system

Abstract

We provide the system. [Solution] Means of collecting advertising-related information, Means for preprocessing the aforementioned advertising-related information, Means for constructing an effect prediction model based on the aforementioned preprocessed information, A means for generating an optimal media plan based on the aforementioned effect prediction model, Means to support creative production, A means for visualizing and displaying the results of the aforementioned effect prediction, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 conventional advertising campaigns, there has been a problem that the prediction of advertising effects is uncertain and optimal media planning and creative production cannot be efficiently carried out. As a result, advertising costs have not been effectively utilized, and often do not directly contribute to the improvement of a company's profits. There is a need to solve such problems.

Means for Solving the Problems

[0005] This invention provides a means for collecting advertising-related information and constructing an effectiveness prediction model based on the pre-processed information. It also includes a means for automatically generating an optimal media plan using this effectiveness prediction model. Furthermore, by utilizing AI technology to support creative production, the invention provides a system that streamlines all steps of an advertising campaign and visualizes and displays the results, enabling companies to effectively utilize advertising budgets and maximize revenue.

[0006] "Advertising-related information" refers to data necessary to predict the effectiveness of advertising and formulate the optimal plan, and includes past advertising performance data and target customer data.

[0007] "Preprocessing" refers to data processing such as imputing missing values, removing outliers, and normalizing, which is performed to prepare collected data for analysis.

[0008] A "performance prediction model" refers to a computational model built using machine learning algorithms to predict the performance of an advertisement.

[0009] A "media plan" refers to a plan that optimizes and determines the media outlets, timing, and target audience for advertising.

[0010] "Means of supporting creative production" refers to tools and functions that utilize AI technology to enable users to efficiently and effectively create and edit advertising materials.

[0011] "Means of visualization and display" refers to methods and tools for visually representing the results of advertising effectiveness predictions and providing the results in a format that is easy for users to understand. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled 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.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] To implement this invention, the first step is to collect advertising-related information. The server efficiently gathers past advertising performance and target customer attribute data from internal and external databases. This allows analysis to begin with all the necessary information available. Users can also provide the server with custom data based on specific requirements.

[0034] Next, the server preprocesses the collected data. This preprocessing converts the data into a format suitable for analysis and machine learning. Specifically, it fills in missing data, detects and removes outliers, and standardizes the data. This improves the quality of the data and increases the accuracy of predictive models.

[0035] Subsequently, the server uses the pre-processed data to build an effectiveness prediction model. By utilizing machine learning algorithms to create a model that accurately predicts the effectiveness of advertisements, it optimizes the company's advertising strategy. This model undergoes validation during the construction phase, and its accuracy is constantly monitored during use.

[0036] Furthermore, the server generates an optimal media plan based on an effectiveness prediction model. This plan includes selecting media outlets for advertising, timing of delivery, and setting target audiences. This maximizes the return on advertising spend.

[0037] At the same time, the device provides support tools to help users smoothly create creative advertising materials. Using AI technology, templates and auto-generate functions allow users to easily design effective advertisements.

[0038] Finally, the server visualizes the predicted advertising effectiveness and provides it to the user in a dashboard format. Users can use this information to improve their advertising strategy and make informed decisions.

[0039] As a concrete example, consider a company launching a campaign for a new product. The server integrates the company's past campaign data with data from the new target market to create a highly accurate effectiveness prediction model. The terminal presents user-optimized creative options and guides the user in creating the best advertisements based on the media plan. As a result, the company can achieve a higher ROI and see the campaign's performance in advance.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects advertising-related information from internal databases and partner platforms. This includes historical advertising performance, customer demographic data, and performance metrics such as click-through rates. Users can upload custom datasets to the server to add specific data for analysis.

[0043] Step 2:

[0044] The server preprocesses the collected data. Specifically, it appropriately imputes missing values ​​and removes outliers using statistical methods. Numerical data is also normalized, preparing it for analysis and machine learning.

[0045] Step 3:

[0046] The server uses pre-processed data to build an effectiveness prediction model. This involves running machine learning algorithms to predict performance based on specific advertising parameters. The algorithms are refined to improve the model's accuracy, and different methods are cross-validated.

[0047] Step 4:

[0048] The server uses an effectiveness prediction model to generate an optimal media plan. This includes optimizing the target audience, delivery schedule, and advertising platforms for the ads. The server then presents the user with a plan that includes budget allocation.

[0049] Step 5:

[0050] The device provides AI-assisted tools to help users effectively create advertising creatives. Users can efficiently design advertisements by utilizing templates and materials suggested by the AI.

[0051] Step 6:

[0052] The server visualizes and provides users with the advertising effectiveness predicted by the model. This includes displays in graph and dashboard formats. Users can adjust their advertising strategies and make decisions based on the prediction results.

[0053] (Example 1)

[0054] 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."

[0055] Traditional advertising strategies struggle to effectively utilize past performance data and target customer data, and the low accuracy of predictive models prevents optimization of return on advertising spend. Furthermore, a lack of efficient support in creating creative advertising materials hinders the rapid improvement of advertising strategies.

[0056] 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.

[0057] In this invention, the server includes means for acquiring advertising-related data, means for processing the advertising-related data, and means for constructing a predictive model based on the processed information. This enables highly accurate effect prediction and allows for the rapid formulation of an optimized advertising strategy.

[0058] "Advertising-related data" refers to information including past performance data and target customer data, which is fundamental data necessary for analyzing advertising effectiveness.

[0059] "Processing" refers to the process of converting acquired data into a format suitable for analysis, including data imputation and removal of outliers.

[0060] A "predictive model" is a metric that uses mathematical or statistical methods to predict the effectiveness of an advertisement based on processed data.

[0061] An "optimized plan" is a strategic proposal that includes selected media, delivery timing, and targeting to maximize advertising effectiveness.

[0062] "Creative production" refers to activities related to design and content creation for the effective production of advertising materials.

[0063] "Artificial intelligence technology" refers to systems that use computers to mimic human intellectual behavior and perform data analysis, decision-making, and problem-solving.

[0064] "Visualization" is a method of representing data in a visual form, such as graphs or charts, to make it easier to understand.

[0065] To implement this invention, the server plays a central role primarily in the collection, processing, and analysis of advertising-related data. The server first retrieves data from internal and external databases, collecting historical performance data and target customer data. This utilizes database access technologies and API interfaces.

[0066] Next, the server uses data analysis software to process the acquired data. It preprocesses the data using the Python library Pandas, performing missing value imputation and standardization. It also utilizes Z-score analysis to remove outliers.

[0067] Furthermore, the server uses machine learning libraries such as Scikit-learn to build predictive models from the preprocessed data. For example, it uses the Random Forest algorithm to predict the effectiveness of advertisements. Cross-validation testing is also performed to improve the accuracy of the models.

[0068] The device plays a crucial role in creating creative advertising materials. It assists users in easily creating advertising materials using Adobe XD and other common design tools. It also provides AI-powered template suggestions and automatic copy generation features to improve user production efficiency.

[0069] Finally, the server uses data visualization tools to visualize and present the results of the predictive model to the user. Specifically, it leverages tools such as Tableau and Power BI to display the information in a dashboard format. This makes it easier for users to intuitively understand the effectiveness of the advertising strategy.

[0070] For example, if a user is planning an advertising campaign for a new product, the server analyzes historical data and suggests the optimal advertising strategy for the target market. With assistance from the device, the user can create creative visual materials and see how the strategy is performing through visualized data.

[0071] An example of a prompt is: "Please propose the optimal advertising strategy for our new product's target audience. Based on past campaign data and target market data, we would like creative suggestions to maximize ROI." This prompt allows the user to obtain specific strategic proposals.

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

[0073] Step 1:

[0074] The server collects advertising-related data. It uses SQL queries and APIs from internal and external databases to gather historical advertising performance data and target customer data. It receives database access information and search criteria as input, and outputs a set of relevant data as a result. Specifically, the server opens a database connection, executes queries, and retrieves the necessary data.

[0075] Step 2:

[0076] The server preprocesses the collected data. The raw data obtained in step 1 is used as input. The Python Pandas library is used to impute missing values, remove outliers, and standardize the data. Missing values ​​are imputed with the mean, and outliers are filtered out, resulting in a clean dataset. Specifically, the server creates a dataframe and applies the processing to each column.

[0077] Step 3:

[0078] The server builds an effect prediction model based on preprocessed data. The clean dataset obtained in step 2 is used as input. The model is trained using random forest or linear regression algorithms with the Scikit-learn library. The model's accuracy is validated through cross-validation, and the trained prediction model object is output. Specifically, the server selects an algorithm, applies data to the model, and performs training and evaluation.

[0079] Step 4:

[0080] The server generates an optimal media plan using the built predictive model. Inputs include the predictive model obtained in step 3 and requirements regarding the advertising strategy. Based on the predictive model's results, it selects media outlets, sets delivery timings, and outputs an optimized media plan document. Specifically, the server analyzes the model's prediction results and creates a plan in report format.

[0081] Step 5:

[0082] The device assists users in creating creative advertising materials. Inputs include templates and design proposals, which are customized according to user selections. It provides intuitively editable templates via Adobe XD and other design software, and outputs the final advertising material. Specifically, the device displays a user interface and provides editing tools.

[0083] Step 6:

[0084] The server visualizes and provides users with predictions of advertising effectiveness. It uses the media plan and prediction model results generated in step 4 as input. It generates graphs and charts using Tableau and Power BI, outputting dashboards that users can review. Specifically, the server operates data visualization tools to present information visually.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] Traditional advertising campaign planning and implementation processes required significant time and resources, and it was difficult to track their effectiveness in real time. As a result, advertisers struggled to develop optimal strategies and maximize the return on investment of their advertising. In particular, there is a need for rapid and effective advertising management methods utilizing mobile devices.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for acquiring advertising-related information, means for processing the advertising-related information, and means for creating a predictive model based on the processed information. This makes it possible to execute advertising campaigns on mobile devices, grasp the effectiveness of the advertisements in real time, and immediately notify the user's device of the effectiveness.

[0090] "Advertising-related information" refers to information that includes past performance data related to the implementation of advertising and data on target customers.

[0091] "Data processing" is the process of converting collected information into a format suitable for analysis and machine learning, and of filling in missing data and removing outliers.

[0092] A "predictive model" is a computational model used to predict the effectiveness of advertising based on past data and to formulate the optimal advertising strategy.

[0093] An "information dissemination plan" is a strategic plan that includes media selection, distribution timing, and target setting for effectively delivering advertisements.

[0094] "Content creation" is the process of producing visual and text-based materials for advertising purposes.

[0095] "Visualization" refers to displaying the results of data analysis in a clear and easy-to-understand format, such as graphs and charts.

[0096] A "mobile device" refers to an information processing device that is portable and can be carried at all times, such as a smartphone or tablet.

[0097] "Information performance data" refers to data that records the results and outcomes of advertising activities conducted in the past.

[0098] "Target customer data" refers to data that includes attribute information and behavioral history of customers who are targeted by the advertisement.

[0099] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0100] To implement this invention, the server first collects advertising-related information. This information includes past advertising performance data and target customer data. The server retrieves this information and uses data processing software to perform tasks such as filling in missing data, removing outliers, and standardizing the data. Possible software to use includes Python and SQL.

[0101] Next, the server uses the processed information to build an effectiveness prediction model using machine learning platforms such as TENSORFLOW® and Scikit-learn. This model is used to accurately predict the effectiveness of advertisements and create an optimal media plan.

[0102] Users create ads on their mobile devices using templates based on media plans proposed by this predictive model. The ad editing interface utilizes HTML5, CSS, and JavaScript (registered trademark), and artificial intelligence technology enables the automatic generation of creative ad materials. This allows users to design ads without much effort.

[0103] Finally, once the ads are delivered, the server measures their effectiveness in real time and visualizes the results, providing them to the user as a dashboard. Visualization tools such as Tableau are used for this visualization. This allows users to understand the campaign's effectiveness in real time and incorporate it into their future strategies.

[0104] As a concrete example, consider an advertising campaign to announce a new product. Users easily create ad creatives on their smartphones based on the optimal media plan suggested by the server. During the campaign, the effectiveness of the ads is notified to the user's device in real time. An example of a prompt message would be, "Please suggest the optimal media plan to effectively run an advertising campaign for our new product."

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

[0106] Step 1:

[0107] The server collects advertising-related information from internal and external databases. This information includes historical advertising performance data and target customer data. The input is information from the databases, and the output is the collected raw data. The server performs queries to extract the necessary information.

