periodic queries via APIs. The collected data is preprocessed to prepare it for analysis.

[0698] 2. Data Analysis and Trend Forecasting

[0699] The server analyzes pre-processed data and calculates the volume of discussion for specific keywords and their rate of change. This information is used to predict trends using machine learning algorithms. The model learns from past data and predicts future trends with high accuracy.

[0700] 3. Dynamic setting of advertising strategy

[0701] The server adjusts the pricing of ad space on relevant websites based on the predicted confidence level of the trend. As confidence increases, prices rise, allowing for lower prices in the early stages of a trend. This enables users to place ads at a competitive time.

[0702] 4. Notifications and Interface

[0703] The user's device receives notifications from the server and displays information about recommended ad placements. This includes the target page, current pricing, and relevant keywords. Users can use the interface to make quick decisions about placing ads.

[0704] 5. Results Analysis and Feedback

[0705] The server collects data from implemented advertising campaigns and evaluates their effectiveness. Based on this, the analysis results are continuously fed back to improve the accuracy of the predictive model. By improving predictive accuracy, the system can always provide effective advertising strategies that are in line with the latest trends.

[0706] As a concrete example, when a new music album is released, this system can be used to place advertisements ahead of the trending music streaming sites and popular blogs. This embodiment allows users to deploy effective advertising strategies quickly and at low cost in a highly competitive advertising market.

[0707] The following describes the processing flow.

[0708] Step 1:

[0709] The server periodically collects data from multiple sources, including news APIs, social media APIs, and e-commerce site APIs. Data collection is automated through scheduled queries.

[0710] Step 2:

[0711] The server preprocesses the collected data. This involves removing duplicate information and noise, and preparing the data for analysis. This process includes text cleaning and transformation operations.

[0712] Step 3:

[0713] The server analyzes pre-processed data and calculates the topic volume for each specified keyword. Furthermore, it models the rate of change to evaluate the increase or decrease in topic volume within a specific period.

[0714] Step 4:

[0715] The server predicts trends based on the analyzed data. It applies machine learning algorithms and utilizes models learned from historical data to calculate the likelihood and confidence level of keyword popularity.

[0716] Step 5:

[0717] The server dynamically adjusts the price of ad space on relevant websites based on predictions. If the reliability is high, the price of ad space will increase, making it possible to place ads at a lower price before competition intensifies.

[0718] Step 6:

[0719] The user's device receives notifications from the server and displays advertising placement suggestions. These suggestions include relevant websites, recommended keywords, and pricing information for ad slots.

[0720] Step 7:

[0721] Users review proposed ad placements and make decisions as appropriate through an interface on their device. This process is flexible, allowing users to optimize their ad placements based on set conditions.

[0722] Step 8:

[0723] The server collects the results of the implemented advertising campaigns and analyzes click-through rates and conversion rates. This data is then used as feedback to improve the predictive model. This feedback mechanism allows for continuous improvement of the model's accuracy.

[0724] (Example 1)

[0725] 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".

[0726] In today's rapidly changing information landscape, optimizing the timing and cost of advertising is a major challenge. Traditional methods require real-time data collection and analysis, as well as rapid decision-making, but performing these tasks manually is inefficient and costly. Furthermore, it is necessary to improve the accuracy of trend predictions based on historical data and to refine advertising strategies by feeding back the results of advertising campaigns.

[0727] 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.

[0728] In this invention, the server includes means for acquiring data from multiple information sources on the Internet and automatically performing data collection; means for preprocessing the acquired data, organizing unnecessary information and extracting features; and means for calculating the rate of change of information and analyzing the volume of topics based on the preprocessed data. This makes it possible to quickly and efficiently optimize the timing and price of advertising placement and accurately predict trends.

[0729] "Data collection methods" refer to methods of automatically acquiring data from multiple sources on the internet.

[0730] "Preprocessing" is the process of organizing acquired data, removing unnecessary information, and converting it into a format suitable for analysis.

[0731] "Feature extraction" is a technique that selects important information and attributes from data, forming the foundation for analysis.

