system

Abstract

We provide the system. [Solution] A means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information, A method for automatically generating ad creatives based on collected parameters, A means of delivering generated ad creatives to the optimal location based on specific time, weather, area, and season, A means of collecting data on the effectiveness of delivered advertising creatives, A means to update the generation model for the next advertising creative based on the collected effectiveness data, 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional marketing methods, there are problems that generating and distributing advanced advertising creatives based on product characteristics and target insights requires time and effort, and it is difficult to quickly launch an effective advertising campaign. Also, since the advertising creatives cannot be autonomously optimized using real-time feedback on the advertising effect, there is a problem that the advertising effect cannot be maximized.

Means for Solving the Problems

[0005] The present invention provides a system comprising means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information, means for automatically generating advertising creatives based on the collected parameters, means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season, means for collecting effectiveness data of the delivered advertising creatives, and means for updating the generation model for the next advertising creative based on the collected effectiveness data. This enables marketing personnel to deploy advertising campaigns quickly and effectively and maximize advertising effectiveness using real-time feedback.

[0006] "Product characteristics" refer to the unique features, advantages, functions, and uses of a product.

[0007] "Target information" refers to attribute information (age, gender, hobbies, behavioral patterns, etc.) about the customer segment targeted by the advertisement.

[0008] "Parameters" refer to the data and conditions necessary for generating and delivering advertising creatives.

[0009] "Advertising creative" refers to advertising materials such as videos, images, and text designed for the purpose of advertising and promoting products.

[0010] "Automatic generation" refers to the process of generating advertising creatives autonomously using systems or algorithms, rather than manually.

[0011] "Distribution" refers to the act of delivering generated advertising creatives to the target audience at the appropriate time and place.

[0012] "Effectiveness data" refers to performance indicators (such as click-through rate, conversion rate, and viewing time) collected after an ad creative has been delivered.

[0013] A "machine learning algorithm" refers to mathematical methods and statistical techniques used to train a model using collected data and apply those results to future ad generation.

[0014] "Model updating" refers to the process of improving and optimizing existing ad generation models based on collected effectiveness data. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] 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), etc.

[0019] 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.

[0020] 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.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the advertising generation model for the next campaign based on collected effectiveness data.

[0037] System Configuration

[0038] This system consists of the following main components:

[0039] 1. Input Interface

[0040] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[0041] This means that marketing personnel will manually provide the information.

[0042] 2. Data Acquisition Module

[0043] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0044] 3. Ad Creative Generation Module

[0045] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[0046] 4. Ad delivery module

[0047] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[0048] 5. Effectiveness Data Collection Module

[0049] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0050] 6. Learning Modules

[0051] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[0052] Specific example

[0053] scenario

[0054] Let's take the example of advertising a new sports drink to active women in their 20s.

[0055] 1. Input

[0056] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[0057] 2. Data Collection

[0058] The server receives product characteristics and target information, and collects the current weather ("sunny") via a weather information API, attribute information of the target area ("urban") from a geographic information service, the current time ("morning") based on the system time, and the season ("summer").

[0059] 3. Ad generation

[0060] The server selects an ad template suitable for a sunny morning and generates ad creatives themed around "women in their 20s enjoying running." For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[0061] 4. Ad delivery

[0062] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[0063] 5. Collection of effectiveness data

[0064] The server collects and analyzes effectiveness data such as click-through rates, conversion rates, and viewing time for delivered advertisements.

[0065] 6. Learning and updating

[0066] The server uses machine learning algorithms to update its model based on the collected performance data, thereby improving the accuracy of future ad creative generation.

[0067] As described above, the system of the present invention automatically generates effective advertising campaigns by utilizing product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[0068] The following describes the processing flow.

[0069] Step 1:

[0070] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[0071] Step 2:

[0072] The terminal sends the information entered by the user to the server. This allows the server to receive the necessary parameters.

[0073] Step 3:

[0074] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[0075] Step 4:

[0076] The server collects information about the target area via geographic information services. The information obtained includes "urban areas," etc.

[0077] Step 5:

[0078] The server identifies the current time zone based on the system time. In this case, for example, the time zone "morning" might be identified.

[0079] Step 6:

[0080] The server retrieves the current seasonal data. For example, it collects seasonal information such as "summer."

[0081] Step 7:

[0082] The server selects the optimal ad template based on all the collected parameters. For example, it might choose a template that includes a "running scene on a sunny day."

[0083] Step 8:

[0084] The server automatically generates specific ad creatives based on product characteristics and target attributes. For example, it might create a scene depicting "a woman in her 20s drinking a sports drink while running."

[0085] Step 9:

[0086] The server creates a preview of the generated ad creative and provides it to the user via the device.

[0087] Step 10:

[0088] The user reviews and approves the ad creative on their device. The approval information is sent from the device to the server.

[0089] Step 11:

[0090] The server delivers the ad creative at the optimal time and place. For example, the target audience might be a "fitness app," and the delivery time might be "a sunny summer morning."

[0091] Step 12:

[0092] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0093] Step 13:

[0094] The server analyzes the collected effectiveness data using machine learning algorithms. This identifies effective factors and areas for improvement.

[0095] Step 14:

[0096] The server updates its ad generation model using the results of machine learning. For example, it learns elements that further emphasize the "refreshing effect after running."

[0097] Step 15:

[0098] The server prepares to incorporate the updated model into the next ad generation. This will enable the automated generation of more effective ad creatives.

[0099] The above describes the specific processing steps of the program and the actions of each step.

[0100] (Example 1)

[0101] 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."

[0102] In today's advertising market, it's essential to generate ad creatives based on product characteristics and target information, and deliver them at the optimal time and place. However, doing this manually is extremely time-consuming and labor-intensive, and furthermore, to generate more effective ads, it's necessary to update the ad generation model to reflect past advertising performance data. Therefore, there is a need for a system that automates the ad generation process and maximizes advertising effectiveness based on collected data.

[0103] 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.

[0104] In this invention, the server includes means for a user to input product characteristics and target information via a terminal; means for transmitting the input product characteristics and target information to the server; means for collecting supplementary data from an external data source based on the transmitted information; means for updating a database based on the collected data; means for inputting prompt text into a generation AI model based on the updated data to generate advertising creatives; means for combining the generated advertising creatives with a selected advertising template; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives in real time; and means for analyzing the collected effectiveness data and updating the advertising generation model using a machine learning algorithm. This enables automatic generation of advertising creatives, delivery at the optimal timing, and model updates based on effectiveness data.

[0105] "Product characteristics" refer to the unique properties and features of a product, including its function, effect, and use.

[0106] "Target information" refers to information about a specific consumer group that is the target of marketing activities, and includes data such as age, gender, region, and interests.

[0107] "User" refers to the entity that inputs and manages information for generating advertising creatives using this system, and usually refers to a marketing professional.

[0108] A "terminal" refers to a device used to input information into or receive information from this system, and includes PCs and mobile devices.

[0109] A "server" refers to a computing system used to process information, manage databases, generate and distribute advertising creatives, and collect performance data.

[0110] "External data sources" refer to external information services that provide supplemental data required by this system, and include weather information APIs and geographic information services.

[0111] A "generative AI model" refers to an artificial intelligence model that generates advertising creatives from given prompt text.

[0112] A "prompt message" refers to a command or instruction given to the AI ​​model, which then generates appropriate advertising creatives.

[0113] An "ad template" refers to a format that has a structure and layout for creating advertising creatives.

[0114] "Advertising creative" refers to advertising materials generated by generative AI models, and includes visuals and text.

[0115] "Effectiveness data" refers to data related to the performance of delivered advertisements, and includes click-through rates, conversion rates, and viewing time.

[0116] A "machine learning algorithm" refers to a computational method used to analyze data, identify patterns and regularities, and update advertising generation models.

[0117] This invention is a system that automatically generates advertising creatives based on product characteristics and target information, and delivers them at the appropriate time and place. This invention is primarily implemented in a form in which three subjects—a server, a terminal, and a user—each handle their respective processing steps.