[0108] Step 2:

[0109] The server preprocesses the collected advertising-related information. The input is the raw data obtained in step 1, and the output is data in an analyzable format. The server uses Python libraries to perform tasks such as filling in missing data, detecting and removing outliers, and standardizing the data. This results in high-quality data.

[0110] Step 3:

[0111] The server builds an effectiveness prediction model based on preprocessed data. The input is the result of step 2, and the output is the effectiveness prediction model. The server uses TensorFlow and Scikit-learn to apply machine learning algorithms to train the model and create a model for predicting advertising effectiveness.

[0112] Step 4:

[0113] The user designs the optimal advertising campaign based on a predictive model using their device. The input is the predictive model generated from step 3, and the output is the campaign's media plan based on the user's selections. The user reviews the prediction results on their device and selects and edits ad creatives using AI-generated templates.

[0114] Step 5:

[0115] The device delivers user-designed advertisements. The input is the ad creative created in step 4, and the output is the delivery of the ad to the target audience. The device displays the ad on the specified media and at the specified time, according to the media plan.

[0116] Step 6:

[0117] The server measures the effectiveness of delivered advertisements in real time and notifies the user of the results. The input is aggregated data after ad delivery, and the output is visualized effectiveness analysis results. The server uses data visualization tools to create and present graphs and dashboards to the user.

[0118] 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.

[0119] To implement this invention, the first step is to collect and preprocess advertising-related information. The server collects past advertising performance data and target customer data, and builds an effectiveness prediction model based on this data. This prediction model makes it possible to evaluate the performance of advertising campaigns in advance.

[0120] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time. This emotion engine analyzes the user's emotional state from their facial expressions and tone of voice, quantifies it, and sends it back to the server as a report. This information is directly used to personalize advertising creatives.

[0121] The device uses AI-assisted tools to create advertising creatives. It provides a function to generate advertising materials optimized for the user's interests and preferences based on emotional information obtained from an emotion engine. This allows users to create more effective and sophisticated creatives.

[0122] Furthermore, the server adjusts the optimal media plan based on user sentiment information. This involves incorporating sentiment data into ad delivery timing and target audience segmentation to create a more engaging plan. It also utilizes a sentiment engine to generate feedback based on user emotions, which helps improve ad effectiveness.

[0123] As a concrete example, consider a company running an online campaign. When a user views an ad, the emotion engine analyzes their reaction, and if the user shows a positive reaction, the server presents an ad creative that leverages that emotion. The device then adjusts the elements of the creative based on that feedback, delivering a more effective ad. This improves ad performance and enhances the quality of the approach to the target audience.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The server efficiently collects historical advertising performance data and target customer data from internal and external databases. This provides the foundational data needed for the next steps.

[0127] Step 2:

[0128] The server preprocesses the collected data. It imputes missing data, removes outliers, normalizes the data, and converts it into a format suitable for machine learning models.

[0129] Step 3:

[0130] The server builds an effectiveness prediction model based on pre-processed data. It runs machine learning algorithms to generate a model for accurately predicting ad performance.

[0131] Step 4:

[0132] The server uses an emotion engine to recognize the user's emotions in real time. While the user is viewing an advertisement, it analyzes their facial expressions and voice using a camera and microphone to acquire emotion data.

[0133] Step 5:

[0134] The server uses emotional information obtained from the emotion engine to adjust the optimal media plan. Based on emotional data, it optimizes ad targeting and delivery timing.

[0135] Step 6:

[0136] The device uses AI-assisted tools to create advertising creatives that respond to the user's emotions. Based on positive responses obtained by the emotion engine, the design and message are personalized and adjusted.

[0137] Step 7:

[0138] The server visualizes the results of advertising campaigns and provides them to users in a dashboard format. This allows users to check the effectiveness of their ads and use that information to inform their next strategies.

[0139] (Example 2)

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

[0141] Traditional advertising systems fail to maximize advertising effectiveness because they deliver ads without considering user emotions. Furthermore, ad production and media planning are often insufficiently optimized, highlighting the need for improved quality in targeting audiences.

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

[0143] In this invention, the server includes means for collecting information, means for preprocessing the information, means for building a predictive model, means for recognizing and analyzing user emotions, means for aggregating the analyzed emotional information as a report, and means for optimizing advertising materials based on the emotional information. This makes it possible to maximize the effectiveness of advertising and improve the quality of the approach to the target audience.

[0144] "Means of collecting information" refers to methods and devices for collecting various types of data, including past performance data and target customer data.

[0145] "Preprocessing means" refers to methods or devices for organizing and converting collected data into a format suitable for analysis and model building.

[0146] "Means for constructing a predictive model" refers to methods or devices for generating a model to evaluate the effectiveness of advertising using pre-processed data.

[0147] "Means for generating the optimal plan" refers to methods or devices that formulate advertising delivery plans based on predictive models and enable their effective implementation.

[0148] "Means of supporting production" refers to methods and devices that utilize artificial intelligence technology to assist in the process of editing and generating advertising materials.

[0149] "Means of visualization and display" refer to interfaces and devices for visually displaying predictive models and analysis results.

[0150] "Means for recognizing and analyzing user emotions" refers to methods or devices that identify and quantify emotional states using a person's facial expressions and tone of voice.

[0151] "Means for aggregating emotional information as a report" refers to methods or devices for integrating recognized emotional data and saving it in a report format that allows for analysis.

[0152] "Methods for optimizing advertising materials" refer to methods or devices that use aggregated emotional information to adjust advertising content to suit the user and maximize its effectiveness.

[0153] This invention is a system that maximizes the effectiveness of advertising by collecting various data, building predictive models, and optimizing advertising materials based on user emotions.

[0154] The server collects information and integrates historical advertising performance data and target customer data through database software (e.g., a database management system). The collected data is preprocessed using data analysis software, and the effectiveness prediction model is built using machine learning libraries (e.g., TensorFlow or scikit-learn).

[0155] Next, the server connects to an emotion recognition engine to recognize the user's emotions. It analyzes data collected through the user's device, such as a webcam or microphone, and quantifies emotions based on the user's facial expressions and tone of voice. The analyzed emotion information is then compiled on the server as a data report.

[0156] Furthermore, the device uses AI-assisted tools to create advertising creatives based on aggregated emotional information. For example, an AI tool integrated with Adobe Creative Cloud automatically generates advertising materials optimized for the user's interests and preferences. By utilizing emotional information in this process, more personalized content is provided.

[0157] As a concrete example, when a company conducts an online campaign, the emotion engine analyzes user reactions when viewing ads, and automatically generates and presents ads tailored to users who show positive emotions. The device adjusts the creative based on the feedback, improving ad performance. This system enables an effective approach to the target audience.

[0158] An example of a prompt message that can be input to the generating AI model is, "I want to personalize ad creatives based on user sentiment data," which allows for efficient ad customization.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The server collects information. Specifically, it uses a database management system to obtain historical advertising performance data and target customer data. This data is collected in its raw form and serves as foundational data for predicting advertising effectiveness. The input is raw advertising performance data, and the output is an organized dataset.

[0162] Step 2:

[0163] The server preprocesses the collected data. Data analysis software is used to perform noise reduction, missing value imputation, and data standardization. This prepares the data for model building. The input is the organized dataset, and the output is the preprocessed data.

[0164] Step 3:

[0165] The server builds an effect prediction model using preprocessed data. It uses a machine learning library (e.g., TensorFlow) to split the data into training and test sets. Then, it applies an algorithm to generate a model and evaluates its accuracy. The input is the preprocessed data, and the output is the trained prediction model.

[0166] Step 4:

[0167] The server recognizes the user's emotions in real time. The emotion engine analyzes facial expressions and voice tone acquired from the user's device and quantifies the emotional state. The emotional information is stored in a database as a report. The input is the user's facial expression and voice data, and the output is quantified emotional data.

[0168] Step 5:

[0169] The device uses AI-assisted tools to create advertising creatives. Here, the advertising materials are optimized based on aggregated emotional information. Using tools integrated with Adobe Creative Cloud, content is automatically generated. The input consists of quantified emotional data and predictive model results, while the output is optimized advertising material.

[0170] Step 6:

[0171] The server generates an optimal media plan based on analyzed sentiment information and predictive models. It adjusts ad delivery timing and target audience segmentation to maximize effectiveness. The input is ad material and the results of the predictive model, and the output is the adjusted media plan.

[0172] Step 7:

[0173] Users receive generated ads and react to them. The server collects emotional feedback based on these reactions and uses it to improve the effectiveness of the ads. The inputs are ad delivery and user reactions, and the output is improvement feedback.

[0174] (Application Example 2)

[0175] 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".

[0176] Current advertising systems have a problem in that ads are delivered uniformly, making it difficult to reflect individual user emotions and reactions in real time, thus failing to maximize the effectiveness of advertising. In particular, the lack of personalization based on user interests and preferences is a challenge in optimizing the effectiveness of advertising.

[0177] 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.

[0178] In this invention, the server includes means for collecting advertising-related information, means for pre-processing the information, means for constructing an effectiveness prediction model, means for generating an optimal media plan, means for supporting creative production, means for visualizing and displaying the results of the effectiveness prediction, and means for recognizing user emotions and optimizing advertising content in real time. This makes it possible to improve advertising performance and enhance the quality of advertising deployment to users.

[0179] "Advertising-related information" refers to all data related to the implementation of advertising, including past advertising performance data and target customer data.

[0180] "Preprocessing" refers to the process of organizing collected data according to its purpose and preparing it in a format that can be analyzed.

[0181] An "effectiveness prediction model" is a mathematical or statistical model built to predict the results of an advertising campaign in advance.

[0182] A "media plan" is a strategic plan that determines when and through which media advertisements will be delivered.

[0183] "Means of supporting creative production" refers to tools and systems that use AI technology to edit and generate advertising materials.

[0184] "Methods for recognizing user emotions and optimizing ad content in real time" refers to technologies and systems that analyze user emotions from facial expressions, voices, etc., and adjust ads on the spot.

[0185] To implement this invention, it is crucial to construct a system for collecting and preprocessing advertising-related information. The server collects advertising-related information from various data sources and preprocesses the information, including past advertising performance data and target customer data. This prepares the system for building an effectiveness prediction model.

[0186] The server generates an effectiveness prediction model based on pre-processed data. This model is developed using machine learning frameworks such as TensorFlow, allowing for the pre-evaluation of the probability of success of an advertising campaign. Based on this evaluation, an optimal media plan is formed to maximize the effectiveness of ad delivery.

[0187] The device utilizes AI-assisted tools to create creative content. The generative AI model used here leverages predefined prompts to generate advertising materials optimized for the user's interests and preferences. An emotion engine analyzes the user's facial expressions and tone of voice, and the collected emotion data is reflected in the advertising content in real time.

[0188] As a concrete example, when a user is watching a movie trailer, the device detects the user's smile and determines that they are expressing a positive emotion. This emotion data is sent to the server, and the system is optimized to prioritize displaying ad creatives for comedy movies.

[0189] Examples of prompt messages are as follows:

[0190] "Enter the current user's emotional data and compare it with past data to suggest the most suitable ad creative. Emotional data: High frequency of smiling, bright voice tone. Goal: Emphasize comedy movie advertisements."

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

[0192] Step 1:

[0193] The server collects advertising-related information from various data sources, including historical advertising performance data and target customer data. It takes historical advertising campaign data as input and generates a dataset integrating this data as output.

[0194] Step 2:

[0195] The server preprocesses the collected advertising-related information. The input data is checked for inconsistencies and missing data, and then cleaned. The cleaned data is used as output to build an effectiveness prediction model.

[0196] Step 3:

[0197] The server builds an effectiveness prediction model based on preprocessed data. This model is trained using machine learning tools such as TensorFlow. Using cleansed advertising data as input, it outputs a model that predicts the future performance of advertising campaigns.

[0198] Step 4:

[0199] The server utilizes the built-in effectiveness prediction model to create an optimal media plan. The results of the prediction model are used as input, and the output plan identifies the timing and media to which advertisements should be delivered.

[0200] Step 5:

[0201] The device utilizes AI-assisted tools to generate prompt messages based on the user's emotional data. It receives emotional data such as the user's smile and tone of voice as input and generates personalized prompt messages as output.

[0202] Step 6:

[0203] The device automatically generates ad creatives using an AI model based on the prompt text. It uses the input prompts to output ad materials tailored to the user's interests and preferences.