[0732] "Rate of change" is an indicator that quantitatively measures the change in the volume of discussion surrounding a specific data point or keyword.

[0733] "Topic volume" is a quantitative measure that indicates the extent to which information about a particular theme or keyword is discussed in society.

[0734] "Trend forecasting" is the process of predicting future consumer and market trends based on past data patterns.

[0735] "Confidence level" is an indicator that shows the degree of confidence in the accuracy of the prediction results produced by a predictive model.

[0736] "Ad slot price adjustment" refers to the operation of changing the price of ad slots based on predicted trend data in order to achieve efficient ad placement.

[0737] "Analyzing the results of an advertising campaign" is the process of evaluating the effectiveness of the advertisements that have been placed and reflecting the results in the business strategy.

[0738] A "feedback mechanism" is a process that uses the results of advertising campaigns to improve predictive models and enable more accurate predictions.

[0739] This system implements a series of processes to streamline advertising placement, and its specific implementation is described below.

[0740] First, the server is responsible for acquiring data from multiple sources. Specifically, it acquires data via APIs from news portals and social media platforms on the internet. This process is automated, enabling real-time data collection. For example, it uses publicly available information APIs to periodically retrieve articles and posts related to specific keywords.

[0741] Next, the server preprocesses the acquired data. Here, natural language processing tools are used to remove noise and extract necessary features. For example, Python libraries such as NLTK and SpaCy are used to clean and tokenize the data.

[0742] Furthermore, the server analyzes the pre-processed data and applies a machine learning model to predict trends. This model learns from historical data and aims to accurately predict future trends. Common machine learning frameworks include Scikit-learn and TensorFlow.

[0743] Subsequently, the server dynamically adjusts the price of the ad space based on the analysis results. Specifically, it optimizes user ad spending by increasing the price of ad space when the trend's credibility is high and setting a lower price when it is low.

[0744] The user's device receives notifications from the server. This displays information including which sites and media outlets to advertise on, current pricing, and relevant keywords. The user then uses this information to quickly decide on their advertising strategy.

[0745] As an example of a prompt, the AI ​​model is given the text, "Generate trend predictions related to the release of a new album on music streaming services and suggest the optimal timing for placing relevant ads." In this way, users can quickly grasp ever-changing trends and reflect that information in their advertising strategies.

[0746] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0747] Step 1:

[0748] The server collects data from multiple sources. The input consists of specified keywords and hashtags, which are used to retrieve information from news sites and social media platforms on the internet. The output is a collection of articles and posts that match the specified criteria. Specifically, the server uses APIs to accumulate data in real time while performing periodic queries.

[0749] Step 2:

[0750] The server preprocesses the acquired data. The input is the collected, unorganized data, which is then cleaned using natural language processing tools. Specifically, it removes unwanted noise and tokenizes the language. The output is a clean, analyzable dataset. This includes tasks such as removing special characters from text and splitting sentences into individual words.

[0751] Step 3:

[0752] The server analyzes pre-processed data and performs trend prediction. The input is a formatted dataset, to which machine learning algorithms are applied. Specifically, the server operates a model that predicts future trends based on past data patterns. The output is a predicted value of the future discussion volume for a specific keyword and its confidence level.

[0753] Step 4:

[0754] The server dynamically sets the advertising strategy based on the prediction results. The input is the result of the trend prediction, and the output is the adjusted pricing of the ad space. Specifically, the server increases the price when the confidence level is high and sets a lower price when the confidence level is low. This enables advertising to be placed at the optimal time and cost.

[0755] Step 5:

[0756] The user's device receives ad placement notifications sent from the server. The input is notification information from the server, including recommended target audiences, pricing, and relevant keywords. The output is a visual presentation of information to the user. Specifically, the device displays information on its interface to support the user in quickly making ad placement decisions.

[0757] Step 6:

[0758] The server analyzes the results of advertising campaigns and provides feedback. The input is the results data of the implemented advertising campaigns, and the output is an improved machine learning model. Specifically, the server evaluates the collected performance metrics (click-through rate, conversion rate, etc.) and updates the model to improve the accuracy of predictions for the next campaign.