[0118] The user, acting as a marketing representative, uses a device (such as a PC or mobile device) to input product characteristics and target information into an input form. For example, they might enter the characteristics of a sports drink ("energy replenishment effect") and target information ("women in their 20s") and click the submit button.

[0119] The terminal sends the entered product characteristics and target information to the server. Specifically, the data is sent to the server as an HTTP request. Based on the entered information, the server collects additional data from external data sources such as weather information APIs and geographic information services. For example, it obtains "sunny" weather data from the weather information API, "urban" area attribute information from the geographic information service, the current time ("morning") from the system clock, and seasonal information ("summer").

[0120] The collected data is stored in a database by the server and also in a temporary data store for ad generation. The server generates ad creatives by inputting prompts into the AI ​​model based on this data. An example of a prompt would be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running."

[0121] The generated ad creatives are combined with the most suitable ad templates by the server to complete the final ad material. For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[0122] The completed ad creative is delivered to target users by a server based on specific time, weather, area, and season. For example, an ad might be delivered to a fitness app frequently used by women in their 20s in urban areas on a sunny summer morning.

[0123] The effectiveness data of delivered ads (click-through rate, conversion rate, viewing time, etc.) is collected in real time by the server and stored in a database. The server analyzes the collected effectiveness data and updates the ad generation model using machine learning algorithms. This ensures that more effective creatives are generated for subsequent ad creations.

[0124] Thus, the system of the present invention automatically generates advertising campaigns based on product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[0125] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0126] Step 1:

[0127] The user enters product characteristics (e.g., "energy boosting effect") and target information (e.g., "women in their 20s") into the input form on the terminal and clicks the "Submit" button. This sends the product characteristics and target information to the server. The input is product characteristics and target information, and the output is the HTTP request sent to the server.

[0128] Step 2:

[0129] The terminal sends product characteristics and target information entered by the user to the server. Specifically, this information is sent to the server in the form of an HTTP request. The input is an HTTP request containing product characteristics and target information, and the output is the information sent to the server.

[0130] Step 3:

[0131] The server receives product characteristics and target information transmitted from the terminal. Then, based on the collected information, it gathers supplementary data (e.g., weather information, area attributes, current time, seasonal information) from external data sources (e.g., weather API, geographic information service). In this step, the input is the information from the terminal, and the output is the collected supplementary data.

[0132] Step 4:

[0133] The server updates its internal database based on the collected data and stores all the data necessary for generating ad creatives in a temporary data store. The updated database is also used for the next ad generation. The input is the collected supplemental data, and the output is the updated database and the temporary data store.

[0134] Step 5:

[0135] The server retrieves the necessary data from the temporary data store and inputs prompt text into the generation AI model to generate ad creatives. For example, the prompt text might be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running." The input is data from the temporary data store and the prompt text, and the output is the generated ad creative.

[0136] Step 6:

[0137] The server selects the optimal ad template based on the ad creatives generated by the AI ​​model. For example, it might select a visual template that matches the theme "a woman in her 20s who enjoys running." The input is the generated ad creative, and the output is the selected ad template.

[0138] Step 7:

[0139] The server combines the selected template and generated creative to create the final advertising material. Specifically, it uses HTML, CSS, and video editing software to visually integrate the advertising creative. The input is the advertising creative and the advertising template, and the output is the final advertising material.

[0140] Step 8:

[0141] The server delivers generated ad materials to target users based on specific time, weather, area, and season. For example, using the delivery platform API, ads can be delivered to fitness apps frequently used by women in their 20s in urban areas on a sunny summer morning. The input is the ad material and delivery conditions, and the output is the delivery of ads to the target users.

[0142] Step 9:

[0143] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time). The collected data is stored in a database and used for analysis. The input is the advertisement effectiveness data, and the output is the stored effectiveness data.

[0144] Step 10:

[0145] The server analyzes the collected performance data and updates the ad generation model using machine learning algorithms. This results in the generation of even more effective ad creatives in the next ad generation cycle. The input is performance data, and the output is the updated ad generation model.

[0146] (Application Example 1)

[0147] 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."

[0148] Traditional advertising systems required marketing personnel to manually set up ad creatives and select the optimal timing and location for delivery, which was time-consuming and laborious. Furthermore, collecting and analyzing performance data was cumbersome, making it difficult to incorporate the findings into subsequent ad campaigns. Moreover, with the proliferation of smart devices, real-time ad display and location-based ad delivery are required, but traditional systems were unable to efficiently handle these requirements.

[0149] 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.

[0150] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives; means for updating the generation model for the next advertising creative based on the collected effectiveness data; means for collecting location information from smart devices and optimizing advertising delivery; and means for displaying advertising creatives in real time on smart devices. This streamlines a series of operations from automatic generation to delivery, effectiveness measurement, and updating the next model, enabling real-time, location-based advertising delivery.

[0151] "Product characteristics" refer to the various attributes and features of a product that is the target of sales promotion.

[0152] "Target information" refers to information about the target customer base or market segment that will be advertised.

[0153] "Advertising creative" refers to content such as images, videos, and text used in advertisements.

[0154] "Parameters" refer to the settings and conditions necessary for generating and distributing advertising content.

[0155] "Weather" refers to local weather conditions obtained through meteorological observations.

[0156] "Area" refers to the region or location where advertisements are delivered.

[0157] "Seasons" refer to the four periods of the year (spring, summer, autumn, and winter).

[0158] "Effectiveness data" refers to data regarding the impact and response that an advertisement had on the target audience.

[0159] A "machine learning algorithm" refers to an algorithm used to train a model with a large amount of data and perform predictions and optimizations.

[0160] "Model updating" refers to the process of adjusting and improving an ad generation model based on collected effectiveness data using machine learning algorithms.

[0161] A "smart device" refers to a portable device with advanced computing capabilities (such as a smartphone or smart glasses).

[0162] "Location information" refers to data about the device's current location.

[0163] "Real-time" refers to a situation where processing or responses occur instantly without delay.

[0164] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Specific embodiments are described below.

[0165] System Configuration

[0166] This system consists of the following main components:

[0167] 1. Input Interface

[0168] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system. This allows the marketing staff to manually provide the information.

[0169] 2. Data Acquisition Module

[0170] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0171] 3. Ad Creative Generation Module

[0172] The server selects an appropriate ad template based on the collected data and automatically generates ad creatives that reflect product characteristics and target attributes.

[0173] 4. Ad delivery module

[0174] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[0175] 5. Effectiveness Data Collection Module

[0176] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0177] 6. Learning Modules

[0178] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[0179] 7. Smart device integration module

[0180] The server collects location information from smart devices (smartphones and smart glasses) and optimizes ad delivery based on that information. It also displays ad creatives in real time on smart devices.

[0181] Hardware and software used

[0182] The following hardware and software will be used to implement this system.

[0183] Hardware: Smartphones, smart glasses, servers

[0184] Software: Python, TENSORFLOW®, Flask (for APIs), SQL (database)

[0185] Processing flow and specific examples

[0186] The system processes the information in the following steps.

[0187] 1. User input:

[0188] The marketing staff inputs "energy replenishment" as the product characteristic and "women in their 20s" as the target audience via a terminal.

[0189] 2. Data collection:

[0190] The server receives the entered product characteristics and target information, and collects current weather (e.g., sunny), location information (e.g., urban area), current time (e.g., morning), and season (e.g., summer) via an external API.

[0191] 3. Ad generation:

[0192] The server uses an AI model based on collected data to automatically generate advertising creatives that include scenes of a woman in her 20s enjoying running and drinking a sports drink.

[0193] 4. Ad delivery:

[0194] The server uses the location information of smart devices to deliver ads in real time within the target area. For example, it can deliver ads to fitness apps in urban areas on a sunny morning.

[0195] 5. Data collection on effectiveness:

[0196] The server collects real-time performance data from smart devices, including click-through rates, conversion rates, and viewing time for delivered advertisements.

[0197] 6. Learning and updating:

[0198] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model, thereby improving the accuracy of future ad generation.

[0199] Example prompt statements

[0200] As a concrete example, the following prompt statement can be used.

[0201] "The sports drink used in the advertisement has an energy-replenishing effect, and the target audience is women in their 20s. The weather is sunny, the area is urban, the time is currently morning, and the season is summer."