[0204] Step 7:

[0205] The server optimizes ad content in real time based on sentiment data received from the user's device. The input includes sentiment information from the device, and the server outputs optimized ad creatives, which are then delivered to the device.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] To implement this invention, the first step is to collect advertising-related information. The server efficiently gathers past advertising performance and target customer attribute data from internal and external databases. This allows analysis to begin with all the necessary information available. Users can also provide the server with custom data based on specific requirements.

[0223] Next, the server preprocesses the collected data. This preprocessing converts the data into a format suitable for analysis and machine learning. Specifically, it fills in missing data, detects and removes outliers, and standardizes the data. This improves the quality of the data and increases the accuracy of predictive models.

[0224] Subsequently, the server uses the pre-processed data to build an effectiveness prediction model. By utilizing machine learning algorithms to create a model that accurately predicts the effectiveness of advertisements, it optimizes the company's advertising strategy. This model undergoes validation during the construction phase, and its accuracy is constantly monitored during use.

[0225] Furthermore, the server generates an optimal media plan based on an effectiveness prediction model. This plan includes selecting media outlets for advertising, timing of delivery, and setting target audiences. This maximizes the return on advertising spend.

[0226] At the same time, the device provides support tools to help users smoothly create creative advertising materials. Using AI technology, templates and auto-generate functions allow users to easily design effective advertisements.

[0227] Finally, the server visualizes the predicted advertising effectiveness and provides it to the user in a dashboard format. Users can use this information to improve their advertising strategy and make informed decisions.

[0228] As a concrete example, consider a company launching a campaign for a new product. The server integrates the company's past campaign data with data from the new target market to create a highly accurate effectiveness prediction model. The terminal presents user-optimized creative options and guides the user in creating the best advertisements based on the media plan. As a result, the company can achieve a higher ROI and see the campaign's performance in advance.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The server collects advertising-related information from internal databases and partner platforms. This includes historical advertising performance, customer demographic data, and performance metrics such as click-through rates. Users can upload custom datasets to the server to add specific data for analysis.

[0232] Step 2:

[0233] The server preprocesses the collected data. Specifically, it appropriately imputes missing values ​​and removes outliers using statistical methods. Numerical data is also normalized, preparing it for analysis and machine learning.

[0234] Step 3:

[0235] The server uses pre-processed data to build an effectiveness prediction model. This involves running machine learning algorithms to predict performance based on specific advertising parameters. The algorithms are refined to improve the model's accuracy, and different methods are cross-validated.

[0236] Step 4:

[0237] The server uses an effectiveness prediction model to generate an optimal media plan. This includes optimizing the target audience, delivery schedule, and advertising platforms for the ads. The server then presents the user with a plan that includes budget allocation.

[0238] Step 5:

[0239] The device provides AI-assisted tools to help users effectively create advertising creatives. Users can efficiently design advertisements by utilizing templates and materials suggested by the AI.

[0240] Step 6:

[0241] The server visualizes and provides users with the advertising effectiveness predicted by the model. This includes displays in graph and dashboard formats. Users can adjust their advertising strategies and make decisions based on the prediction results.

[0242] (Example 1)

[0243] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0244] Traditional advertising strategies struggle to effectively utilize past performance data and target customer data, and the low accuracy of predictive models prevents optimization of return on advertising spend. Furthermore, a lack of efficient support in creating creative advertising materials hinders the rapid improvement of advertising strategies.

[0245] 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.

[0246] In this invention, the server includes means for acquiring advertising-related data, means for processing the advertising-related data, and means for constructing a predictive model based on the processed information. This enables highly accurate effect prediction and allows for the rapid formulation of an optimized advertising strategy.

[0247] "Advertising-related data" refers to information including past performance data and target customer data, which is fundamental data necessary for analyzing advertising effectiveness.

[0248] "Processing" refers to the process of converting acquired data into a format suitable for analysis, including data imputation and removal of outliers.

[0249] A "predictive model" is a metric that uses mathematical or statistical methods to predict the effectiveness of an advertisement based on processed data.

[0250] An "optimized plan" is a strategic proposal that includes selected media, delivery timing, and targeting to maximize advertising effectiveness.

[0251] "Creative production" refers to activities related to design and content creation for the effective production of advertising materials.

[0252] "Artificial intelligence technology" refers to systems that use computers to mimic human intellectual behavior and perform data analysis, decision-making, and problem-solving.

[0253] "Visualization" is a method of representing data in a visual form, such as graphs or charts, to make it easier to understand.

[0254] To implement this invention, the server plays a central role primarily in the collection, processing, and analysis of advertising-related data. The server first retrieves data from internal and external databases, collecting historical performance data and target customer data. This utilizes database access technologies and API interfaces.

[0255] Next, the server uses data analysis software to process the acquired data. It preprocesses the data using the Python library Pandas, performing missing value imputation and standardization. It also utilizes Z-score analysis to remove outliers.

[0256] Furthermore, the server uses machine learning libraries such as Scikit-learn to build predictive models from the preprocessed data. For example, it uses the Random Forest algorithm to predict the effectiveness of advertisements. Cross-validation testing is also performed to improve the accuracy of the models.

[0257] The device plays a crucial role in creating creative advertising materials. It assists users in easily creating advertising materials using Adobe XD and other common design tools. It also provides AI-powered template suggestions and automatic copy generation features to improve user production efficiency.

[0258] Finally, the server uses data visualization tools to visualize and present the results of the predictive model to the user. Specifically, it leverages tools such as Tableau and Power BI to display the information in a dashboard format. This makes it easier for users to intuitively understand the effectiveness of the advertising strategy.

[0259] For example, if a user is planning an advertising campaign for a new product, the server analyzes historical data and suggests the optimal advertising strategy for the target market. With assistance from the device, the user can create creative visual materials and see how the strategy is performing through visualized data.

[0260] An example of a prompt is: "Please propose the optimal advertising strategy for our new product's target audience. Based on past campaign data and target market data, we would like creative suggestions to maximize ROI." This prompt allows the user to obtain specific strategic proposals.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The server collects advertising-related data. It uses SQL queries and APIs from internal and external databases to gather historical advertising performance data and target customer data. It receives database access information and search criteria as input, and outputs a set of relevant data as a result. Specifically, the server opens a database connection, executes queries, and retrieves the necessary data.

[0264] Step 2:

[0265] The server preprocesses the collected data. The raw data obtained in step 1 is used as input. The Python Pandas library is used to impute missing values, remove outliers, and standardize the data. Missing values ​​are imputed with the mean, and outliers are filtered out, resulting in a clean dataset. Specifically, the server creates a dataframe and applies the processing to each column.

[0266] Step 3:

[0267] The server builds an effect prediction model based on preprocessed data. The clean dataset obtained in step 2 is used as input. The model is trained using random forest or linear regression algorithms with the Scikit-learn library. The model's accuracy is validated through cross-validation, and the trained prediction model object is output. Specifically, the server selects an algorithm, applies data to the model, and performs training and evaluation.

[0268] Step 4:

[0269] The server generates an optimal media plan using the built predictive model. Inputs include the predictive model obtained in step 3 and requirements regarding the advertising strategy. Based on the predictive model's results, it selects media outlets, sets delivery timings, and outputs an optimized media plan document. Specifically, the server analyzes the model's prediction results and creates a plan in report format.

[0270] Step 5:

[0271] The device assists users in creating creative advertising materials. Inputs include templates and design proposals, which are customized according to user selections. It provides intuitively editable templates via Adobe XD and other design software, and outputs the final advertising material. Specifically, the device displays a user interface and provides editing tools.

[0272] Step 6:

[0273] The server visualizes and provides users with predictions of advertising effectiveness. It uses the media plan and prediction model results generated in step 4 as input. It generates graphs and charts using Tableau and Power BI, outputting dashboards that users can review. Specifically, the server operates data visualization tools to present information visually.

[0274] (Application Example 1)

[0275] 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."

[0276] Traditional advertising campaign planning and implementation processes required significant time and resources, and it was difficult to track their effectiveness in real time. As a result, advertisers struggled to develop optimal strategies and maximize the return on investment of their advertising. In particular, there is a need for rapid and effective advertising management methods utilizing mobile devices.

[0277] 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.

[0278] In this invention, the server includes means for acquiring advertisement-related information, means for processing the advertisement-related information, and means for creating a prediction model based on the processed information. As a result, it becomes possible to execute an advertising campaign on a mobile terminal, grasp the effect of the advertisement in real time, and immediately notify the user terminal of the effect.

[0279] "Advertisement-related information" refers to information including past performance data related to the implementation of advertisements and data related to target customers.

[0280] "Data processing" is a process of converting the collected information into a form suitable for analysis and machine learning, and filling in missing data and removing outliers.

[0281] "Prediction model" is a calculation model for predicting the effect of an advertisement based on past data and formulating an optimal advertising strategy.

[0282] "Information distribution plan" is a strategic plan including media selection, distribution timing, target setting, etc. for effectively distributing advertisements.

[0283] "Content production" is a process of creating visual and text-based materials for the purpose of advertisements.

[0284] "Visualization" refers to displaying the analysis results of data as graphs or charts in an easy-to-see and easy-to-understand form.

[0285] "Mobile terminal" refers to an information processing device such as a smartphone or tablet that can be carried and always carried around.

[0286] "Information performance data" is data that records the results and outcomes of past advertising activities.

[0287] "Target customer data" is data including the attribute information and behavior history of customers targeted by advertisements.

[0288] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0289] To implement this invention, the server first collects advertising-related information. This information includes past advertising performance data and target customer data. The server retrieves this information and uses data processing software to perform tasks such as filling in missing data, removing outliers, and standardizing the data. Possible software to use includes Python and SQL.

[0290] Next, the server uses the processed information to build an effectiveness prediction model using machine learning platforms such as TensorFlow and Scikit-learn. This model is used to accurately predict the effectiveness of advertisements and create an optimal media plan.

[0291] Users create ads on their mobile devices using templates based on media plans proposed by this predictive model. The ad editing interface utilizes HTML5, CSS, and JavaScript, and artificial intelligence technology enables the automatic generation of creative ad materials. This allows users to design ads with minimal effort.

[0292] Finally, once the ads are delivered, the server measures their effectiveness in real time and visualizes the results, providing them to the user as a dashboard. Visualization tools such as Tableau are used for this visualization. This allows users to understand the campaign's effectiveness in real time and incorporate it into their future strategies.

[0293] As a concrete example, consider an advertising campaign to announce a new product. Users easily create ad creatives on their smartphones based on the optimal media plan suggested by the server. During the campaign, the effectiveness of the ads is notified to the user's device in real time. An example of a prompt message would be, "Please suggest the optimal media plan to effectively run an advertising campaign for our new product."

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The server collects advertising-related information from internal and external databases. This information includes historical advertising performance data and target customer data. The input is information from the databases, and the output is the collected raw data. The server performs queries to extract the necessary information.

[0297] Step 2:

[0298] The server preprocesses the collected advertising-related information. The input is the raw data obtained in step 1, and the output is data in an analyzable format. The server uses Python libraries to perform tasks such as filling in missing data, detecting and removing outliers, and standardizing the data. This results in high-quality data.

[0299] Step 3:

[0300] The server builds an effectiveness prediction model based on preprocessed data. The input is the result of step 2, and the output is the effectiveness prediction model. The server uses TensorFlow and Scikit-learn to apply machine learning algorithms to train the model and create a model for predicting advertising effectiveness.

[0301] Step 4:

[0302] The user designs an optimal advertising campaign based on a prediction model using a terminal. The input is the prediction model generated from Step 3, and the output is the media plan for the campaign based on the user's selection. The user checks the prediction results on the terminal and selects and edits the ad creatives using the templates generated by the AI.

[0303] Step 5:

[0304] The terminal distributes the ads designed by the user. The input is the ad creative created in Step 4, and the output is the ad distribution to the target audience. The terminal displays the ads on the specified media and at the specified time according to the media plan.

[0305] Step 6:

[0306] The server measures the effect of the distributed ads in real time and notifies the user of the results. The input is the aggregated data after ad distribution, and the output is the visualized effect analysis results. The server uses a data visualization tool to create graphs and dashboards and presents them to the user.

[0307] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0308] To implement this invention, first, the collection and preprocessing of advertising-related information are performed. The server collects past advertising performance data and target customer data and constructs an effect prediction model based on them. This prediction model enables the performance of an advertising campaign to be evaluated in advance.

[0309] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time. This emotion engine analyzes the user's emotional state from their facial expressions and tone of voice, quantifies it, and sends it back to the server as a report. This information is directly used to personalize advertising creatives.