[0759] (Application Example 1)

[0760] 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".

[0761] Maximizing the effectiveness of advertising campaigns and enabling timely ad placement are crucial challenges for many companies. However, current systems lack sufficient real-time information gathering, analysis, and trend prediction capabilities, resulting in a failure to maximize advertising effectiveness.

[0762] 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.

[0763] In this invention, the server includes means for acquiring information, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the topic volume and its rate of change, means for providing advertising recommendations to a display device based on predicted trends, and feedback means for evaluating the effectiveness of advertising and improving the relevant numerical model. This enables advertising to be placed at the appropriate time.

[0764] "Means of acquiring information" refers to a system that automatically collects data from various information sources on the internet.

[0765] "Means for preprocessing and removing duplication and noise" refers to techniques that remove unnecessary information from collected data before analysis, preparing it for analysis.

[0766] "Means for calculating topic volume and its rate of change" refers to a method for calculating the frequency of occurrence and increase / decrease of specific keywords from collected information.

[0767] "Means of providing advertising recommendations to display devices based on predicted trends" refers to a technology that visually notifies users of the appropriate timing for advertising based on analysis results.

[0768] A "feedback mechanism for evaluating the effectiveness of advertising and improving related numerical models" is a system that analyzes actual advertising effectiveness and improves the accuracy of prediction algorithms accordingly.

[0769] To realize this invention, it is necessary to build a program in which a server integrates and performs functions such as information gathering, analysis, and dynamic setting of advertising strategies. The hardware used includes a server computer for analyzing and calculating data, and the software used is an API for data gathering and Python and TensorFlow for analysis.

[0770] Specifically, the server collects data from the internet via APIs, preprocesses that data, and removes duplicates and noise. This preprocessing phase optimizes the information so that it can be effectively used in the next analysis step. Next, the server calculates the frequency and rate of change of specific topics based on the collected information, and uses this to predict future trends. In this process, a generative AI model trained on vast amounts of historical data is utilized.

[0771] The user's device includes a display device that receives and displays signals from the server. This device notifies the user in real time of advertising recommendations based on the analysis results. This notification allows the user to place ads at the optimal time, giving them a competitive advantage in the market. For example, if the user is in a certain region, ads related to popular products in that region can be placed instantly.

[0772] As a result, the effectiveness of the implemented advertisements is reflected, and the server continuously improves its predictive model based on the collected advertising performance data. This enables even more accurate predictions for future advertising campaigns, providing advertisers with the optimal strategy.

[0773] An example of a prompt message would be: "Analyze the latest sales information in the shopping mall and generate recommendations for effective advertising."

[0774] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0775] Step 1:

[0776] The server retrieves information from news sites and social media on the internet. The input consists of data obtained from each information source via APIs, which the server collects and stores in a database. Its primary function is the collection of large amounts of text data on topics that arise on a daily basis.

[0777] Step 2:

[0778] The server preprocesses the collected data, removing duplicates and noise. The input is the raw data collected in step 1, and the output is the cleaned data. Specifically, natural language processing is used to clean the text and prepare the data for analysis.

[0779] Step 3:

[0780] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. The input is noise-free data, and the output is data showing the frequency and rate of change of specific keywords. Here, a specialized algorithm is used to calculate which topics increase or decrease over time.

[0781] Step 4:

[0782] The server uses a generative AI model based on the analysis results to predict the likelihood of an epidemic. The input is the analysis results obtained in step 3, and the output is future epidemic prediction data. Since the model predicts epidemics from patterns in past data, the results of learning from similar past datasets are immediately utilized.

[0783] Step 5:

[0784] The device receives advertising recommendations from the server and displays them to the user. The input is advertising strategy information based on trend forecasts sent from the server, and the output is advertising recommendations provided to the user. Specifically, the analysis results are displayed in real time on a display such as smart glasses and suggested to the user as a notification.

[0785] Step 6:

[0786] Users review ad placement recommendations displayed on their devices and place ads as needed. The input is the information displayed on the device, and the output is the user's decision to place ads. In this step, the user makes an instant decision based on the information provided to determine whether to run the ad campaign.