[0202] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0203] Processing steps

[0204] Step 1:

[0205] Users input product characteristics and target information through their devices. Specifically, marketing personnel use the input interface on their devices to provide the system with information such as "energy replenishment" and "women in their 20s."

[0206] Input: Product characteristics, target information

[0207] Output: Input product characteristics and target information

[0208] Step 2:

[0209] The server receives the entered product characteristics and target information and uses external APIs to collect real-time data (weather, area, time, season). For example, it obtains current weather data from a weather information API and attribute information for the target area from a geographic information service.

[0210] Input: Product characteristics, target information

[0211] Output: Weather data, area data, time data, seasonal data

[0212] Step 3:

[0213] The server automatically generates advertising creatives using an AI model based on the collected data. This involves selecting templates and combining data to create, for example, a scene of a woman in her 20s enjoying a run while drinking a sports drink.

[0214] Input: Product characteristics, target information, weather data, area data, time data, seasonal data

[0215] Output: Generated ad creative

[0216] Step 4:

[0217] The server delivers the generated ad creatives to the optimal locations based on specific time, weather, area, and season. For example, it might display ads in urban fitness apps on a sunny morning.

[0218] Input: Ad creative, weather data, area data, time data, seasonal data

[0219] Output: Where and when the ad was delivered.

[0220] Step 5:

[0221] The server collects real-time data on the effectiveness of delivered advertisements (click-through rates, conversion rates, viewing time, etc.). Specifically, it sends user interaction data from smart devices to the server.

[0222] Input: Where and when the ad was delivered

[0223] Output: Performance data (click-through rate, conversion rate, viewing time, etc.)

[0224] Step 6:

[0225] The server uses machine learning algorithms to update the ad generation model for the next campaign based on the collected performance data. During this process, it analyzes the performance data and incorporates newly discovered patterns and trends into the model.

[0226] Input: Effect data

[0227] Output: Updated ad generation model

[0228] Step 7:

[0229] The server collects location information from smart devices and optimizes ad delivery based on that information. For example, it uses location data from smart glasses to deliver ads to users in specific locations.

[0230] Input: Location information

[0231] Output: Optimized ad delivery strategy

[0232] Step 8:

[0233] The server displays ad creatives in real time on smart devices. It dynamically displays ads on smartphone and smart glasses displays, providing users with an effective advertising experience.

[0234] Input: Ad creative, location information

[0235] Output: Ad creative displayed on smart devices

[0236] The above outlines the specific processing steps based on application examples. Through the specific actions performed in each step and the resulting data processing and calculations, a sophisticated advertising delivery system can be realized.

[0237] 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.

[0238] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[0239] System Configuration

[0240] This system consists of the following main components:

[0241] 1. Input Interface

[0242] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[0243] This means that marketing personnel will manually provide the information.

[0244] 2. Data Acquisition Module

[0245] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0246] 3. Ad Creative Generation Module

[0247] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[0248] 4. Emotional Engine

[0249] The server is equipped with an emotion engine that analyzes user facial expressions and voice data to recognize user emotions. User emotion data is used for personalizing ad creatives and collecting effectiveness data.

[0250] 5. Ad delivery module

[0251] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. These delivery destinations include, for example, fitness apps and social media platforms.

[0252] 6. Effectiveness Data Collection Module

[0253] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine.

[0254] 7. Learning Modules

[0255] The server analyzes the collected effectiveness and sentiment data and uses machine learning algorithms to update the next ad generation model.

[0256] Specific example

[0257] scenario

[0258] Let's take the example of advertising a new sports drink to active women in their 20s.

[0259] 1. Input

[0260] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[0261] 2. Data Collection

[0262] The server receives product characteristics and target information, and collects current weather information (e.g., "sunny") via a weather information API, target area information (e.g., "urban area") from geographic information services, and the current time of day (e.g., "morning") and season (e.g., "summer") based on system time.

[0263] 3. Ad generation

[0264] The server selects an ad template suitable for a sunny morning and generates ad creatives based on the theme of "a woman in her 20s enjoying running." The content includes a scene of the woman in her 20s drinking a sports drink while running.

[0265] 4. Emotion recognition

[0266] The server analyzes the user's facial expressions and voice, and uses an emotion engine to recognize the user's emotions. For example, it can determine whether a user viewing an advertisement is expressing emotions such as "interesting" or "satisfied."

[0267] 5. Ad delivery

[0268] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[0269] 6. Collection of effectiveness data

[0270] The server collects effectiveness data such as click-through rates, conversion rates, and viewing time for delivered ads, and also collects user sentiment data using an emotion engine.

[0271] 7. Learning and updating

[0272] The server analyzes the collected effectiveness and sentiment data using machine learning algorithms and incorporates the findings into the next update of the ad generation model. For example, it might enhance elements that users found "interesting."

[0273] The system of this invention enables marketers to deploy advertising campaigns quickly and effectively, and to maximize advertising effectiveness using real-time feedback and user sentiment data.

[0274] The following describes the processing flow.

[0275] Step 1:

[0276] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[0277] Step 2:

[0278] The terminal sends product characteristics and target information entered by the user to the server. This allows the server to receive the necessary parameters.

[0279] Step 3:

[0280] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[0281] Step 4:

[0282] The server collects information on the target area via the geographic information service. The information obtained includes "urban areas" and the like.

[0283] Step 5:

[0284] The server identifies the current time zone based on the system time. In this case, for example, a time zone such as "morning" is specified.

[0285] Step 6:

[0286] The server obtains the current season data. For example, it collects season information such as "summer".

[0287] Step 7:

[0288] Based on all the parameters collected by the server, the server selects the optimal advertising template. For example, it selects a template that includes a "sunny day running scene".

[0289] Step 8:

[0290] The server automatically generates specific advertising creatives based on the product characteristics and target attributes. For example, it creates a scene of "a 20-year-old woman drinking a sports drink while running".

[0291] Step 9:

[0292] The server creates a preview of the generated advertising creative and provides it to the user through the terminal.

[0293] Step 10:

[0294] The user checks and approves the preview of the advertising creative on the terminal. The approval information is sent from the terminal to the server.

[0295] Step 11:

[0296] The server delivers the advertising creative at the optimal timing and location. The delivery destination is, for example, a "fitness app", and the delivery timing is "mid-morning on a sunny summer day".

[0297] Step 12:

[0298] Simultaneously with the delivery, the server activates the emotion engine and analyzes the user's facial expressions and voice data in real time. It identifies whether the user shows emotions such as being interested or satisfied.

[0299] Step 13:

[0300] The server collects the effectiveness data of the delivered advertisement. The effectiveness data includes click-through rate, conversion rate, viewing time, etc.

[0301] Step 14:

[0302] The server saves the user's emotion data collected by the emotion engine together with the effectiveness data. For example, it records the emotions (interested, satisfied, indifferent, etc.) shown by the user when viewing the advertisement.

[0303] Step 15:

[0304] The server analyzes the collected effectiveness data and emotion data using a machine learning algorithm and reflects it in the update of the next advertisement generation model. For example, it improves the model to particularly emphasize the elements that the user finds "interesting".

[0305] Step 16:

[0306] Based on the updated model, the server further optimizes the next advertising creative based on the newly collected parameters and emotion data, and prepares for automatic generation.

[0307] The above are the specific processing steps and the respective operation contents of the system combined with the emotion engine.

[0308] (Example 2)

[0309] 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".

[0310] Traditional advertising delivery systems could automatically generate ads based on product characteristics and target information, but they lacked sufficient personalization to maximize the effectiveness of the generated ads. Furthermore, when updating the ad creative generation model based on post-delivery performance data, user sentiment data was not effectively utilized. As a result, ad effectiveness was limited, making it difficult to optimize the performance of advertising campaigns.

[0311] 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.

[0312] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for analyzing user sentiment data using a generation AI model and personalizing the advertising creatives; means for collecting effectiveness data and user sentiment data of the delivered advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and sentiment data. This enables real-time optimization of advertising performance and personalization based on user sentiment.

[0313] "Product characteristics" refer to the features and attributes of the product or service being advertised.