[0310] The device uses AI-assisted tools to create advertising creatives. It provides a function to generate advertising materials optimized for the user's interests and preferences based on emotional information obtained from an emotion engine. This allows users to create more effective and sophisticated creatives.

[0311] Furthermore, the server adjusts the optimal media plan based on user sentiment information. This involves incorporating sentiment data into ad delivery timing and target audience segmentation to create a more engaging plan. It also utilizes a sentiment engine to generate feedback based on user emotions, which helps improve ad effectiveness.

[0312] As a concrete example, consider a company running an online campaign. When a user views an ad, the emotion engine analyzes their reaction, and if the user shows a positive reaction, the server presents an ad creative that leverages that emotion. The device then adjusts the elements of the creative based on that feedback, delivering a more effective ad. This improves ad performance and enhances the quality of the approach to the target audience.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The server efficiently collects historical advertising performance data and target customer data from internal and external databases. This provides the foundational data needed for the next steps.

[0316] Step 2:

[0317] The server preprocesses the collected data. It imputes missing data, removes outliers, normalizes the data, and converts it into a format suitable for machine learning models.

[0318] Step 3:

[0319] The server builds an effectiveness prediction model based on pre-processed data. It runs machine learning algorithms to generate a model for accurately predicting ad performance.

[0320] Step 4:

[0321] The server uses an emotion engine to recognize the user's emotions in real time. While the user is viewing an advertisement, it analyzes their facial expressions and voice using a camera and microphone to acquire emotion data.

[0322] Step 5:

[0323] The server uses emotional information obtained from the emotion engine to adjust the optimal media plan. Based on emotional data, it optimizes ad targeting and delivery timing.

[0324] Step 6:

[0325] The device uses AI-assisted tools to create advertising creatives that respond to the user's emotions. Based on positive responses obtained by the emotion engine, the design and message are personalized and adjusted.

[0326] Step 7:

[0327] The server visualizes the results of advertising campaigns and provides them to users in a dashboard format. This allows users to check the effectiveness of their ads and use that information to inform their next strategies.

[0328] (Example 2)

[0329] 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".

[0330] Traditional advertising systems fail to maximize advertising effectiveness because they deliver ads without considering user emotions. Furthermore, ad production and media planning are often insufficiently optimized, highlighting the need for improved quality in targeting audiences.

[0331] 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.

[0332] In this invention, the server includes means for collecting information, means for preprocessing the information, means for building a predictive model, means for recognizing and analyzing user emotions, means for aggregating the analyzed emotional information as a report, and means for optimizing advertising materials based on the emotional information. This makes it possible to maximize the effectiveness of advertising and improve the quality of the approach to the target audience.

[0333] "Means of collecting information" refers to methods and devices for collecting various types of data, including past performance data and target customer data.

[0334] "Preprocessing means" refers to methods or devices for organizing and converting collected data into a format suitable for analysis and model building.

[0335] "Means for constructing a predictive model" refers to methods or devices for generating a model to evaluate the effectiveness of advertising using pre-processed data.

[0336] "Means for generating the optimal plan" refers to methods or devices that formulate advertising delivery plans based on predictive models and enable their effective implementation.

[0337] "Means of supporting production" refers to methods and devices that utilize artificial intelligence technology to assist in the process of editing and generating advertising materials.

[0338] "Means of visualization and display" refer to interfaces and devices for visually displaying predictive models and analysis results.

[0339] "Means for recognizing and analyzing user emotions" refers to methods or devices that identify and quantify emotional states using a person's facial expressions and tone of voice.

[0340] "Means for aggregating emotional information as a report" refers to methods or devices for integrating recognized emotional data and saving it in a report format that allows for analysis.

[0341] "Methods for optimizing advertising materials" refer to methods or devices that use aggregated emotional information to adjust advertising content to suit the user and maximize its effectiveness.

[0342] This invention is a system that maximizes the effectiveness of advertising by collecting various data, building predictive models, and optimizing advertising materials based on user emotions.

[0343] The server collects information and integrates historical advertising performance data and target customer data through database software (e.g., a database management system). The collected data is preprocessed using data analysis software, and the effectiveness prediction model is built using machine learning libraries (e.g., TensorFlow or scikit-learn).

[0344] Next, the server connects to an emotion recognition engine to recognize the user's emotions. It analyzes data collected through the user's device, such as a webcam or microphone, and quantifies emotions based on the user's facial expressions and tone of voice. The analyzed emotion information is then compiled on the server as a data report.

[0345] Furthermore, the device uses AI-assisted tools to create advertising creatives based on aggregated emotional information. For example, an AI tool integrated with Adobe Creative Cloud automatically generates advertising materials optimized for the user's interests and preferences. By utilizing emotional information in this process, more personalized content is provided.

[0346] As a concrete example, when a company conducts an online campaign, the emotion engine analyzes user reactions when viewing ads, and automatically generates and presents ads tailored to users who show positive emotions. The device adjusts the creative based on the feedback, improving ad performance. This system enables an effective approach to the target audience.

[0347] An example of a prompt message that can be input to the generating AI model is, "I want to personalize ad creatives based on user sentiment data," which allows for efficient ad customization.

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] The server collects information. Specifically, it uses a database management system to obtain historical advertising performance data and target customer data. This data is collected in its raw form and serves as foundational data for predicting advertising effectiveness. The input is raw advertising performance data, and the output is an organized dataset.

[0351] Step 2:

[0352] The server preprocesses the collected data. Data analysis software is used to perform noise reduction, missing value imputation, and data standardization. This prepares the data for model building. The input is the organized dataset, and the output is the preprocessed data.

[0353] Step 3:

[0354] The server builds an effect prediction model using preprocessed data. It uses a machine learning library (e.g., TensorFlow) to split the data into training and test sets. Then, it applies an algorithm to generate a model and evaluates its accuracy. The input is the preprocessed data, and the output is the trained prediction model.

[0355] Step 4:

[0356] The server recognizes the user's emotions in real time. The emotion engine analyzes facial expressions and voice tone acquired from the user's device and quantifies the emotional state. The emotional information is stored in a database as a report. The input is the user's facial expression and voice data, and the output is quantified emotional data.

[0357] Step 5:

[0358] The device uses AI-assisted tools to create advertising creatives. Here, the advertising materials are optimized based on aggregated emotional information. Using tools integrated with Adobe Creative Cloud, content is automatically generated. The input consists of quantified emotional data and predictive model results, while the output is optimized advertising material.

[0359] Step 6:

[0360] The server generates an optimal media plan based on analyzed sentiment information and predictive models. It adjusts ad delivery timing and target audience segmentation to maximize effectiveness. The input is ad material and the results of the predictive model, and the output is the adjusted media plan.

[0361] Step 7:

[0362] Users receive generated ads and react to them. The server collects emotional feedback based on these reactions and uses it to improve the effectiveness of the ads. The inputs are ad delivery and user reactions, and the output is improvement feedback.

[0363] (Application Example 2)

[0364] 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."

[0365] Current advertising systems have a problem in that ads are delivered uniformly, making it difficult to reflect individual user emotions and reactions in real time, thus failing to maximize the effectiveness of advertising. In particular, the lack of personalization based on user interests and preferences is a challenge in optimizing the effectiveness of advertising.

[0366] 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.

[0367] In this invention, the server includes means for collecting advertising-related information, means for pre-processing the information, means for constructing an effectiveness prediction model, means for generating an optimal media plan, means for supporting creative production, means for visualizing and displaying the results of the effectiveness prediction, and means for recognizing user emotions and optimizing advertising content in real time. This makes it possible to improve advertising performance and enhance the quality of advertising deployment to users.

[0368] "Advertising-related information" refers to all data related to the implementation of advertising, including past advertising performance data and target customer data.

[0369] "Preprocessing" refers to the process of organizing collected data according to its purpose and preparing it in a format that can be analyzed.

[0370] An "effectiveness prediction model" is a mathematical or statistical model built to predict the results of an advertising campaign in advance.

[0371] A "media plan" is a strategic plan that determines when and through which media advertisements will be delivered.

[0372] "Means of supporting creative production" refers to tools and systems that use AI technology to edit and generate advertising materials.

[0373] "Methods for recognizing user emotions and optimizing ad content in real time" refers to technologies and systems that analyze user emotions from facial expressions, voices, etc., and adjust ads on the spot.

[0374] To implement this invention, it is crucial to construct a system for collecting and preprocessing advertising-related information. The server collects advertising-related information from various data sources and preprocesses the information, including past advertising performance data and target customer data. This prepares the system for building an effectiveness prediction model.

[0375] The server generates an effectiveness prediction model based on pre-processed data. This model is developed using machine learning frameworks such as TensorFlow, allowing for the pre-evaluation of the probability of success of an advertising campaign. Based on this evaluation, an optimal media plan is formed to maximize the effectiveness of ad delivery.

[0376] The device utilizes AI-assisted tools to create creative content. The generative AI model used here leverages predefined prompts to generate advertising materials optimized for the user's interests and preferences. An emotion engine analyzes the user's facial expressions and tone of voice, and the collected emotion data is reflected in the advertising content in real time.

[0377] As a concrete example, when a user is watching a movie trailer, the device detects the user's smile and determines that they are expressing a positive emotion. This emotion data is sent to the server, and the system is optimized to prioritize displaying ad creatives for comedy movies.

[0378] Examples of prompt messages are as follows:

[0379] "Enter the current user's emotional data and compare it with past data to suggest the most suitable ad creative. Emotional data: High frequency of smiling, bright voice tone. Goal: Emphasize comedy movie advertisements."

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The server collects advertising-related information from various data sources, including historical advertising performance data and target customer data. It takes historical advertising campaign data as input and generates a dataset integrating this data as output.

[0383] Step 2:

[0384] The server preprocesses the collected advertising-related information. The input data is checked for inconsistencies and missing data, and then cleaned. The cleaned data is used as output to build an effectiveness prediction model.

[0385] Step 3:

[0386] The server builds an effectiveness prediction model based on preprocessed data. This model is trained using machine learning tools such as TensorFlow. Using cleansed advertising data as input, it outputs a model that predicts the future performance of advertising campaigns.

[0387] Step 4:

[0388] The server utilizes the built-in effectiveness prediction model to create an optimal media plan. The results of the prediction model are used as input, and the output plan identifies the timing and media to which advertisements should be delivered.

[0389] Step 5:

[0390] The device utilizes AI-assisted tools to generate prompt messages based on the user's emotional data. It receives emotional data such as the user's smile and tone of voice as input and generates personalized prompt messages as output.

[0391] Step 6:

[0392] The device automatically generates ad creatives using an AI model based on the prompt text. It uses the input prompts to output ad materials tailored to the user's interests and preferences.

[0393] Step 7:

[0394] The server optimizes ad content in real time based on sentiment data received from the user's device. The input includes sentiment information from the device, and the server outputs optimized ad creatives, which are then delivered to the device.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] [Third Embodiment]

[0399] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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".

[0411] To implement this invention, the first step is to collect advertising-related information. The server efficiently gathers past advertising performance and target customer attribute data from internal and external databases. This allows analysis to begin with all the necessary information available. Users can also provide the server with custom data based on specific requirements.

[0412] Next, the server preprocesses the collected data. This preprocessing converts the data into a format suitable for analysis and machine learning. Specifically, it fills in missing data, detects and removes outliers, and standardizes the data. This improves the quality of the data and increases the accuracy of predictive models.

[0413] Subsequently, the server uses the pre-processed data to build an effectiveness prediction model. By utilizing machine learning algorithms to create a model that accurately predicts the effectiveness of advertisements, it optimizes the company's advertising strategy. This model undergoes validation during the construction phase, and its accuracy is constantly monitored during use.

[0414] Furthermore, the server generates an optimal media plan based on an effectiveness prediction model. This plan includes selecting media outlets for advertising, timing of delivery, and setting target audiences. This maximizes the return on advertising spend.

[0415] At the same time, the device provides support tools to help users smoothly create creative advertising materials. Using AI technology, templates and auto-generate functions allow users to easily design effective advertisements.

[0416] Finally, the server visualizes the predicted advertising effectiveness and provides it to the user in a dashboard format. Users can use this information to improve their advertising strategy and make informed decisions.