[0787] Step 7:

[0788] The server collects and re-analyzes the results data of the implemented advertising campaigns. The input is the advertising campaign results data, and the output is feedback for improving the next predictive model. The success or failure of the campaign is evaluated, and the analysis model is adjusted using the data as feedback.

[0789] 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.

[0790] This invention is an advertising support system incorporating an emotion engine, which automates the entire process from data collection and analysis to ad placement proposals and feedback. An embodiment of this system is shown below.

[0791] 1. Information gathering and emotion recognition

[0792] The server retrieves information from news sites, social media, e-commerce platforms, and other sources. This is done through periodic data queries via APIs.

[0793] The collected data is analyzed through an emotion engine to recognize user emotions, such as positive or negative. Emotional information is particularly effective in word-of-mouth and reviews.

[0794] 2. Data Preprocessing and Trend Analysis

[0795] The server cleans the acquired data, removing duplicates and noise. Furthermore, it calculates topic volume and evaluates sentiment tendencies.

[0796] Preprocessed data is analyzed to calculate the likelihood and confidence level of a trend, based on sentiment information, along with its topic volume and rate of change.

[0797] 3. Trend forecasting and optimization of advertising strategies

[0798] The server uses machine learning algorithms based on the analyzed data to predict trends.

[0799] Emotional information is used to adjust the timing and content of advertising campaigns. This allows for the creation of optimal advertising strategies that align with emotional trends.

[0800] 4. Proposals and Notifications

[0801] The user's device receives suggestions from the server and displays the provided advertising strategies. These suggestions include information such as the pages where the ads will be placed, keywords, and pricing.

[0802] Sentiment-based recommendations help users understand the situation better and support faster decision-making.

[0803] 5. Analysis of results and improvement of the model

[0804] The server analyzes data from implemented advertising campaigns in detail and evaluates the effectiveness of the ads. Emotion-based effectiveness measurement is also performed.

[0805] The resulting data is incorporated into the predictive model as a feedback loop, continuously improving the accuracy of predictions and the quality of advertising strategies for future attempts.

[0806] As a concrete example, when a food-related product becomes a hot topic on social media, this system can be used to detect positive consumer sentiment and place advertisements on cooking blogs and recipe websites related to that trend. In this way, this embodiment allows advertisers to effectively capture the market at a time that is appropriate for consumer sentiment.

[0807] The following describes the processing flow.

[0808] Step 1:

[0809] The server retrieves data from external news sites, social media platforms, and e-commerce sites. This data retrieval is performed through periodic requests using APIs, gathering the latest data from diverse information sources.

[0810] Step 2:

[0811] The server preprocesses the acquired raw data before feeding it into the sentiment engine. This step involves cleaning the data, removing duplicates and irrelevant information, and removing noise to generate data optimized for analysis.

[0812] Step 3:

[0813] The server passes the pre-processed data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing techniques to assign emotion labels such as positive, negative, and neutral to each data point.

[0814] Step 4:

[0815] The server uses sentiment analysis results to calculate the volume of a topic and its rate of change. This information is input into a machine learning model to predict the likelihood and confidence level of its popularity.

[0816] Step 5:

[0817] The server dynamically adjusts the price of ad space on relevant websites, taking sentiment information into account. The higher the popularity and credibility of a trend, the higher the price of the ad space, providing users with an early opportunity to place ads at a lower price.

[0818] Step 6:

[0819] The user's device receives ad placement proposals sent from the server and displays ad content, pricing, and recommendation strategies based on sentiment analysis. The user can then make an ad placement decision based on this information.

[0820] Step 7:

[0821] Users interact with their devices and plan effective advertising campaigns based on the displayed ad suggestions. Emotion-based information provides users with sophisticated and compelling advertising options.

[0822] Step 8:

[0823] The server collects data on the results of implemented advertising campaigns and performs advertising effectiveness analysis. Furthermore, it incorporates the obtained sentiment data to form a feedback loop that improves the accuracy of predictions and the quality of strategies for the next campaign.

[0824] (Example 2)

[0825] 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".