[0314] "Target information" refers to data about a specific consumer group targeted for advertising purposes.

[0315] "Advertising creative" refers to the content, including the content and design of the advertisement.

[0316] "Parameters" refer to various pieces of information and settings that influence the generation of advertising creatives.

[0317] "Real-time data" refers to dynamic data acquired at a given moment, such as current weather, time, area, and season.

[0318] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate advertising creatives.

[0319] An "emotion engine" refers to a technology or system that analyzes a user's facial expressions and voice data to recognize their emotions.

[0320] "Effectiveness data" refers to data that shows the results of ad delivery (such as click-through rate, conversion rate, and viewing time).

[0321] A "machine learning algorithm" refers to a computational method used to train a model based on collected data and perform predictions and classifications.

[0322] "Personalization" refers to individually optimizing content and services according to the user's characteristics and circumstances.

[0323] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[0324] This system functions through terminals used by marketing personnel, servers, and terminals used by users to view advertisements. Hardware includes personal computers or smartphones used by marketing personnel, cloud servers or data center servers, and smartphones or tablets for users to view advertisements. Software includes generative AI models for generating ad creatives, an emotion engine for analyzing user sentiment, API call programs for leveraging external APIs, and machine learning algorithms for collecting and analyzing performance data.

[0325] Specific example

[0326] scenario

[0327] Let's take the example of advertising a new sports drink to active women in their 20s.

[0328] 1. Input

[0329] The user inputs information about the sports drink's characteristics (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device. Specifically, they log in to a dedicated marketing interface, fill in the product name, characteristics, and target information in a form, and click the submit button.

[0330] 2. Data Collection

[0331] The server receives product characteristics and target information, and collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time.

[0332] 3. Ad generation

[0333] The server uses a generative AI model to generate ad creatives based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running."

[0334] 4. Emotion recognition

[0335] The server analyzes facial and audio data collected from the user's device and uses an emotion engine to recognize the user's emotions. Specifically, it captures facial data using face recognition technology when users view advertisements and analyzes audio data using audio analysis technology. This allows it to identify emotions such as whether the user finds the advertisement interesting or satisfied.

[0336] 5. Ad delivery

[0337] The server delivers the generated ad creatives at the optimal time and location. Specifically, ads will be delivered to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. Delivery will be done in real time using the app's ad slots.

[0338] 6. Collection of effectiveness data

[0339] The server collects real-time data on the effectiveness of delivered advertisements. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. This clearly shows how interested users were in the advertisements.

[0340] 7. Learning and updating

[0341] The server analyzes the collected effectiveness and sentiment data to update the ad generation model for the next campaign. Specifically, it uses machine learning algorithms to train the collected data and improve the model's performance. For example, it adjusts the generation AI model to enhance elements that users find "interesting."

[0342] Example of a prompt

[0343] "Create a new sports drink advertisement targeting women in their 20s. The ad should include a scene of drinking the sports drink while running, emphasizing its energy-boosting effects."

[0344] This system allows marketers to deploy advertising campaigns quickly and effectively, maximizing advertising effectiveness using real-time feedback and user sentiment data.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The user inputs product characteristics and target information via their device. The user logs into the marketing interface, enters the product name, characteristics (e.g., "energy boosting effect"), and target information (e.g., "women in their 20s"), and clicks the submit button. The entered information is sent from the device to the server. The input data includes the product name, product characteristics, and target information. The output data is this information stored on the server.

[0348] Step 2:

[0349] The server collects real-time data from external APIs and internal databases based on the received product characteristics and target information. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time. The input data consists of product characteristics, target information, and data from external APIs, while the output data is real-time data that integrates this information.

[0350] Step 3:

[0351] The server generates ad creatives using a generative AI model based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running." The input data consists of product characteristics, target information, real-time data, and prompts for the generative AI model, while the output data is the generated ad creative.

[0352] Step 4:

[0353] The server analyzes facial and audio data collected from the user's device to recognize the user's emotions. Using an emotion engine, it captures facial data using face recognition technology and analyzes audio data using audio analysis technology. Specifically, it captures video of the user's face while they are viewing an advertisement and records their voice. The input data consists of the user's facial and audio data, and the output data is the analyzed emotion data of the user.

[0354] Step 5:

[0355] The server delivers the generated ad creatives at the optimal time and location. Specifically, it delivers ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. The app's ad slots are used for delivery. Input data includes the generated ad creatives, real-time data, and sentiment data, while output data is the delivered ad creatives.

[0356] Step 6:

[0357] The server collects real-time data on the effectiveness of delivered advertisements and user sentiment data. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. The input data consists of user response data and sentiment data to delivered advertisements, and the output data is the integrated effectiveness data.

[0358] Step 7:

[0359] The server updates the ad generation model for the next generation based on the collected effectiveness and sentiment data. Specifically, it uses machine learning algorithms to analyze the collected data, uses it as training data for the model, and improves the model's performance. The input data is integrated effectiveness and sentiment data, and the output data is the updated ad generation model.

[0360] (Application Example 2)

[0361] 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 device 14 will be referred to as the "terminal."

[0362] Existing ad delivery systems do not adequately personalize or optimize ad timing, making it difficult to generate and deliver ad creatives that take into account user emotions and real-time environmental data. Furthermore, feedback on ad effectiveness is not reflected in real time, making it difficult to utilize this feedback for future ad generation. As a result, resources are wasted without maximizing ad effectiveness.

[0363] 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. In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for displaying the generated advertising creatives during video playback; means for collecting effectiveness data of the delivered advertising creatives; means for analyzing the emotional data of users who view the collected advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and emotional data. This enables advertising personalization and delivery at the optimal timing, and maximizes advertising effectiveness by utilizing user emotional data as feedback.

[0364] "Product characteristics" refer to information that describes the attributes and features of a particular product.

[0365] "Target information" refers to information about the target customers to whom a particular advertisement should be directed.

[0366] "Advertising creative" is a general term for the content and design of advertisements created for marketing purposes.

[0367] "Parameters" refer to the variables and settings necessary for generating and delivering advertising creatives.

[0368] "Specific time" refers to the specific time or time slot selected for delivering advertisements.

[0369] "Weather" refers to the weather conditions at the time the advertisement is delivered.

[0370] "Area" refers to the geographical location or region where an advertisement is delivered.

[0371] "Seasons" refer to the cycle of spring, summer, autumn, and winter throughout the year.

[0372] "Optimal location" refers to the distribution destination selected to maximize the effectiveness of the advertisement.

[0373] "Distribution" refers to the act of publishing and distributing advertising creatives to selected locations and media.

[0374] "Effectiveness data" refers to data used to measure the results of delivered advertisements.

[0375] "Emotional data" refers to data that represents the emotional state of users viewing advertisements.

[0376] "Analysis" refers to the act of processing data and deriving information or insights from it.

[0377] "Update" refers to the act of improving or revising an existing ad generation model based on new information.

[0378] "Video playback" refers to the act of playing digital video content.

[0379] This invention is a system that generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, this system aims to collect effectiveness and sentiment data of delivered advertisements and update the generation model for the next set of advertising creatives.

[0380] Components

[0381] 1. Collection Module

[0382] The server collects the parameters necessary for generating advertising creatives based on the collected product characteristics and target information. This collection module has the ability to import real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0383] 2. Generated Module

[0384] The server automatically generates ad creatives based on the collected parameters. This generation process includes selecting ad templates and incorporating information entered by marketers.

[0385] 3. Distribution Module

[0386] The server delivers the generated ad creatives to the optimal location based on specific time, weather, area, and season. This delivery module has the capability to display ads to users while they are playing videos.

[0387] 4. Effectiveness Data Collection Module

[0388] The server collects performance data for delivered ad creatives (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine. This data is used to evaluate ad performance and improve the ad generation model for the next campaign.

[0389] 5. Emotion Recognition Module

[0390] The server analyzes the emotional data of users who view the ad creatives. Emotion recognition includes analyzing the user's facial expressions and voice.

[0391] 6. Update Module

[0392] The server updates the model for generating the next ad creative based on the collected effectiveness and sentiment data. Machine learning algorithms are used to improve the model.