[0417] As a concrete example, consider a company launching a campaign for a new product. The server integrates the company's past campaign data with data from the new target market to create a highly accurate effectiveness prediction model. The terminal presents user-optimized creative options and guides the user in creating the best advertisements based on the media plan. As a result, the company can achieve a higher ROI and see the campaign's performance in advance.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] The server collects advertising-related information from internal databases and partner platforms. This includes historical advertising performance, customer demographic data, and performance metrics such as click-through rates. Users can upload custom datasets to the server to add specific data for analysis.

[0421] Step 2:

[0422] The server preprocesses the collected data. Specifically, it appropriately imputes missing values ​​and removes outliers using statistical methods. Numerical data is also normalized, preparing it for analysis and machine learning.

[0423] Step 3:

[0424] The server uses pre-processed data to build an effectiveness prediction model. This involves running machine learning algorithms to predict performance based on specific advertising parameters. The algorithms are refined to improve the model's accuracy, and different methods are cross-validated.

[0425] Step 4:

[0426] The server uses an effectiveness prediction model to generate an optimal media plan. This includes optimizing the target audience, delivery schedule, and advertising platforms for the ads. The server then presents the user with a plan that includes budget allocation.

[0427] Step 5:

[0428] The device provides AI-assisted tools to help users effectively create advertising creatives. Users can efficiently design advertisements by utilizing templates and materials suggested by the AI.

[0429] Step 6:

[0430] The server visualizes and provides users with the advertising effectiveness predicted by the model. This includes displays in graph and dashboard formats. Users can adjust their advertising strategies and make decisions based on the prediction results.

[0431] (Example 1)

[0432] 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."

[0433] Traditional advertising strategies struggle to effectively utilize past performance data and target customer data, and the low accuracy of predictive models prevents optimization of return on advertising spend. Furthermore, a lack of efficient support in creating creative advertising materials hinders the rapid improvement of advertising strategies.

[0434] 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.

[0435] In this invention, the server includes means for acquiring advertising-related data, means for processing the advertising-related data, and means for constructing a predictive model based on the processed information. This enables highly accurate effect prediction and allows for the rapid formulation of an optimized advertising strategy.

[0436] "Advertising-related data" refers to information including past performance data and target customer data, which is fundamental data necessary for analyzing advertising effectiveness.

[0437] "Processing" refers to the process of converting acquired data into a format suitable for analysis, including data imputation and removal of outliers.

[0438] A "predictive model" is a metric that uses mathematical or statistical methods to predict the effectiveness of an advertisement based on processed data.

[0439] An "optimized plan" is a strategic proposal that includes selected media, delivery timing, and targeting to maximize advertising effectiveness.

[0440] "Creative production" refers to activities related to design and content creation for the effective production of advertising materials.

[0441] "Artificial intelligence technology" refers to systems that use computers to mimic human intellectual behavior and perform data analysis, decision-making, and problem-solving.

[0442] "Visualization" is a method of representing data in a visual form, such as graphs or charts, to make it easier to understand.

[0443] To implement this invention, the server plays a central role primarily in the collection, processing, and analysis of advertising-related data. The server first retrieves data from internal and external databases, collecting historical performance data and target customer data. This utilizes database access technologies and API interfaces.

[0444] Next, the server uses data analysis software to process the acquired data. It preprocesses the data using the Python library Pandas, performing missing value imputation and standardization. It also utilizes Z-score analysis to remove outliers.

[0445] Furthermore, the server uses machine learning libraries such as Scikit-learn to build predictive models from the preprocessed data. For example, it uses the Random Forest algorithm to predict the effectiveness of advertisements. Cross-validation testing is also performed to improve the accuracy of the models.

[0446] The device plays a crucial role in creating creative advertising materials. It assists users in easily creating advertising materials using Adobe XD and other common design tools. It also provides AI-powered template suggestions and automatic copy generation features to improve user production efficiency.

[0447] Finally, the server uses data visualization tools to visualize and present the results of the predictive model to the user. Specifically, it leverages tools such as Tableau and Power BI to display the information in a dashboard format. This makes it easier for users to intuitively understand the effectiveness of the advertising strategy.

[0448] For example, if a user is planning an advertising campaign for a new product, the server analyzes historical data and suggests the optimal advertising strategy for the target market. With assistance from the device, the user can create creative visual materials and see how the strategy is performing through visualized data.

[0449] An example of a prompt is: "Please propose the optimal advertising strategy for our new product's target audience. Based on past campaign data and target market data, we would like creative suggestions to maximize ROI." This prompt allows the user to obtain specific strategic proposals.

[0450] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0451] Step 1:

[0452] The server collects advertising-related data. It uses SQL queries and APIs from internal and external databases to gather historical advertising performance data and target customer data. It receives database access information and search criteria as input, and outputs a set of relevant data as a result. Specifically, the server opens a database connection, executes queries, and retrieves the necessary data.

[0453] Step 2:

[0454] The server preprocesses the collected data. The raw data obtained in step 1 is used as input. The Python Pandas library is used to impute missing values, remove outliers, and standardize the data. Missing values ​​are imputed with the mean, and outliers are filtered out, resulting in a clean dataset. Specifically, the server creates a dataframe and applies the processing to each column.

[0455] Step 3:

[0456] The server builds an effect prediction model based on preprocessed data. The clean dataset obtained in step 2 is used as input. The model is trained using random forest or linear regression algorithms with the Scikit-learn library. The model's accuracy is validated through cross-validation, and the trained prediction model object is output. Specifically, the server selects an algorithm, applies data to the model, and performs training and evaluation.

[0457] Step 4:

[0458] The server generates an optimal media plan using the built predictive model. Inputs include the predictive model obtained in step 3 and requirements regarding the advertising strategy. Based on the predictive model's results, it selects media outlets, sets delivery timings, and outputs an optimized media plan document. Specifically, the server analyzes the model's prediction results and creates a plan in report format.

[0459] Step 5:

[0460] The device assists users in creating creative advertising materials. Inputs include templates and design proposals, which are customized according to user selections. It provides intuitively editable templates via Adobe XD and other design software, and outputs the final advertising material. Specifically, the device displays a user interface and provides editing tools.

[0461] Step 6:

[0462] The server visualizes and provides users with predictions of advertising effectiveness. It uses the media plan and prediction model results generated in step 4 as input. It generates graphs and charts using Tableau and Power BI, outputting dashboards that users can review. Specifically, the server operates data visualization tools to present information visually.

[0463] (Application Example 1)

[0464] 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."

[0465] Traditional advertising campaign planning and implementation processes required significant time and resources, and it was difficult to track their effectiveness in real time. As a result, advertisers struggled to develop optimal strategies and maximize the return on investment of their advertising. In particular, there is a need for rapid and effective advertising management methods utilizing mobile devices.

[0466] 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.

[0467] In this invention, the server includes means for acquiring advertising-related information, means for processing the advertising-related information, and means for creating a predictive model based on the processed information. This makes it possible to execute advertising campaigns on mobile devices, grasp the effectiveness of the advertisements in real time, and immediately notify the user's device of the effectiveness.

[0468] "Advertising-related information" refers to information that includes past performance data related to the implementation of advertising and data on target customers.

[0469] "Data processing" is the process of converting collected information into a format suitable for analysis and machine learning, and of filling in missing data and removing outliers.

[0470] A "predictive model" is a computational model used to predict the effectiveness of advertising based on past data and to formulate the optimal advertising strategy.

[0471] An "information dissemination plan" is a strategic plan that includes media selection, distribution timing, and target setting for effectively delivering advertisements.

[0472] "Content creation" is the process of producing visual and text-based materials for advertising purposes.

[0473] "Visualization" refers to displaying the results of data analysis in a clear and easy-to-understand format, such as graphs and charts.

[0474] A "mobile device" refers to an information processing device that is portable and can be carried at all times, such as a smartphone or tablet.

[0475] "Information performance data" refers to data that records the results and outcomes of advertising activities conducted in the past.

[0476] "Target customer data" refers to data that includes attribute information and behavioral history of customers who are targeted by the advertisement.

[0477] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0478] To implement this invention, the server first collects advertising-related information. This information includes past advertising performance data and target customer data. The server retrieves this information and uses data processing software to perform tasks such as filling in missing data, removing outliers, and standardizing the data. Possible software to use includes Python and SQL.

[0479] Next, the server uses the processed information to build an effectiveness prediction model using machine learning platforms such as TensorFlow and Scikit-learn. This model is used to accurately predict the effectiveness of advertisements and create an optimal media plan.

[0480] Users create ads on their mobile devices using templates based on media plans proposed by this predictive model. The ad editing interface utilizes HTML5, CSS, and JavaScript, and artificial intelligence technology enables the automatic generation of creative ad materials. This allows users to design ads with minimal effort.

[0481] Finally, once the ads are delivered, the server measures their effectiveness in real time and visualizes the results, providing them to the user as a dashboard. Visualization tools such as Tableau are used for this visualization. This allows users to understand the campaign's effectiveness in real time and incorporate it into their future strategies.

[0482] As a concrete example, consider an advertising campaign to announce a new product. Users easily create ad creatives on their smartphones based on the optimal media plan suggested by the server. During the campaign, the effectiveness of the ads is notified to the user's device in real time. An example of a prompt message would be, "Please suggest the optimal media plan to effectively run an advertising campaign for our new product."

[0483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0484] Step 1:

[0485] The server collects advertising-related information from internal and external databases. This information includes historical advertising performance data and target customer data. The input is information from the databases, and the output is the collected raw data. The server performs queries to extract the necessary information.

[0486] Step 2:

[0487] The server preprocesses the collected advertising-related information. The input is the raw data obtained in step 1, and the output is data in an analyzable format. The server uses Python libraries to perform tasks such as filling in missing data, detecting and removing outliers, and standardizing the data. This results in high-quality data.

[0488] Step 3:

[0489] The server builds an effectiveness prediction model based on preprocessed data. The input is the result of step 2, and the output is the effectiveness prediction model. The server uses TensorFlow and Scikit-learn to apply machine learning algorithms to train the model and create a model for predicting advertising effectiveness.

[0490] Step 4:

[0491] The user designs the optimal advertising campaign based on a predictive model using their device. The input is the predictive model generated from step 3, and the output is the campaign's media plan based on the user's selections. The user reviews the prediction results on their device and selects and edits ad creatives using AI-generated templates.

[0492] Step 5:

[0493] The device delivers user-designed advertisements. The input is the ad creative created in step 4, and the output is the delivery of the ad to the target audience. The device displays the ad on the specified media and at the specified time, according to the media plan.

[0494] Step 6:

[0495] The server measures the effectiveness of delivered advertisements in real time and notifies the user of the results. The input is aggregated data after ad delivery, and the output is visualized effectiveness analysis results. The server uses data visualization tools to create and present graphs and dashboards to the user.

[0496] 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.

[0497] To implement this invention, the first step is to collect and preprocess advertising-related information. The server collects past advertising performance data and target customer data, and builds an effectiveness prediction model based on this data. This prediction model makes it possible to evaluate the performance of advertising campaigns in advance.

[0498] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time. This emotion engine analyzes the user's emotional state from their facial expressions and tone of voice, quantifies it, and sends it back to the server as a report. This information is directly used to personalize advertising creatives.

[0499] The device uses AI-assisted tools to create advertising creatives. It provides a function to generate advertising materials optimized for the user's interests and preferences based on emotional information obtained from an emotion engine. This allows users to create more effective and sophisticated creatives.

[0500] Furthermore, the server adjusts the optimal media plan based on user sentiment information. This involves incorporating sentiment data into ad delivery timing and target audience segmentation to create a more engaging plan. It also utilizes a sentiment engine to generate feedback based on user emotions, which helps improve ad effectiveness.

[0501] As a concrete example, consider a company running an online campaign. When a user views an ad, the emotion engine analyzes their reaction, and if the user shows a positive reaction, the server presents an ad creative that leverages that emotion. The device then adjusts the elements of the creative based on that feedback, delivering a more effective ad. This improves ad performance and enhances the quality of the approach to the target audience.

[0502] The following describes the processing flow.

[0503] Step 1:

[0504] The server efficiently collects historical advertising performance data and target customer data from internal and external databases. This provides the foundational data needed for the next steps.

[0505] Step 2:

[0506] The server preprocesses the collected data. It imputes missing data, removes outliers, normalizes the data, and converts it into a format suitable for machine learning models.

[0507] Step 3:

[0508] The server builds an effectiveness prediction model based on pre-processed data. It runs machine learning algorithms to generate a model for accurately predicting ad performance.

[0509] Step 4:

[0510] The server uses an emotion engine to recognize the user's emotions in real time. While the user is viewing an advertisement, it analyzes their facial expressions and voice using a camera and microphone to acquire emotion data.