[0826] Traditional advertising systems made it difficult to create timely advertising strategies that reflected user emotions, resulting in a failure to maximize advertising effectiveness. Furthermore, there was a lack of mechanisms to fully utilize past advertising data and incorporate it into future strategies.

[0827] 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.

[0828] In this invention, the server includes means for acquiring information from multiple sources, means for recognizing and analyzing emotions using natural language processing techniques from the pre-processed information, and means for determining the optimal timing and content of advertisements. This enables the creation of effective advertising strategies that respond to user emotions and the continuous improvement of predictive models based on past data.

[0829] A "data collection method" is a system for obtaining necessary information from multiple sources.

[0830] "Preprocessing" refers to a series of processes that remove duplicates and noise from acquired information and prepare it for analysis.

[0831] "Natural language processing technology" is a technology that allows computers to understand, generate, and analyze human language, and is also used for recognizing emotions.

[0832] "Emotion recognition" is the process of determining a user's emotional state from text data and classifying it into categories such as positive, negative, and neutral.

[0833] "Trend forecasting" is the process of predicting topics and market trends that are likely to attract attention in the future, based on analyzed data.

[0834] An "advertising strategy" is a set of guidelines and plans for determining the time, place, and content of advertisements to be delivered effectively.

[0835] A "feedback mechanism" is a system that evaluates the effectiveness of advertising and uses the results to improve the system's predictive models and advertising strategies.

[0836] A "user terminal" is a device that receives information and notifications from a server and transmits them to the user.

[0837] The system of this invention consistently performs data collection from a wide range of sources, sentiment analysis, trend forecasting, and strategic optimization of advertising placements. Details are described below.

[0838] The server at the core of this system retrieves data in real time from news sites, social media, and online trading platforms when collecting information. Specific technologies used include continuous data queries via web APIs, enabling the system to continuously obtain the latest information.

[0839] The collected data undergoes sentiment analysis using natural language processing technology on the server. Specifically, the technology used extracts positive, negative, and neutral emotions from the text. This sentiment recognition is supported by a generative AI model and contributes to optimizing advertising strategies based on user emotions.

[0840] The analyzed sentiment data is then analyzed by a trend prediction algorithm to forecast future trends. Based on this forecast, advertising strategies are optimized. The server utilizes the collected data and its analysis results to determine the most effective timing, targeting, and content for advertising.

[0841] Subsequently, a notification is sent from the server to the user's terminal, and the proposed advertising strategy is displayed. As a concrete example, if a food-related product is trending positively on social media, it is possible to leverage consumer sentiment to effectively place advertisements related to that product on cooking blogs and recipe websites.

[0842] Furthermore, this system aggregates advertising results data and uses feedback mechanisms to further improve the predictive model on the server in order to evaluate its effectiveness. This process allows for continuous improvement of the accuracy and results of subsequent advertising strategies.

[0843] An example of a prompt used as input to the generative AI model is, "Please tell me the optimal timing for placing ads based on current sentiment trends." This prompt allows the system to generate an effective advertising strategy based on user sentiment and market trends.

[0844] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0845] Step 1:

[0846] The server periodically retrieves data from news sites, social media, and e-commerce platforms via APIs. This input data may contain new trends and user sentiment. The retrieved data is stored for use in subsequent processing. Specifically, it performs processes such as aggregating articles and posts related to specific keywords.

[0847] Step 2:

[0848] The server preprocesses the acquired data. Since the input data is raw, it removes duplicates and noise to generate a clean dataset. Specifically, it removes HTML tags, deletes meaningless spaces, and filters out duplicate data. The output is formatted text data.

[0849] Step 3:

[0850] The server analyzes the formatted text data using natural language processing techniques to recognize user sentiment. In this step, it classifies the sentiment from the input text as positive, negative, or neutral. Specifically, it analyzes keywords and context within the text to calculate a sentiment score. The output is data with the sentiment classified.

[0851] Step 4:

[0852] The server performs trend analysis using machine learning algorithms based on data with classified sentiment. This step uses sentiment information and associated metadata as input data to calculate the volume of trending topics and their rate of change. Specifically, time-series analysis is used to predict the upward trend and peaks of topics. The output is data indicating the potential for future trends.