[0393] Hardware and software

[0394] Hardware to use:

[0395] server

[0396] User terminals (smartphones, mobile devices, etc.)

[0397] Software to use:

[0398] Requests: Obtain real-time data from an external weather information API.

[0399] CV2: Computer Vision Library. Used to display advertisements.

[0400] EmotionEngine: An emotion recognition engine that analyzes user emotion data.

[0401] AdGenerator: Software for automatically generating ad creatives.

[0402] AdOptimizer: Software that optimizes ad models and reflects the changes in subsequent ad generation.

[0403] Specific example

[0404] For example, consider advertising a new sports drink targeted at women in their 20s. The marketing person inputs product characteristics (e.g., energy replenishment effect) and target information (e.g., women in their 20s) into the system via a terminal.

[0405] The server collects sunny weather information using a weather information API and obtains target area information from a geographic information service. Then, it selects an ad template suitable for a sunny morning and generates ad creative with the theme of "a woman in her 20s enjoying running." This ad is displayed to users of a video streaming app while they are playing a video.

[0406] While the ad is playing, the emotion engine analyzes the user's facial expressions and voice to collect user emotion data (e.g., interesting, satisfied). The server also collects effectiveness data such as ad click-through rates and viewing time, and uses machine learning algorithms to update the ad generation model for the next ad.

[0407] Example of a prompt

[0408] "We need personalized ads for a new sports drink aimed at women in their 20s, emphasizing its energy-boosting effects, including scenes of running. The content should be particularly suitable for a sunny morning."

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The user inputs product characteristics and target information via their device. This input data includes the characteristics of the product being advertised (e.g., energy boost effect) and the attributes of the target customer (e.g., women in their 20s). The server receives this input data and initializes the parameters necessary for generating the ad creative.

[0412] Step 2:

[0413] The server collects real-time data using external APIs. This includes weather information (e.g., sunny), time of day (e.g., morning), and area information (e.g., urban areas). Specifically, it uses the requests library to access the weather information API and retrieve weather data. Time information is obtained from the system's internal clock, and area information is obtained from geographic information services.

[0414] Step 3:

[0415] The server automatically generates ad creatives based on collected product characteristics, target information, and real-time data. Specifically, AdGenerator selects an appropriate ad template and passes the information entered by the marketing team as prompts to the generation AI model. This model generates personalized ad content. The output is an ad creative depicting a specific scenario (e.g., a woman in her 20s enjoying running).

[0416] Step 4:

[0417] The server displays the generated ad creative during video playback. It uses the CV2 library to overlay the ad on the video streaming app's playback screen. Specifically, it optimizes the ad display timing based on real-time data (e.g., morning). Users visually view this ad while the video is playing.

[0418] Step 5:

[0419] The server collects emotional data from users who view ad creatives. Specifically, EmotionEngine analyzes users' facial expressions and voice data to obtain emotional data such as interest and satisfaction. This data serves as an important indicator for evaluating ad performance. The output is the analyzed user emotional data.

[0420] Step 6:

[0421] The server collects performance data for delivered ad creatives. This data includes click-through rates, conversion rates, and viewing time. Specifically, AdOptimizer collects user behavior data and organizes it as performance data. The output is ad performance data.

[0422] Step 7:

[0423] The server updates the ad creative generation model for the next ad based on the collected effectiveness and sentiment data. It optimizes the ad generation model using machine learning algorithms and incorporates feedback information into the next ad generation. Specifically, AdOptimizer analyzes effectiveness and sentiment data and builds a new generative AI model. The output is the updated generative AI model.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Second Embodiment]

[0428] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the advertising generation model for the next campaign based on collected effectiveness data.

[0441] System Configuration

[0442] This system consists of the following main components:

[0443] 1. Input Interface

[0444] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[0445] This means that marketing personnel will manually provide the information.

[0446] 2. Data Acquisition Module

[0447] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0448] 3. Ad Creative Generation Module

[0449] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[0450] 4. Ad delivery module

[0451] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[0452] 5. Effectiveness Data Collection Module

[0453] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0454] 6. Learning Modules

[0455] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[0456] Specific example

[0457] scenario

[0458] Let's take the example of advertising a new sports drink to active women in their 20s.

[0459] 1. Input

[0460] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[0461] 2. Data Collection

[0462] The server receives product characteristics and target information, and collects the current weather ("sunny") via a weather information API, attribute information of the target area ("urban") from a geographic information service, the current time ("morning") based on the system time, and the season ("summer").

[0463] 3. Ad generation

[0464] The server selects an ad template suitable for a sunny morning and generates ad creatives themed around "women in their 20s enjoying running." For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[0465] 4. Ad delivery

[0466] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[0467] 5. Collection of effectiveness data

[0468] The server collects and analyzes effectiveness data such as click-through rates, conversion rates, and viewing time for delivered advertisements.

[0469] 6. Learning and updating

[0470] The server uses machine learning algorithms to update its model based on the collected performance data, thereby improving the accuracy of future ad creative generation.

[0471] As described above, the system of the present invention automatically generates effective advertising campaigns by utilizing product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[0475] Step 2:

[0476] The terminal sends the information entered by the user to the server. This allows the server to receive the necessary parameters.

[0477] Step 3:

[0478] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[0479] Step 4:

[0480] The server collects information about the target area via geographic information services. The information obtained includes "urban areas," etc.

[0481] Step 5:

[0482] The server identifies the current time zone based on the system time. In this case, for example, the time zone "morning" might be identified.

[0483] Step 6:

[0484] The server retrieves the current seasonal data. For example, it collects seasonal information such as "summer."

[0485] Step 7:

[0486] The server selects the optimal ad template based on all the collected parameters. For example, it might choose a template that includes a "running scene on a sunny day."

[0487] Step 8:

[0488] The server automatically generates specific ad creatives based on product characteristics and target attributes. For example, it might create a scene depicting "a woman in her 20s drinking a sports drink while running."

[0489] Step 9:

[0490] The server creates a preview of the generated ad creative and provides it to the user via the device.

[0491] Step 10:

[0492] The user reviews and approves the ad creative on their device. The approval information is sent from the device to the server.

[0493] Step 11:

[0494] The server delivers the ad creative at the optimal time and place. For example, the target audience might be a "fitness app," and the delivery time might be "a sunny summer morning."

[0495] Step 12:

[0496] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0497] Step 13:

[0498] The server analyzes the collected effectiveness data using machine learning algorithms. This identifies effective factors and areas for improvement.

[0499] Step 14:

[0500] The server updates its ad generation model using the results of machine learning. For example, it learns elements that further emphasize the "refreshing effect after running."

[0501] Step 15:

[0502] The server prepares to incorporate the updated model into the next ad generation. This will enable the automated generation of more effective ad creatives.

[0503] The above describes the specific processing steps of the program and the actions of each step.

[0504] (Example 1)

[0505] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0506] In today's advertising market, it's essential to generate ad creatives based on product characteristics and target information, and deliver them at the optimal time and place. However, doing this manually is extremely time-consuming and labor-intensive, and furthermore, to generate more effective ads, it's necessary to update the ad generation model to reflect past advertising performance data. Therefore, there is a need for a system that automates the ad generation process and maximizes advertising effectiveness based on collected data.

[0507] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0508] In this invention, the server includes means for a user to input product characteristics and target information via a terminal; means for transmitting the input product characteristics and target information to the server; means for collecting supplementary data from an external data source based on the transmitted information; means for updating a database based on the collected data; means for inputting prompt text into a generation AI model based on the updated data to generate advertising creatives; means for combining the generated advertising creatives with a selected advertising template; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives in real time; and means for analyzing the collected effectiveness data and updating the advertising generation model using a machine learning algorithm. This enables automatic generation of advertising creatives, delivery at the optimal timing, and model updates based on effectiveness data.

[0509] "Product characteristics" refer to the unique properties and features of a product, including its function, effect, and use.

[0510] "Target information" refers to information about a specific consumer group that is the target of marketing activities, and includes data such as age, gender, region, and interests.

[0511] "User" refers to the entity that inputs and manages information for generating advertising creatives using this system, and usually refers to a marketing professional.