[0511] Step 5:

[0512] The server uses emotional information obtained from the emotion engine to adjust the optimal media plan. Based on emotional data, it optimizes ad targeting and delivery timing.

[0513] Step 6:

[0514] The device uses AI-assisted tools to create advertising creatives that respond to the user's emotions. Based on positive responses obtained by the emotion engine, the design and message are personalized and adjusted.

[0515] Step 7:

[0516] The server visualizes the results of advertising campaigns and provides them to users in a dashboard format. This allows users to check the effectiveness of their ads and use that information to inform their next strategies.

[0517] (Example 2)

[0518] 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."

[0519] Traditional advertising systems fail to maximize advertising effectiveness because they deliver ads without considering user emotions. Furthermore, ad production and media planning are often insufficiently optimized, highlighting the need for improved quality in targeting audiences.

[0520] 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.

[0521] In this invention, the server includes means for collecting information, means for preprocessing the information, means for building a predictive model, means for recognizing and analyzing user emotions, means for aggregating the analyzed emotional information as a report, and means for optimizing advertising materials based on the emotional information. This makes it possible to maximize the effectiveness of advertising and improve the quality of the approach to the target audience.

[0522] "Means of collecting information" refers to methods and devices for collecting various types of data, including past performance data and target customer data.

[0523] "Preprocessing means" refers to methods or devices for organizing and converting collected data into a format suitable for analysis and model building.

[0524] "Means for constructing a predictive model" refers to methods or devices for generating a model to evaluate the effectiveness of advertising using pre-processed data.

[0525] "Means for generating the optimal plan" refers to methods or devices that formulate advertising delivery plans based on predictive models and enable their effective implementation.

[0526] "Means of supporting production" refers to methods and devices that utilize artificial intelligence technology to assist in the process of editing and generating advertising materials.

[0527] "Means of visualization and display" refer to interfaces and devices for visually displaying predictive models and analysis results.

[0528] "Means for recognizing and analyzing user emotions" refers to methods or devices that identify and quantify emotional states using a person's facial expressions and tone of voice.

[0529] "Means for aggregating emotional information as a report" refers to methods or devices for integrating recognized emotional data and saving it in a report format that allows for analysis.

[0530] "Methods for optimizing advertising materials" refer to methods or devices that use aggregated emotional information to adjust advertising content to suit the user and maximize its effectiveness.

[0531] This invention is a system that maximizes the effectiveness of advertising by collecting various data, building predictive models, and optimizing advertising materials based on user emotions.

[0532] The server collects information and integrates historical advertising performance data and target customer data through database software (e.g., a database management system). The collected data is preprocessed using data analysis software, and the effectiveness prediction model is built using machine learning libraries (e.g., TensorFlow or scikit-learn).

[0533] Next, the server connects to an emotion recognition engine to recognize the user's emotions. It analyzes data collected through the user's device, such as a webcam or microphone, and quantifies emotions based on the user's facial expressions and tone of voice. The analyzed emotion information is then compiled on the server as a data report.

[0534] Furthermore, the device uses AI-assisted tools to create advertising creatives based on aggregated emotional information. For example, an AI tool integrated with Adobe Creative Cloud automatically generates advertising materials optimized for the user's interests and preferences. By utilizing emotional information in this process, more personalized content is provided.

[0535] As a concrete example, when a company conducts an online campaign, the emotion engine analyzes user reactions when viewing ads, and automatically generates and presents ads tailored to users who show positive emotions. The device adjusts the creative based on the feedback, improving ad performance. This system enables an effective approach to the target audience.

[0536] An example of a prompt message that can be input to the generating AI model is, "I want to personalize ad creatives based on user sentiment data," which allows for efficient ad customization.

[0537] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0538] Step 1:

[0539] The server collects information. Specifically, it uses a database management system to obtain historical advertising performance data and target customer data. This data is collected in its raw form and serves as foundational data for predicting advertising effectiveness. The input is raw advertising performance data, and the output is an organized dataset.

[0540] Step 2:

[0541] The server preprocesses the collected data. Data analysis software is used to perform noise reduction, missing value imputation, and data standardization. This prepares the data for model building. The input is the organized dataset, and the output is the preprocessed data.

[0542] Step 3:

[0543] The server builds an effect prediction model using preprocessed data. It uses a machine learning library (e.g., TensorFlow) to split the data into training and test sets. Then, it applies an algorithm to generate a model and evaluates its accuracy. The input is the preprocessed data, and the output is the trained prediction model.

[0544] Step 4:

[0545] The server recognizes the user's emotions in real time. The emotion engine analyzes facial expressions and voice tone acquired from the user's device and quantifies the emotional state. The emotional information is stored in a database as a report. The input is the user's facial expression and voice data, and the output is quantified emotional data.

[0546] Step 5:

[0547] The device uses AI-assisted tools to create advertising creatives. Here, the advertising materials are optimized based on aggregated emotional information. Using tools integrated with Adobe Creative Cloud, content is automatically generated. The input consists of quantified emotional data and predictive model results, while the output is optimized advertising material.

[0548] Step 6:

[0549] The server generates an optimal media plan based on analyzed sentiment information and predictive models. It adjusts ad delivery timing and target audience segmentation to maximize effectiveness. The input is ad material and the results of the predictive model, and the output is the adjusted media plan.

[0550] Step 7:

[0551] Users receive generated ads and react to them. The server collects emotional feedback based on these reactions and uses it to improve the effectiveness of the ads. The inputs are ad delivery and user reactions, and the output is improvement feedback.

[0552] (Application Example 2)

[0553] 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."

[0554] Current advertising systems have a problem in that ads are delivered uniformly, making it difficult to reflect individual user emotions and reactions in real time, thus failing to maximize the effectiveness of advertising. In particular, the lack of personalization based on user interests and preferences is a challenge in optimizing the effectiveness of advertising.

[0555] 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.

[0556] In this invention, the server includes means for collecting advertising-related information, means for pre-processing the information, means for constructing an effectiveness prediction model, means for generating an optimal media plan, means for supporting creative production, means for visualizing and displaying the results of the effectiveness prediction, and means for recognizing user emotions and optimizing advertising content in real time. This makes it possible to improve advertising performance and enhance the quality of advertising deployment to users.

[0557] "Advertising-related information" refers to all data related to the implementation of advertising, including past advertising performance data and target customer data.

[0558] "Preprocessing" refers to the process of organizing collected data according to its purpose and preparing it in a format that can be analyzed.

[0559] An "effectiveness prediction model" is a mathematical or statistical model built to predict the results of an advertising campaign in advance.

[0560] A "media plan" is a strategic plan that determines when and through which media advertisements will be delivered.

[0561] "Means of supporting creative production" refers to tools and systems that use AI technology to edit and generate advertising materials.

[0562] "Methods for recognizing user emotions and optimizing ad content in real time" refers to technologies and systems that analyze user emotions from facial expressions, voices, etc., and adjust ads on the spot.

[0563] To implement this invention, it is crucial to construct a system for collecting and preprocessing advertising-related information. The server collects advertising-related information from various data sources and preprocesses the information, including past advertising performance data and target customer data. This prepares the system for building an effectiveness prediction model.

[0564] The server generates an effectiveness prediction model based on pre-processed data. This model is developed using machine learning frameworks such as TensorFlow, allowing for the pre-evaluation of the probability of success of an advertising campaign. Based on this evaluation, an optimal media plan is formed to maximize the effectiveness of ad delivery.

[0565] The device utilizes AI-assisted tools to create creative content. The generative AI model used here leverages predefined prompts to generate advertising materials optimized for the user's interests and preferences. An emotion engine analyzes the user's facial expressions and tone of voice, and the collected emotion data is reflected in the advertising content in real time.

[0566] As a concrete example, when a user is watching a movie trailer, the device detects the user's smile and determines that they are expressing a positive emotion. This emotion data is sent to the server, and the system is optimized to prioritize displaying ad creatives for comedy movies.

[0567] Examples of prompt messages are as follows:

[0568] "Enter the current user's emotional data and compare it with past data to suggest the most suitable ad creative. Emotional data: High frequency of smiling, bright voice tone. Goal: Emphasize comedy movie advertisements."

[0569] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0570] Step 1:

[0571] The server collects advertising-related information from various data sources, including historical advertising performance data and target customer data. It takes historical advertising campaign data as input and generates a dataset integrating this data as output.

[0572] Step 2:

[0573] The server preprocesses the collected advertising-related information. The input data is checked for inconsistencies and missing data, and then cleaned. The cleaned data is used as output to build an effectiveness prediction model.

[0574] Step 3:

[0575] The server builds an effectiveness prediction model based on preprocessed data. This model is trained using machine learning tools such as TensorFlow. Using cleansed advertising data as input, it outputs a model that predicts the future performance of advertising campaigns.

[0576] Step 4:

[0577] The server utilizes the built-in effectiveness prediction model to create an optimal media plan. The results of the prediction model are used as input, and the output plan identifies the timing and media to which advertisements should be delivered.

[0578] Step 5:

[0579] The device utilizes AI-assisted tools to generate prompt messages based on the user's emotional data. It receives emotional data such as the user's smile and tone of voice as input and generates personalized prompt messages as output.

[0580] Step 6:

[0581] The device automatically generates ad creatives using an AI model based on the prompt text. It uses the input prompts to output ad materials tailored to the user's interests and preferences.

[0582] Step 7:

[0583] The server optimizes ad content in real time based on sentiment data received from the user's device. The input includes sentiment information from the device, and the server outputs optimized ad creatives, which are then delivered to the device.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] [Fourth Embodiment]

[0588] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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".

[0601] To implement this invention, the first step is to collect advertising-related information. The server efficiently gathers past advertising performance and target customer attribute data from internal and external databases. This allows analysis to begin with all the necessary information available. Users can also provide the server with custom data based on specific requirements.

[0602] Next, the server preprocesses the collected data. This preprocessing converts the data into a format suitable for analysis and machine learning. Specifically, it fills in missing data, detects and removes outliers, and standardizes the data. This improves the quality of the data and increases the accuracy of predictive models.

[0603] Subsequently, the server uses the pre-processed data to build an effectiveness prediction model. By utilizing machine learning algorithms to create a model that accurately predicts the effectiveness of advertisements, it optimizes the company's advertising strategy. This model undergoes validation during the construction phase, and its accuracy is constantly monitored during use.

[0604] Furthermore, the server generates an optimal media plan based on an effectiveness prediction model. This plan includes selecting media outlets for advertising, timing of delivery, and setting target audiences. This maximizes the return on advertising spend.

[0605] At the same time, the device provides support tools to help users smoothly create creative advertising materials. Using AI technology, templates and auto-generate functions allow users to easily design effective advertisements.

[0606] Finally, the server visualizes the predicted advertising effectiveness and provides it to the user in a dashboard format. Users can use this information to improve their advertising strategy and make informed decisions.

[0607] As a concrete example, consider a company launching a campaign for a new product. The server integrates the company's past campaign data with data from the new target market to create a highly accurate effectiveness prediction model. The terminal presents user-optimized creative options and guides the user in creating the best advertisements based on the media plan. As a result, the company can achieve a higher ROI and see the campaign's performance in advance.

[0608] The following describes the processing flow.

[0609] Step 1:

[0610] The server collects advertising-related information from internal databases and partner platforms. This includes historical advertising performance, customer demographic data, and performance metrics such as click-through rates. Users can upload custom datasets to the server to add specific data for analysis.

[0611] Step 2:

[0612] The server preprocesses the collected data. Specifically, it appropriately imputes missing values ​​and removes outliers using statistical methods. Numerical data is also normalized, preparing it for analysis and machine learning.

[0613] Step 3:

[0614] The server uses pre-processed data to build an effectiveness prediction model. This involves running machine learning algorithms to predict performance based on specific advertising parameters. The algorithms are refined to improve the model's accuracy, and different methods are cross-validated.

[0615] Step 4:

[0616] The server uses an effectiveness prediction model to generate an optimal media plan. This includes optimizing the target audience, delivery schedule, and advertising platforms for the ads. The server then presents the user with a plan that includes budget allocation.

[0617] Step 5:

[0618] The device provides AI-assisted tools to help users effectively create advertising creatives. Users can efficiently design advertisements by utilizing templates and materials suggested by the AI.

[0619] Step 6:

[0620] The server visualizes and provides users with the advertising effectiveness predicted by the model. This includes displays in graph and dashboard formats. Users can adjust their advertising strategies and make decisions based on the prediction results.