[0853] Step 5:

[0854] The server optimizes advertising strategies based on predicted trend information. Inputs at this stage include trend prediction data and sentiment information. This information is used to determine the optimal timing and content for ad placement. Specifically, it creates ad copy templates and selects appropriate ad slots. The output is the proposed advertising strategy.

[0855] Step 6:

[0856] The user's device receives advertising strategy proposals sent from the server and notifies the user. In this step, the acquired strategy information becomes the input information. The notification is displayed on the user's device, allowing the user to review the proposed strategy. Specifically, it displays information such as advertising targeting settings and the campaign schedule.

[0857] Step 7:

[0858] The server aggregates and analyzes the results data of implemented advertising campaigns. The input here is the performance data of the advertising campaigns. The server uses this data to measure advertising effectiveness and generate feedback that leads to improvements in the predictive model. Specific operations include calculating click-through rates and analyzing conversion rates. The output is the advertising performance and a newly tuned predictive model.

[0859] (Application Example 2)

[0860] 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".

[0861] In modern advertising strategies, accurately capturing consumer emotions and delivering optimized ads is crucial. However, while traditional systems can predict trends and dynamically adjust ad prices, they lack the ability to personalize ads based on individual user emotions. As a result, advertising effectiveness is not maximized, and potential opportunities are missed. To solve this problem, a new system is needed that incorporates emotional data and enhances the user experience.

[0862] 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.

[0863] In this invention, the server includes means for acquiring information from multiple sources, means for preprocessing the acquired information and removing duplication and noise, means for analyzing the preprocessed information and calculating the amount of topic and its rate of change, means for dynamically adjusting the price of advertising space on relevant websites based on predicted trends, means for dynamically optimizing and personalizing advertising content based on sentiment data acquired from personal information terminals, and means for collecting, analyzing, and providing feedback on advertising results data. This makes it possible to provide advertisements that meet the sentiment needs of individual users.

[0864] "Data collection means" refers to a device or system for acquiring information from multiple sources.

[0865] "Preprocessing means" refers to the process of organizing the collected information and removing duplication and noise.

[0866] A "topic volume calculation method" is a method for measuring how much attention a particular topic is receiving based on the analyzed information.

[0867] A "trend prediction tool" is a function that predicts future trends based on the data obtained.

[0868] An "ad space adjustment mechanism" is a system that changes the price of advertising space on a relevant website in response to fluctuations in demand.

[0869] "Personalization methods" refer to the process of optimizing ad content based on individual user sentiment data.

[0870] A "feedback mechanism" is a function that provides information to analyze the results of advertising campaigns and use it to help formulate future strategies.

[0871] This invention is an advertising support system that utilizes personal information terminals and servers, and provides a unique advertising experience by leveraging user emotional data.

[0872] The server first acquires information from multiple sources using data collection methods. This includes data from news sites, social media, and e-commerce platforms. The collected information is cleaned by pre-processing methods to remove duplication and noise. This allows for accurate calculation of topic volume and prediction of upcoming trends using trend prediction methods. Furthermore, based on these trend indicators, the advertising space prices on the website can be dynamically changed through advertising space adjustment methods.

[0873] Meanwhile, personal information terminals collect user sentiment information and send it to a server. Based on this sentiment data, the server dynamically optimizes ad content using personalization methods, providing ads optimized for each individual user. For example, if a user is interested in travel, travel-related ads will be displayed preferentially.

[0874] Ultimately, the server uses feedback mechanisms to collect and analyze data on the results of ad campaigns, continuously improving its predictive models for future campaigns. This enhances the accuracy and effectiveness of the advertising strategy.

[0875] For example, if a user posts on social media that they "want to go mountain climbing this weekend," this system can detect that positive emotion data and display advertisements for outdoor equipment.

[0876] An example of a prompt message might be: "Based on the user's feed, we've detected positive sentiment indicating interest in travel this weekend. Please suggest a strategy to display travel-related ads."