[0512] A "terminal" refers to a device used to input information into or receive information from this system, and includes PCs and mobile devices.

[0513] A "server" refers to a computing system used to process information, manage databases, generate and distribute advertising creatives, and collect performance data.

[0514] "External data sources" refer to external information services that provide supplemental data required by this system, and include weather information APIs and geographic information services.

[0515] A "generative AI model" refers to an artificial intelligence model that generates advertising creatives from given prompt text.

[0516] A "prompt message" refers to a command or instruction given to the AI ​​model, which then generates appropriate advertising creatives.

[0517] An "ad template" refers to a format that has a structure and layout for creating advertising creatives.

[0518] "Advertising creative" refers to advertising materials generated by generative AI models, and includes visuals and text.

[0519] "Effectiveness data" refers to data related to the performance of delivered advertisements, and includes click-through rates, conversion rates, and viewing time.

[0520] A "machine learning algorithm" refers to a computational method used to analyze data, identify patterns and regularities, and update advertising generation models.

[0521] This invention is a system that automatically generates advertising creatives based on product characteristics and target information, and delivers them at the appropriate time and place. This invention is primarily implemented in a form in which three subjects—a server, a terminal, and a user—each handle their respective processing steps.

[0522] The user, acting as a marketing representative, uses a device (such as a PC or mobile device) to input product characteristics and target information into an input form. For example, they might enter the characteristics of a sports drink ("energy replenishment effect") and target information ("women in their 20s") and click the submit button.

[0523] The terminal sends the entered product characteristics and target information to the server. Specifically, the data is sent to the server as an HTTP request. Based on the entered information, the server collects additional data from external data sources such as weather information APIs and geographic information services. For example, it obtains "sunny" weather data from the weather information API, "urban" area attribute information from the geographic information service, the current time ("morning") from the system clock, and seasonal information ("summer").

[0524] The collected data is stored in a database by the server and also in a temporary data store for ad generation. The server generates ad creatives by inputting prompts into the AI ​​model based on this data. An example of a prompt would be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running."

[0525] The generated ad creatives are combined with the most suitable ad templates by the server to complete the final ad material. For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[0526] The completed ad creative is delivered to target users by a server based on specific time, weather, area, and season. For example, an ad might be delivered to a fitness app frequently used by women in their 20s in urban areas on a sunny summer morning.

[0527] The effectiveness data of delivered ads (click-through rate, conversion rate, viewing time, etc.) is collected in real time by the server and stored in a database. The server analyzes the collected effectiveness data and updates the ad generation model using machine learning algorithms. This ensures that more effective creatives are generated for subsequent ad creations.

[0528] Thus, the system of the present invention automatically generates advertising campaigns based on product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[0529] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0530] Step 1:

[0531] The user enters product characteristics (e.g., "energy boosting effect") and target information (e.g., "women in their 20s") into the input form on the terminal and clicks the "Submit" button. This sends the product characteristics and target information to the server. The input is product characteristics and target information, and the output is the HTTP request sent to the server.

[0532] Step 2:

[0533] The terminal sends product characteristics and target information entered by the user to the server. Specifically, this information is sent to the server in the form of an HTTP request. The input is an HTTP request containing product characteristics and target information, and the output is the information sent to the server.

[0534] Step 3:

[0535] The server receives product characteristics and target information transmitted from the terminal. Then, based on the collected information, it gathers supplementary data (e.g., weather information, area attributes, current time, seasonal information) from external data sources (e.g., weather API, geographic information service). In this step, the input is the information from the terminal, and the output is the collected supplementary data.

[0536] Step 4:

[0537] The server updates its internal database based on the collected data and stores all the data necessary for generating ad creatives in a temporary data store. The updated database is also used for the next ad generation. The input is the collected supplemental data, and the output is the updated database and the temporary data store.

[0538] Step 5:

[0539] The server retrieves the necessary data from the temporary data store and inputs prompt text into the generation AI model to generate ad creatives. For example, the prompt text might be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running." The input is data from the temporary data store and the prompt text, and the output is the generated ad creative.

[0540] Step 6:

[0541] The server selects the optimal ad template based on the ad creatives generated by the AI ​​model. For example, it might select a visual template that matches the theme "a woman in her 20s who enjoys running." The input is the generated ad creative, and the output is the selected ad template.

[0542] Step 7:

[0543] The server combines the selected template and generated creative to create the final advertising material. Specifically, it uses HTML, CSS, and video editing software to visually integrate the advertising creative. The input is the advertising creative and the advertising template, and the output is the final advertising material.

[0544] Step 8:

[0545] The server delivers generated ad materials to target users based on specific time, weather, area, and season. For example, using the delivery platform API, ads can be delivered to fitness apps frequently used by women in their 20s in urban areas on a sunny summer morning. The input is the ad material and delivery conditions, and the output is the delivery of ads to the target users.

[0546] Step 9:

[0547] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time). The collected data is stored in a database and used for analysis. The input is the advertisement effectiveness data, and the output is the stored effectiveness data.

[0548] Step 10:

[0549] The server analyzes the collected performance data and updates the ad generation model using machine learning algorithms. This results in the generation of even more effective ad creatives in the next ad generation cycle. The input is performance data, and the output is the updated ad generation model.

[0550] (Application Example 1)

[0551] 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."

[0552] Traditional advertising systems required marketing personnel to manually set up ad creatives and select the optimal timing and location for delivery, which was time-consuming and laborious. Furthermore, collecting and analyzing performance data was cumbersome, making it difficult to incorporate the findings into subsequent ad campaigns. Moreover, with the proliferation of smart devices, real-time ad display and location-based ad delivery are required, but traditional systems were unable to efficiently handle these requirements.

[0553] 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.

[0554] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives; means for updating the generation model for the next advertising creative based on the collected effectiveness data; means for collecting location information from smart devices and optimizing advertising delivery; and means for displaying advertising creatives in real time on smart devices. This streamlines a series of operations from automatic generation to delivery, effectiveness measurement, and updating the next model, enabling real-time, location-based advertising delivery.

[0555] "Product characteristics" refer to the various attributes and features of a product that is the target of sales promotion.

[0556] "Target information" refers to information about the target customer base or market segment that will be advertised.

[0557] "Advertising creative" refers to content such as images, videos, and text used in advertisements.

[0558] "Parameters" refer to the settings and conditions necessary for generating and distributing advertising content.

[0559] "Weather" refers to local weather conditions obtained through meteorological observations.

[0560] "Area" refers to the region or location where advertisements are delivered.

[0561] "Seasons" refer to the four periods of the year (spring, summer, autumn, and winter).

[0562] "Effectiveness data" refers to data regarding the impact and response that an advertisement had on the target audience.

[0563] A "machine learning algorithm" refers to an algorithm used to train a model with a large amount of data and perform predictions and optimizations.

[0564] "Model updating" refers to the process of adjusting and improving an ad generation model based on collected effectiveness data using machine learning algorithms.

[0565] A "smart device" refers to a portable device with advanced computing capabilities (such as a smartphone or smart glasses).

[0566] "Location information" refers to data about the device's current location.

[0567] "Real-time" refers to a situation where processing or responses occur instantly without delay.

[0568] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Specific embodiments are described below.

[0569] System Configuration

[0570] This system consists of the following main components:

[0571] 1. Input Interface

[0572] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system. This allows the marketing staff to manually provide the information.

[0573] 2. Data Acquisition Module

[0574] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0575] 3. Ad Creative Generation Module

[0576] The server selects an appropriate ad template based on the collected data and automatically generates ad creatives that reflect product characteristics and target attributes.

[0577] 4. Ad delivery module

[0578] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[0579] 5. Effectiveness Data Collection Module

[0580] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0581] 6. Learning Modules

[0582] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[0583] 7. Smart device integration module

[0584] The server collects location information from smart devices (smartphones and smart glasses) and optimizes ad delivery based on that information. It also displays ad creatives in real time on smart devices.

[0585] Hardware and software used

[0586] The following hardware and software will be used to implement this system.

[0587] Hardware: Smartphones, smart glasses, servers

[0588] Software: Python, TensorFlow, Flask (for APIs), SQL (database)

[0589] Processing flow and specific examples

[0590] The system processes the information in the following steps.