[0621] (Example 1)

[0622] 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".

[0623] Traditional advertising strategies struggle to effectively utilize past performance data and target customer data, and the low accuracy of predictive models prevents optimization of return on advertising spend. Furthermore, a lack of efficient support in creating creative advertising materials hinders the rapid improvement of advertising strategies.

[0624] 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.

[0625] In this invention, the server includes means for acquiring advertising-related data, means for processing the advertising-related data, and means for constructing a predictive model based on the processed information. This enables highly accurate effect prediction and allows for the rapid formulation of an optimized advertising strategy.

[0626] "Advertising-related data" refers to information including past performance data and target customer data, which is fundamental data necessary for analyzing advertising effectiveness.

[0627] "Processing" refers to the process of converting acquired data into a format suitable for analysis, including data imputation and removal of outliers.

[0628] A "predictive model" is a metric that uses mathematical or statistical methods to predict the effectiveness of an advertisement based on processed data.

[0629] An "optimized plan" is a strategic proposal that includes selected media, delivery timing, and targeting to maximize advertising effectiveness.

[0630] "Creative production" refers to activities related to design and content creation for the effective production of advertising materials.

[0631] "Artificial intelligence technology" refers to systems that use computers to mimic human intellectual behavior and perform data analysis, decision-making, and problem-solving.

[0632] "Visualization" is a method of representing data in a visual form, such as graphs or charts, to make it easier to understand.

[0633] To implement this invention, the server plays a central role primarily in the collection, processing, and analysis of advertising-related data. The server first retrieves data from internal and external databases, collecting historical performance data and target customer data. This utilizes database access technologies and API interfaces.

[0634] Next, the server uses data analysis software to process the acquired data. It preprocesses the data using the Python library Pandas, performing missing value imputation and standardization. It also utilizes Z-score analysis to remove outliers.

[0635] Furthermore, the server uses machine learning libraries such as Scikit-learn to build predictive models from the preprocessed data. For example, it uses the Random Forest algorithm to predict the effectiveness of advertisements. Cross-validation testing is also performed to improve the accuracy of the models.

[0636] The device plays a crucial role in creating creative advertising materials. It assists users in easily creating advertising materials using Adobe XD and other common design tools. It also provides AI-powered template suggestions and automatic copy generation features to improve user production efficiency.

[0637] Finally, the server uses data visualization tools to visualize and present the results of the predictive model to the user. Specifically, it leverages tools such as Tableau and Power BI to display the information in a dashboard format. This makes it easier for users to intuitively understand the effectiveness of the advertising strategy.

[0638] For example, if a user is planning an advertising campaign for a new product, the server analyzes historical data and suggests the optimal advertising strategy for the target market. With assistance from the device, the user can create creative visual materials and see how the strategy is performing through visualized data.

[0639] An example of a prompt is: "Please propose the optimal advertising strategy for our new product's target audience. Based on past campaign data and target market data, we would like creative suggestions to maximize ROI." This prompt allows the user to obtain specific strategic proposals.

[0640] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0641] Step 1:

[0642] The server collects advertising-related data. It uses SQL queries and APIs from internal and external databases to gather historical advertising performance data and target customer data. It receives database access information and search criteria as input, and outputs a set of relevant data as a result. Specifically, the server opens a database connection, executes queries, and retrieves the necessary data.

[0643] Step 2:

[0644] The server preprocesses the collected data. The raw data obtained in step 1 is used as input. The Python Pandas library is used to impute missing values, remove outliers, and standardize the data. Missing values ​​are imputed with the mean, and outliers are filtered out, resulting in a clean dataset. Specifically, the server creates a dataframe and applies the processing to each column.

[0645] Step 3:

[0646] The server builds an effect prediction model based on preprocessed data. The clean dataset obtained in step 2 is used as input. The model is trained using random forest or linear regression algorithms with the Scikit-learn library. The model's accuracy is validated through cross-validation, and the trained prediction model object is output. Specifically, the server selects an algorithm, applies data to the model, and performs training and evaluation.

[0647] Step 4:

[0648] The server generates an optimal media plan using the built predictive model. Inputs include the predictive model obtained in step 3 and requirements regarding the advertising strategy. Based on the predictive model's results, it selects media outlets, sets delivery timings, and outputs an optimized media plan document. Specifically, the server analyzes the model's prediction results and creates a plan in report format.

[0649] Step 5:

[0650] The device assists users in creating creative advertising materials. Inputs include templates and design proposals, which are customized according to user selections. It provides intuitively editable templates via Adobe XD and other design software, and outputs the final advertising material. Specifically, the device displays a user interface and provides editing tools.

[0651] Step 6:

[0652] The server visualizes and provides users with predictions of advertising effectiveness. It uses the media plan and prediction model results generated in step 4 as input. It generates graphs and charts using Tableau and Power BI, outputting dashboards that users can review. Specifically, the server operates data visualization tools to present information visually.

[0653] (Application Example 1)

[0654] 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".

[0655] Traditional advertising campaign planning and implementation processes required significant time and resources, and it was difficult to track their effectiveness in real time. As a result, advertisers struggled to develop optimal strategies and maximize the return on investment of their advertising. In particular, there is a need for rapid and effective advertising management methods utilizing mobile devices.

[0656] 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.

[0657] In this invention, the server includes means for acquiring advertising-related information, means for processing the advertising-related information, and means for creating a predictive model based on the processed information. This makes it possible to execute advertising campaigns on mobile devices, grasp the effectiveness of the advertisements in real time, and immediately notify the user's device of the effectiveness.

[0658] "Advertising-related information" refers to information that includes past performance data related to the implementation of advertising and data on target customers.

[0659] "Data processing" is the process of converting collected information into a format suitable for analysis and machine learning, and of filling in missing data and removing outliers.

[0660] A "predictive model" is a computational model used to predict the effectiveness of advertising based on past data and to formulate the optimal advertising strategy.

[0661] An "information dissemination plan" is a strategic plan that includes media selection, distribution timing, and target setting for effectively delivering advertisements.

[0662] "Content creation" is the process of producing visual and text-based materials for advertising purposes.

[0663] "Visualization" refers to displaying the results of data analysis in a clear and easy-to-understand format, such as graphs and charts.

[0664] A "mobile device" refers to an information processing device that is portable and can be carried at all times, such as a smartphone or tablet.

[0665] "Information performance data" refers to data that records the results and outcomes of advertising activities conducted in the past.

[0666] "Target customer data" refers to data that includes attribute information and behavioral history of customers who are targeted by the advertisement.

[0667] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0668] To implement this invention, the server first collects advertising-related information. This information includes past advertising performance data and target customer data. The server retrieves this information and uses data processing software to perform tasks such as filling in missing data, removing outliers, and standardizing the data. Possible software to use includes Python and SQL.

[0669] Next, the server uses the processed information to build an effectiveness prediction model using machine learning platforms such as TensorFlow and Scikit-learn. This model is used to accurately predict the effectiveness of advertisements and create an optimal media plan.

[0670] Users create ads on their mobile devices using templates based on media plans proposed by this predictive model. The ad editing interface utilizes HTML5, CSS, and JavaScript, and artificial intelligence technology enables the automatic generation of creative ad materials. This allows users to design ads with minimal effort.

[0671] Finally, once the ads are delivered, the server measures their effectiveness in real time and visualizes the results, providing them to the user as a dashboard. Visualization tools such as Tableau are used for this visualization. This allows users to understand the campaign's effectiveness in real time and incorporate it into their future strategies.

[0672] As a concrete example, consider an advertising campaign to announce a new product. Users easily create ad creatives on their smartphones based on the optimal media plan suggested by the server. During the campaign, the effectiveness of the ads is notified to the user's device in real time. An example of a prompt message would be, "Please suggest the optimal media plan to effectively run an advertising campaign for our new product."

[0673] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0674] Step 1:

[0675] The server collects advertising-related information from internal and external databases. This information includes historical advertising performance data and target customer data. The input is information from the databases, and the output is the collected raw data. The server performs queries to extract the necessary information.

[0676] Step 2:

[0677] The server preprocesses the collected advertising-related information. The input is the raw data obtained in step 1, and the output is data in an analyzable format. The server uses Python libraries to perform tasks such as filling in missing data, detecting and removing outliers, and standardizing the data. This results in high-quality data.

[0678] Step 3:

[0679] The server builds an effectiveness prediction model based on preprocessed data. The input is the result of step 2, and the output is the effectiveness prediction model. The server uses TensorFlow and Scikit-learn to apply machine learning algorithms to train the model and create a model for predicting advertising effectiveness.

[0680] Step 4:

[0681] The user designs the optimal advertising campaign based on a predictive model using their device. The input is the predictive model generated from step 3, and the output is the campaign's media plan based on the user's selections. The user reviews the prediction results on their device and selects and edits ad creatives using AI-generated templates.

[0682] Step 5:

[0683] The device delivers user-designed advertisements. The input is the ad creative created in step 4, and the output is the delivery of the ad to the target audience. The device displays the ad on the specified media and at the specified time, according to the media plan.

[0684] Step 6:

[0685] The server measures the effectiveness of delivered advertisements in real time and notifies the user of the results. The input is aggregated data after ad delivery, and the output is visualized effectiveness analysis results. The server uses data visualization tools to create and present graphs and dashboards to the user.

[0686] 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.

[0687] To implement this invention, the first step is to collect and preprocess advertising-related information. The server collects past advertising performance data and target customer data, and builds an effectiveness prediction model based on this data. This prediction model makes it possible to evaluate the performance of advertising campaigns in advance.

[0688] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time. This emotion engine analyzes the user's emotional state from their facial expressions and tone of voice, quantifies it, and sends it back to the server as a report. This information is directly used to personalize advertising creatives.

[0689] The device uses AI-assisted tools to create advertising creatives. It provides a function to generate advertising materials optimized for the user's interests and preferences based on emotional information obtained from an emotion engine. This allows users to create more effective and sophisticated creatives.

[0690] Furthermore, the server adjusts the optimal media plan based on user sentiment information. This involves incorporating sentiment data into ad delivery timing and target audience segmentation to create a more engaging plan. It also utilizes a sentiment engine to generate feedback based on user emotions, which helps improve ad effectiveness.

[0691] As a concrete example, consider a company running an online campaign. When a user views an ad, the emotion engine analyzes their reaction, and if the user shows a positive reaction, the server presents an ad creative that leverages that emotion. The device then adjusts the elements of the creative based on that feedback, delivering a more effective ad. This improves ad performance and enhances the quality of the approach to the target audience.

[0692] The following describes the processing flow.

[0693] Step 1:

[0694] The server efficiently collects historical advertising performance data and target customer data from internal and external databases. This provides the foundational data needed for the next steps.

[0695] Step 2:

[0696] The server preprocesses the collected data. It imputes missing data, removes outliers, normalizes the data, and converts it into a format suitable for machine learning models.

[0697] Step 3:

[0698] The server builds an effectiveness prediction model based on pre-processed data. It runs machine learning algorithms to generate a model for accurately predicting ad performance.

[0699] Step 4:

[0700] The server uses an emotion engine to recognize the user's emotions in real time. While the user is viewing an advertisement, it analyzes their facial expressions and voice using a camera and microphone to acquire emotion data.

[0701] Step 5:

[0702] The server uses emotional information obtained from the emotion engine to adjust the optimal media plan. Based on emotional data, it optimizes ad targeting and delivery timing.

[0703] Step 6:

[0704] The device uses AI-assisted tools to create advertising creatives that respond to the user's emotions. Based on positive responses obtained by the emotion engine, the design and message are personalized and adjusted.

[0705] Step 7:

[0706] The server visualizes the results of advertising campaigns and provides them to users in a dashboard format. This allows users to check the effectiveness of their ads and use that information to inform their next strategies.

[0707] (Example 2)

[0708] 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".

[0709] Traditional advertising systems fail to maximize advertising effectiveness because they deliver ads without considering user emotions. Furthermore, ad production and media planning are often insufficiently optimized, highlighting the need for improved quality in targeting audiences.

[0710] 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.

[0711] In this invention, the server includes means for collecting information, means for preprocessing the information, means for building a predictive model, means for recognizing and analyzing user emotions, means for aggregating the analyzed emotional information as a report, and means for optimizing advertising materials based on the emotional information. This makes it possible to maximize the effectiveness of advertising and improve the quality of the approach to the target audience.

[0712] "Means of collecting information" refers to methods and devices for collecting various types of data, including past performance data and target customer data.