[0877] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0878] Step 1:

[0879] The server periodically retrieves data from multiple sources, such as news sites, social media, and e-commerce platforms, using APIs. It receives data from the APIs as input and prepares it for storage within the server. The output is raw, unprocessed data.

[0880] Step 2:

[0881] The server preprocesses the acquired raw data to remove duplicates and noise. Specifically, it applies data cleaning algorithms to remove duplicates and unnecessary information. It takes raw data as input and produces a clean dataset as output.

[0882] Step 3:

[0883] The server analyzes the pre-processed data and calculates the topic volume and its rate of change. Here, a data analysis algorithm is used to identify the current topic of interest and calculate its fluctuations. Clean data is used as input, and the analysis results are obtained as output.

[0884] Step 4:

[0885] The server uses the analysis results to predict trends. It analyzes data using a machine learning model and predicts the next likely trending topic. It uses the analyzed data as input and obtains trend prediction data as output.

[0886] Step 5:

[0887] The server dynamically adjusts the price of website ad space based on trend forecasts. It uses a price adjustment algorithm to re-evaluate the value of ad space in real time. It takes trend forecast data as input and outputs adjusted ad prices.

[0888] Step 6:

[0889] The device acquires user sentiment data and sends it to the server. Sentiment analysis tools are used to analyze user input (e.g., text posts) and calculate a sentiment score. User data is taken as input, and a sentiment score is obtained as output.

[0890] Step 7:

[0891] The server generates personalized ads based on sentiment data. It uses a generative AI model to create ad content that aligns with the sentiment score. The sentiment score is used as input, and the optimized ad is obtained as output.

[0892] Step 8:

[0893] The user receives personalized advertisements through their device. The user's device receives notifications from the server and displays the advertisements on the screen. It receives advertising data from the server as input and shows the displayed advertisements to the user as output.

[0894] Step 9:

[0895] The server collects data on the results of ad placements and provides feedback. It uses ad effectiveness measurement tools to analyze the level of response achieved. It receives data after ad display as input and obtains ad effectiveness analysis results as output.

[0896] Step 10:

[0897] The server improves the predictive model based on the collected results data. A feedback loop is formed to improve accuracy in subsequent runs. The results data is used as input, and the improved predictive model is obtained as output.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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."

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] The following is further disclosed regarding the embodiments described above.

[0920] (Claim 1)

[0921] A data collection means, comprising means for acquiring information from multiple information sources,

[0922] Means for preprocessing acquired information and removing duplicates and noise,

[0923] A means for analyzing pre-processed information and calculating the topic volume and its rate of change,

[0924] A means of predicting the likelihood and reliability of an epidemic using analyzed data,

[0925] A means of dynamically adjusting the price of advertising space on relevant websites based on predicted trends,

[0926] A means of notifying users of advertising placement proposals on their devices,

[0927] A means of collecting and analyzing advertising results data and providing feedback to improve predictive models,

[0928] A system that includes this.

[0929] (Claim 2)

[0930] The system according to claim 1, which performs trend prediction using a machine learning algorithm based on the analyzed data.

[0931] (Claim 3)

[0932] The system according to claim 1, which analyzes the data obtained as a result of the aforementioned advertising placement and updates the prediction model to improve the accuracy of predictions for subsequent times.

[0933] "Example 1"

[0934] (Claim 1)

[0935] A means of automatically collecting data by obtaining data from multiple sources on the internet,

[0936] A means for preprocessing acquired data, organizing unnecessary information and extracting features,

[0937] A means for calculating the rate of change of information and analyzing the topic volume based on preprocessed data,

[0938] A means of predicting future trends and their reliability based on past data,

[0939] A means to dynamically adjust the price of ad space based on the prediction results,

[0940] A means of providing notifications to user terminals to expedite the placement of advertisements,

[0941] A feedback mechanism that analyzes the results of advertising campaigns and uses that data to optimize predictive algorithms,

[0942] A system that includes this.

[0943] (Claim 2)

[0944] The system according to claim 1, which applies machine learning technology to predict trends from the data and improves reliability.