[0591] 1. User input:

[0592] The marketing staff inputs "energy replenishment" as the product characteristic and "women in their 20s" as the target audience via a terminal.

[0593] 2. Data collection:

[0594] The server receives the entered product characteristics and target information, and collects current weather (e.g., sunny), location information (e.g., urban area), current time (e.g., morning), and season (e.g., summer) via an external API.

[0595] 3. Ad generation:

[0596] The server uses an AI model based on collected data to automatically generate advertising creatives that include scenes of a woman in her 20s enjoying running and drinking a sports drink.

[0597] 4. Ad delivery:

[0598] The server uses the location information of smart devices to deliver ads in real time within the target area. For example, it can deliver ads to fitness apps in urban areas on a sunny morning.

[0599] 5. Data collection on effectiveness:

[0600] The server collects real-time performance data from smart devices, including click-through rates, conversion rates, and viewing time for delivered advertisements.

[0601] 6. Learning and updating:

[0602] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model, thereby improving the accuracy of future ad generation.

[0603] Example prompt statements

[0604] As a concrete example, the following prompt statement can be used.

[0605] "The sports drink used in the advertisement has an energy-replenishing effect, and the target audience is women in their 20s. The weather is sunny, the area is urban, the time is currently morning, and the season is summer."

[0606] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0607] Processing steps

[0608] Step 1:

[0609] Users input product characteristics and target information through their devices. Specifically, marketing personnel use the input interface on their devices to provide the system with information such as "energy replenishment" and "women in their 20s."

[0610] Input: Product characteristics, target information

[0611] Output: Input product characteristics and target information

[0612] Step 2:

[0613] The server receives the entered product characteristics and target information and uses external APIs to collect real-time data (weather, area, time, season). For example, it obtains current weather data from a weather information API and attribute information for the target area from a geographic information service.

[0614] Input: Product characteristics, target information

[0615] Output: Weather data, area data, time data, seasonal data

[0616] Step 3:

[0617] The server automatically generates advertising creatives using an AI model based on the collected data. This involves selecting templates and combining data to create, for example, a scene of a woman in her 20s enjoying a run while drinking a sports drink.

[0618] Input: Product characteristics, target information, weather data, area data, time data, seasonal data

[0619] Output: Generated ad creative

[0620] Step 4:

[0621] The server delivers the generated ad creatives to the optimal locations based on specific time, weather, area, and season. For example, it might display ads in urban fitness apps on a sunny morning.

[0622] Input: Ad creative, weather data, area data, time data, seasonal data

[0623] Output: Where and when the ad was delivered.

[0624] Step 5:

[0625] The server collects real-time data on the effectiveness of delivered advertisements (click-through rates, conversion rates, viewing time, etc.). Specifically, it sends user interaction data from smart devices to the server.

[0626] Input: Where and when the ad was delivered

[0627] Output: Performance data (click-through rate, conversion rate, viewing time, etc.)

[0628] Step 6:

[0629] The server uses machine learning algorithms to update the ad generation model for the next campaign based on the collected performance data. During this process, it analyzes the performance data and incorporates newly discovered patterns and trends into the model.

[0630] Input: Effect data

[0631] Output: Updated ad generation model

[0632] Step 7:

[0633] The server collects location information from smart devices and optimizes ad delivery based on that information. For example, it uses location data from smart glasses to deliver ads to users in specific locations.

[0634] Input: Location information

[0635] Output: Optimized ad delivery strategy

[0636] Step 8:

[0637] The server displays ad creatives in real time on smart devices. It dynamically displays ads on smartphone and smart glasses displays, providing users with an effective advertising experience.

[0638] Input: Ad creative, location information

[0639] Output: Ad creative displayed on smart devices

[0640] The above outlines the specific processing steps based on application examples. Through the specific actions performed in each step and the resulting data processing and calculations, a sophisticated advertising delivery system can be realized.

[0641] 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.

[0642] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[0643] System Configuration

[0644] This system consists of the following main components:

[0645] 1. Input Interface

[0646] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[0647] This means that marketing personnel will manually provide the information.

[0648] 2. Data Acquisition Module

[0649] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0650] 3. Ad Creative Generation Module

[0651] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[0652] 4. Emotional Engine

[0653] The server is equipped with an emotion engine that analyzes user facial expressions and voice data to recognize user emotions. User emotion data is used for personalizing ad creatives and collecting effectiveness data.

[0654] 5. Ad delivery module

[0655] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. These delivery destinations include, for example, fitness apps and social media platforms.

[0656] 6. Effectiveness Data Collection Module

[0657] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine.

[0658] 7. Learning Modules

[0659] The server analyzes the collected effectiveness and sentiment data and uses machine learning algorithms to update the next ad generation model.

[0660] Specific example

[0661] scenario

[0662] Let's take the example of advertising a new sports drink to active women in their 20s.

[0663] 1. Input

[0664] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[0665] 2. Data Collection

[0666] The server receives product characteristics and target information, and collects current weather information (e.g., "sunny") via a weather information API, target area information (e.g., "urban area") from geographic information services, and the current time of day (e.g., "morning") and season (e.g., "summer") based on system time.

[0667] 3. Ad generation

[0668] The server selects an ad template suitable for a sunny morning and generates ad creatives based on the theme of "a woman in her 20s enjoying running." The content includes a scene of the woman in her 20s drinking a sports drink while running.

[0669] 4. Emotion recognition

[0670] The server analyzes the user's facial expressions and voice, and uses an emotion engine to recognize the user's emotions. For example, it can determine whether a user viewing an advertisement is expressing emotions such as "interesting" or "satisfied."

[0671] 5. Ad delivery

[0672] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[0673] 6. Collection of effectiveness data

[0674] The server collects effectiveness data such as click-through rates, conversion rates, and viewing time for delivered ads, and also collects user sentiment data using an emotion engine.

[0675] 7. Learning and updating

[0676] The server analyzes the collected effectiveness and sentiment data using machine learning algorithms and incorporates the findings into the next update of the ad generation model. For example, it might enhance elements that users found "interesting."

[0677] The system of this invention enables marketers to deploy advertising campaigns quickly and effectively, and to maximize advertising effectiveness using real-time feedback and user sentiment data.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[0681] Step 2:

[0682] The terminal sends product characteristics and target information entered by the user to the server. This allows the server to receive the necessary parameters.

[0683] Step 3:

[0684] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[0685] Step 4:

[0686] The server collects information about the target area via geographic information services. The information obtained includes "urban areas," etc.

[0687] Step 5:

[0688] The server identifies the current time zone based on the system time. In this case, for example, the time zone "morning" might be identified.

[0689] Step 6:

[0690] The server retrieves the current seasonal data. For example, it collects seasonal information such as "summer."

[0691] Step 7:

[0692] The server selects the optimal ad template based on all the collected parameters. For example, it might choose a template that includes a "running scene on a sunny day."

[0693] Step 8:

[0694] The server automatically generates specific ad creatives based on product characteristics and target attributes. For example, it might create a scene depicting "a woman in her 20s drinking a sports drink while running."

[0695] Step 9:

[0696] The server creates a preview of the generated ad creative and provides it to the user via the device.

[0697] Step 10:

[0698] The user reviews and approves the ad creative on their device. The approval information is sent from the device to the server.

[0699] Step 11:

[0700] The server delivers the ad creative at the optimal time and place. For example, the target audience might be a "fitness app," and the delivery time might be "a sunny summer morning."

[0701] Step 12:

[0702] Simultaneously with streaming, the server activates an emotion engine to analyze the user's facial expressions and voice data in real time. It identifies whether the user is expressing emotions such as interest or satisfaction.

[0703] Step 13:

[0704] The server collects data on the effectiveness of the delivered advertisements. This data includes click-through rates, conversion rates, and viewing time.

[0705] Step 14:

[0706] The server stores user sentiment data collected by the sentiment engine along with effectiveness data. For example, it records the emotions a user expressed when viewing an advertisement (interested, satisfied, indifferent, etc.).