[0713] "Preprocessing means" refers to methods or devices for organizing and converting collected data into a format suitable for analysis and model building.

[0714] "Means for constructing a predictive model" refers to methods or devices for generating a model to evaluate the effectiveness of advertising using pre-processed data.

[0715] "Means for generating the optimal plan" refers to methods or devices that formulate advertising delivery plans based on predictive models and enable their effective implementation.

[0716] "Means of supporting production" refers to methods and devices that utilize artificial intelligence technology to assist in the process of editing and generating advertising materials.

[0717] "Means of visualization and display" refer to interfaces and devices for visually displaying predictive models and analysis results.

[0718] "Means for recognizing and analyzing user emotions" refers to methods or devices that identify and quantify emotional states using a person's facial expressions and tone of voice.

[0719] "Means for aggregating emotional information as a report" refers to methods or devices for integrating recognized emotional data and saving it in a report format that allows for analysis.

[0720] "Methods for optimizing advertising materials" refer to methods or devices that use aggregated emotional information to adjust advertising content to suit the user and maximize its effectiveness.

[0721] This invention is a system that maximizes the effectiveness of advertising by collecting various data, building predictive models, and optimizing advertising materials based on user emotions.

[0722] The server collects information and integrates historical advertising performance data and target customer data through database software (e.g., a database management system). The collected data is preprocessed using data analysis software, and the effectiveness prediction model is built using machine learning libraries (e.g., TensorFlow or scikit-learn).

[0723] Next, the server connects to an emotion recognition engine to recognize the user's emotions. It analyzes data collected through the user's device, such as a webcam or microphone, and quantifies emotions based on the user's facial expressions and tone of voice. The analyzed emotion information is then compiled on the server as a data report.

[0724] Furthermore, the device uses AI-assisted tools to create advertising creatives based on aggregated emotional information. For example, an AI tool integrated with Adobe Creative Cloud automatically generates advertising materials optimized for the user's interests and preferences. By utilizing emotional information in this process, more personalized content is provided.

[0725] As a concrete example, when a company conducts an online campaign, the emotion engine analyzes user reactions when viewing ads, and automatically generates and presents ads tailored to users who show positive emotions. The device adjusts the creative based on the feedback, improving ad performance. This system enables an effective approach to the target audience.

[0726] An example of a prompt message that can be input to the generating AI model is, "I want to personalize ad creatives based on user sentiment data," which allows for efficient ad customization.

[0727] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0728] Step 1:

[0729] The server collects information. Specifically, it uses a database management system to obtain historical advertising performance data and target customer data. This data is collected in its raw form and serves as foundational data for predicting advertising effectiveness. The input is raw advertising performance data, and the output is an organized dataset.

[0730] Step 2:

[0731] The server preprocesses the collected data. Data analysis software is used to perform noise reduction, missing value imputation, and data standardization. This prepares the data for model building. The input is the organized dataset, and the output is the preprocessed data.

[0732] Step 3:

[0733] The server builds an effect prediction model using preprocessed data. It uses a machine learning library (e.g., TensorFlow) to split the data into training and test sets. Then, it applies an algorithm to generate a model and evaluates its accuracy. The input is the preprocessed data, and the output is the trained prediction model.

[0734] Step 4:

[0735] The server recognizes the user's emotions in real time. The emotion engine analyzes facial expressions and voice tone acquired from the user's device and quantifies the emotional state. The emotional information is stored in a database as a report. The input is the user's facial expression and voice data, and the output is quantified emotional data.

[0736] Step 5:

[0737] The device uses AI-assisted tools to create advertising creatives. Here, the advertising materials are optimized based on aggregated emotional information. Using tools integrated with Adobe Creative Cloud, content is automatically generated. The input consists of quantified emotional data and predictive model results, while the output is optimized advertising material.

[0738] Step 6:

[0739] The server generates an optimal media plan based on analyzed sentiment information and predictive models. It adjusts ad delivery timing and target audience segmentation to maximize effectiveness. The input is ad material and the results of the predictive model, and the output is the adjusted media plan.

[0740] Step 7:

[0741] Users receive generated ads and react to them. The server collects emotional feedback based on these reactions and uses it to improve the effectiveness of the ads. The inputs are ad delivery and user reactions, and the output is improvement feedback.

[0742] (Application Example 2)

[0743] 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".

[0744] Current advertising systems have a problem in that ads are delivered uniformly, making it difficult to reflect individual user emotions and reactions in real time, thus failing to maximize the effectiveness of advertising. In particular, the lack of personalization based on user interests and preferences is a challenge in optimizing the effectiveness of advertising.

[0745] 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.

[0746] In this invention, the server includes means for collecting advertising-related information, means for pre-processing the information, means for constructing an effectiveness prediction model, means for generating an optimal media plan, means for supporting creative production, means for visualizing and displaying the results of the effectiveness prediction, and means for recognizing user emotions and optimizing advertising content in real time. This makes it possible to improve advertising performance and enhance the quality of advertising deployment to users.

[0747] "Advertising-related information" refers to all data related to the implementation of advertising, including past advertising performance data and target customer data.

[0748] "Preprocessing" refers to the process of organizing collected data according to its purpose and preparing it in a format that can be analyzed.

[0749] An "effectiveness prediction model" is a mathematical or statistical model built to predict the results of an advertising campaign in advance.

[0750] A "media plan" is a strategic plan that determines when and through which media advertisements will be delivered.

[0751] "Means of supporting creative production" refers to tools and systems that use AI technology to edit and generate advertising materials.

[0752] "Methods for recognizing user emotions and optimizing ad content in real time" refers to technologies and systems that analyze user emotions from facial expressions, voices, etc., and adjust ads on the spot.

[0753] To implement this invention, it is crucial to construct a system for collecting and preprocessing advertising-related information. The server collects advertising-related information from various data sources and preprocesses the information, including past advertising performance data and target customer data. This prepares the system for building an effectiveness prediction model.

[0754] The server generates an effectiveness prediction model based on pre-processed data. This model is developed using machine learning frameworks such as TensorFlow, allowing for the pre-evaluation of the probability of success of an advertising campaign. Based on this evaluation, an optimal media plan is formed to maximize the effectiveness of ad delivery.

[0755] The device utilizes AI-assisted tools to create creative content. The generative AI model used here leverages predefined prompts to generate advertising materials optimized for the user's interests and preferences. An emotion engine analyzes the user's facial expressions and tone of voice, and the collected emotion data is reflected in the advertising content in real time.

[0756] As a concrete example, when a user is watching a movie trailer, the device detects the user's smile and determines that they are expressing a positive emotion. This emotion data is sent to the server, and the system is optimized to prioritize displaying ad creatives for comedy movies.

[0757] Examples of prompt messages are as follows:

[0758] "Enter the current user's emotional data and compare it with past data to suggest the most suitable ad creative. Emotional data: High frequency of smiling, bright voice tone. Goal: Emphasize comedy movie advertisements."

[0759] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0760] Step 1:

[0761] The server collects advertising-related information from various data sources, including historical advertising performance data and target customer data. It takes historical advertising campaign data as input and generates a dataset integrating this data as output.

[0762] Step 2:

[0763] The server preprocesses the collected advertising-related information. The input data is checked for inconsistencies and missing data, and then cleaned. The cleaned data is used as output to build an effectiveness prediction model.

[0764] Step 3:

[0765] The server builds an effectiveness prediction model based on preprocessed data. This model is trained using machine learning tools such as TensorFlow. Using cleansed advertising data as input, it outputs a model that predicts the future performance of advertising campaigns.

[0766] Step 4:

[0767] The server utilizes the built-in effectiveness prediction model to create an optimal media plan. The results of the prediction model are used as input, and the output plan identifies the timing and media to which advertisements should be delivered.

[0768] Step 5:

[0769] The device utilizes AI-assisted tools to generate prompt messages based on the user's emotional data. It receives emotional data such as the user's smile and tone of voice as input and generates personalized prompt messages as output.

[0770] Step 6:

[0771] The device automatically generates ad creatives using an AI model based on the prompt text. It uses the input prompts to output ad materials tailored to the user's interests and preferences.

[0772] Step 7:

[0773] The server optimizes ad content in real time based on sentiment data received from the user's device. The input includes sentiment information from the device, and the server outputs optimized ad creatives, which are then delivered to the device.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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."

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0795] The following is further disclosed regarding the embodiments described above.

[0796] (Claim 1)

[0797] Means of collecting advertising-related information,

[0798] Means for preprocessing the aforementioned advertising-related information,

[0799] Means for constructing an effect prediction model based on the aforementioned preprocessed information,

[0800] A means for generating an optimal media plan based on the aforementioned effect prediction model,

[0801] Means to support creative production,

[0802] A means for visualizing and displaying the results of the aforementioned effect prediction,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, wherein the advertising-related information includes past advertising performance data and target customer data.

[0806] (Claim 3)

[0807] The means for supporting the creative production is the system according to claim 1, which enables the editing and generation of advertising materials using AI technology.

[0808] "Example 1"

[0809] (Claim 1)

[0810] Means of obtaining advertising-related data,

[0811] Means for processing the aforementioned advertising-related data,

[0812] A means for constructing a predictive model based on the processed information,

[0813] Means for generating an optimized plan based on the aforementioned prediction model,

[0814] Devices to support creative production,

[0815] A device for visualizing and presenting the aforementioned prediction results,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, wherein the advertising-related data includes past performance data and target customer data.

[0819] (Claim 3)

[0820] The apparatus for supporting the aforementioned creative production is the system according to claim 1, which enables the editing and generation of materials using artificial intelligence technology.

[0821] "Application Example 1"

[0822] (Claim 1)

[0823] Means of obtaining advertising-related information,

[0824] Means for processing the aforementioned advertising-related information,

[0825] Means for creating a predictive model based on the data processed information,

[0826] A means for formulating an optimal information dissemination plan based on the aforementioned predictive model,

[0827] Means to support content creation,

[0828] Means for visualizing and displaying the results of the aforementioned prediction,

[0829] Means of running advertising campaigns on mobile devices,

[0830] A means of notifying users of the effectiveness of advertisements in real time,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, wherein the advertising-related information includes past information performance data and target customer data.

[0834] (Claim 3)

[0835] The means for assisting in the creation of the aforementioned content is the system according to claim 1, which enables the editing and generation of information materials using artificial intelligence technology.

[0836] "Example 2 of combining an emotion engine"

[0837] (Claim 1)

[0838] Means of collecting information,

[0839] Means for preprocessing the aforementioned information,

[0840] Means for constructing a predictive model based on the aforementioned preprocessed information,

[0841] Means for generating an optimal plan based on the aforementioned prediction model,

[0842] Means to support production,

[0843] Means for visualizing and displaying the results,

[0844] A means of recognizing and analyzing user emotions,

[0845] A means for aggregating the analyzed emotional information into a report,

[0846] A means for optimizing advertising materials based on the aforementioned emotional information,

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, wherein the aforementioned information includes past performance data and target customer data.

[0850] (Claim 3)

[0851] The means for supporting the production is the system according to claim 1, which enables the editing and generation of materials using artificial intelligence technology.

[0852] "Application example 2 when combining with an emotional engine"

[0853] (Claim 1)

[0854] Means of collecting advertising-related information,

[0855] Means for preprocessing the aforementioned advertising-related information,

[0856] Means for constructing an effect prediction model based on the aforementioned preprocessed information,

[0857] A means for generating an optimal media plan based on the aforementioned effect prediction model,

[0858] Means to support creative production,

[0859] A means for visualizing and displaying the results of the aforementioned effect prediction,

[0860] A means of recognizing user emotions and optimizing ad content in real time,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, wherein the advertising-related information includes past advertising performance data and target customer data.

[0864] (Claim 3)

[0865] The means for supporting the creative production is the system according to claim 1, which enables the editing and generation of advertising materials using artificial intelligence technology and instantly optimizes them based on user sentiment data. [Explanation of symbols]

[0866] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting advertising-related information, Means for preprocessing the aforementioned advertising-related information, Means for constructing an effect prediction model based on the aforementioned preprocessed information, A means for generating an optimal media plan based on the aforementioned effect prediction model, Means to support creative production, A means for visualizing and displaying the results of the aforementioned effect prediction, A system that includes this.

2. The system according to claim 1, wherein the advertising-related information includes past advertising performance data and target customer data.

3. The means for supporting the creative production is the system according to claim 1, which enables the editing and generation of advertising materials using AI technology.

Images