[0945] (Claim 3)

[0946] The system according to claim 1, which analyzes advertising results data in detail, updates a predictive model based on the insights gained, and improves its accuracy.

[0947] "Application Example 1"

[0948] (Claim 1)

[0949] Means of obtaining information,

[0950] A means for preprocessing the acquired information and removing duplicates and noise,

[0951] A means for analyzing pre-processed information and calculating the topic volume and its rate of change,

[0952] A means of predicting the likelihood and reliability of an epidemic using analyzed information,

[0953] A means of providing advertising recommendations to a display device based on predicted trends,

[0954] A feedback mechanism for evaluating the effectiveness of advertising campaigns and improving related numerical models,

[0955] Automation equipment including

[0956] (Claim 2)

[0957] The automated apparatus according to claim 1, which predicts the epidemic using numerical prediction technology based on the analyzed information.

[0958] (Claim 3)

[0959] The automated apparatus according to claim 1, which analyzes the information obtained as a result of the aforementioned advertising placement and updates the numerical model to improve the accuracy of future predictions.

[0960] "Example 2 of combining an emotion engine"

[0961] (Claim 1)

[0962] A data collection means, comprising means for acquiring information from multiple information sources,

[0963] Means for preprocessing acquired information and removing duplicates and noise,

[0964] A means for recognizing and analyzing emotions using natural language processing techniques for preprocessed information,

[0965] A means of calculating the volume of topics and their rate of change using analyzed data, and predicting the likelihood and reliability of trends,

[0966] A means of determining the optimal timing and content of advertising based on predicted trends,

[0967] A means of notifying the user's device of the decided advertising strategy,

[0968] A means of collecting and analyzing advertising results data, improving predictive models, and optimizing advertising effectiveness through feedback,

[0969] A system that includes this.

[0970] (Claim 2)

[0971] The system according to claim 1, which uses a machine learning algorithm to predict trends based on the analyzed data and utilizes sentiment information in advertising strategies.

[0972] (Claim 3)

[0973] The system according to claim 1, which analyzes the data obtained as a result of the aforementioned advertising placement, updates the predictive model, and improves the accuracy and effectiveness of subsequent advertising placements.

[0974] "Application example 2 when combining with an emotional engine"

[0975] (Claim 1)

[0976] A data collection means, comprising means for acquiring information from multiple information sources,

[0977] Means for preprocessing acquired information and removing duplicates and noise,

[0978] A means for analyzing pre-processed information and calculating the topic volume and its rate of change,

[0979] A means of predicting the likelihood and reliability of an epidemic using analyzed data,

[0980] A means of dynamically adjusting the price of advertising space on relevant websites based on predicted trends,

[0981] A means of notifying users of advertising placement proposals on their devices,

[0982] A means of dynamically optimizing and personalizing advertising content based on sentiment data acquired from personal information terminals,

[0983] A means of collecting and analyzing advertising results data and providing feedback to improve predictive models,

[0984] A system that includes this.

[0985] (Claim 2)

[0986] The system according to claim 1, which performs trend prediction using a machine learning algorithm based on the analyzed data.

[0987] (Claim 3)

[0988] The system according to claim 1, which analyzes the data obtained as a result of the aforementioned advertising placement and updates the prediction model to improve the accuracy of predictions for subsequent times. [Explanation of symbols]

[0989] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection means, comprising means for acquiring information from multiple information sources, Means for preprocessing acquired information and removing duplicates and noise, A means for analyzing pre-processed information and calculating the topic volume and its rate of change, A means of predicting the likelihood and reliability of an epidemic using analyzed data, A means of dynamically adjusting the price of advertising space on relevant websites based on predicted trends, A means of notifying the user's terminal of advertising placement proposals, A means of collecting and analyzing advertising results data and providing feedback to improve predictive models, A system that includes this.

2. The system according to claim 1, which performs trend prediction using a machine learning algorithm based on the analyzed data.

3. The system according to claim 1, which analyzes the data obtained as a result of the aforementioned advertising placement and updates the prediction model to improve the accuracy of predictions for subsequent times.

Images