[0707] Step 15:

[0708] The server analyzes the collected effectiveness and sentiment data using machine learning algorithms and incorporates the findings into the next update of the ad generation model. For example, the model is improved to particularly highlight elements that users found "interesting."

[0709] Step 16:

[0710] Based on the updated model, the server further optimizes the next ad creative based on newly collected parameters and sentiment data, preparing it for automated generation.

[0711] The above describes the specific processing steps and their respective operations in a system that combines emotional engines.

[0712] (Example 2)

[0713] 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".

[0714] Traditional advertising delivery systems could automatically generate ads based on product characteristics and target information, but they lacked sufficient personalization to maximize the effectiveness of the generated ads. Furthermore, when updating the ad creative generation model based on post-delivery performance data, user sentiment data was not effectively utilized. As a result, ad effectiveness was limited, making it difficult to optimize the performance of advertising campaigns.

[0715] 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.

[0716] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for analyzing user sentiment data using a generation AI model and personalizing the advertising creatives; means for collecting effectiveness data and user sentiment data of the delivered advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and sentiment data. This enables real-time optimization of advertising performance and personalization based on user sentiment.

[0717] "Product characteristics" refer to the features and attributes of the product or service being advertised.

[0718] "Target information" refers to data about a specific consumer group targeted for advertising purposes.

[0719] "Advertising creative" refers to the content, including the content and design of the advertisement.

[0720] "Parameters" refer to various pieces of information and settings that influence the generation of advertising creatives.

[0721] "Real-time data" refers to dynamic data acquired at a given moment, such as current weather, time, area, and season.

[0722] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate advertising creatives.

[0723] An "emotion engine" refers to a technology or system that analyzes a user's facial expressions and voice data to recognize their emotions.

[0724] "Effectiveness data" refers to data that shows the results of ad delivery (such as click-through rate, conversion rate, and viewing time).

[0725] A "machine learning algorithm" refers to a computational method used to train a model based on collected data and perform predictions and classifications.

[0726] "Personalization" refers to individually optimizing content and services according to the user's characteristics and circumstances.

[0727] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[0728] This system functions through terminals used by marketing personnel, servers, and terminals used by users to view advertisements. Hardware includes personal computers or smartphones used by marketing personnel, cloud servers or data center servers, and smartphones or tablets for users to view advertisements. Software includes generative AI models for generating ad creatives, an emotion engine for analyzing user sentiment, API call programs for leveraging external APIs, and machine learning algorithms for collecting and analyzing performance data.

[0729] Specific example

[0730] scenario

[0731] Let's take the example of advertising a new sports drink to active women in their 20s.

[0732] 1. Input

[0733] The user inputs information about the sports drink's characteristics (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device. Specifically, they log in to a dedicated marketing interface, fill in the product name, characteristics, and target information in a form, and click the submit button.

[0734] 2. Data Collection

[0735] The server receives product characteristics and target information, and collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time.

[0736] 3. Ad generation

[0737] The server uses a generative AI model to generate ad creatives based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running."

[0738] 4. Emotion recognition

[0739] The server analyzes facial and audio data collected from the user's device and uses an emotion engine to recognize the user's emotions. Specifically, it captures facial data using face recognition technology when users view advertisements and analyzes audio data using audio analysis technology. This allows it to identify emotions such as whether the user finds the advertisement interesting or satisfied.

[0740] 5. Ad delivery

[0741] The server delivers the generated ad creatives at the optimal time and location. Specifically, ads will be delivered to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. Delivery will be done in real time using the app's ad slots.

[0742] 6. Collection of effectiveness data

[0743] The server collects real-time data on the effectiveness of delivered advertisements. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. This clearly shows how interested users were in the advertisements.

[0744] 7. Learning and updating

[0745] The server analyzes the collected effectiveness and sentiment data to update the ad generation model for the next campaign. Specifically, it uses machine learning algorithms to train the collected data and improve the model's performance. For example, it adjusts the generation AI model to enhance elements that users find "interesting."

[0746] Example of a prompt

[0747] "Create a new sports drink advertisement targeting women in their 20s. The ad should include a scene of drinking the sports drink while running, emphasizing its energy-boosting effects."

[0748] This system allows marketers to deploy advertising campaigns quickly and effectively, maximizing advertising effectiveness using real-time feedback and user sentiment data.

[0749] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0750] Step 1:

[0751] The user inputs product characteristics and target information via their device. The user logs into the marketing interface, enters the product name, characteristics (e.g., "energy boosting effect"), and target information (e.g., "women in their 20s"), and clicks the submit button. The entered information is sent from the device to the server. The input data includes the product name, product characteristics, and target information. The output data is this information stored on the server.

[0752] Step 2:

[0753] The server collects real-time data from external APIs and internal databases based on the received product characteristics and target information. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time. The input data consists of product characteristics, target information, and data from external APIs, while the output data is real-time data that integrates this information.

[0754] Step 3:

[0755] The server generates ad creatives using a generative AI model based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running." The input data consists of product characteristics, target information, real-time data, and prompts for the generative AI model, while the output data is the generated ad creative.

[0756] Step 4:

[0757] The server analyzes facial and audio data collected from the user's device to recognize the user's emotions. Using an emotion engine, it captures facial data using face recognition technology and analyzes audio data using audio analysis technology. Specifically, it captures video of the user's face while they are viewing an advertisement and records their voice. The input data consists of the user's facial and audio data, and the output data is the analyzed emotion data of the user.

[0758] Step 5:

[0759] The server delivers the generated ad creatives at the optimal time and location. Specifically, it delivers ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. The app's ad slots are used for delivery. Input data includes the generated ad creatives, real-time data, and sentiment data, while output data is the delivered ad creatives.

[0760] Step 6:

[0761] The server collects real-time data on the effectiveness of delivered advertisements and user sentiment data. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. The input data consists of user response data and sentiment data to delivered advertisements, and the output data is the integrated effectiveness data.

[0762] Step 7:

[0763] The server updates the ad generation model for the next generation based on the collected effectiveness and sentiment data. Specifically, it uses machine learning algorithms to analyze the collected data, uses it as training data for the model, and improves the model's performance. The input data is integrated effectiveness and sentiment data, and the output data is the updated ad generation model.

[0764] (Application Example 2)

[0765] 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."

[0766] Existing ad delivery systems do not adequately personalize or optimize ad timing, making it difficult to generate and deliver ad creatives that take into account user emotions and real-time environmental data. Furthermore, feedback on ad effectiveness is not reflected in real time, making it difficult to utilize this feedback for future ad generation. As a result, resources are wasted without maximizing ad effectiveness.

[0767] 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. In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for displaying the generated advertising creatives during video playback; means for collecting effectiveness data of the delivered advertising creatives; means for analyzing the emotional data of users who view the collected advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and emotional data. This enables advertising personalization and delivery at the optimal timing, and maximizes advertising effectiveness by utilizing user emotional data as feedback.

[0768] "Product characteristics" refer to information that describes the attributes and features of a particular product.

[0769] "Target information" refers to information about the target customers to whom a particular advertisement should be directed.

[0770] "Advertising creative" is a general term for the content and design of advertisements created for marketing purposes.

[0771] "Parameters" refer to the variables and settings necessary for generating and delivering advertising creatives.

[0772] "Specific time" refers to the specific time or time slot selected for delivering advertisements.

[0773] "Weather" refers to the weather conditions at the time the advertisement is delivered.

[0774] "Area" refers to the geographical location or region where an advertisement is delivered.

[0775] "Seasons" refer to the cycle of spring, summer, autumn, and winter throughout the year.

[0776] "Optimal location" refers to the distribution destination selected to maximize the effectiveness of the advertisement.

[0777] "Distribution" refers to the act of publishing and distributing advertising creatives to selected locations and media.

[0778] "Effectiveness data" refers to data used to measure the results of delivered advertisements.

[0779] "Emotional data" refers to data that represents the emotional state of users viewing advertisements.

[0780] "Analysis" refers to the act of processing data and deriving information or insights from it.

[0781] "Update" refers to the act of improving or revising an existing ad generation model based on new information.

[0782] "Video playback" refers to the act of playing digital video content.

[0783] This invention is a system that generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, this system aims to collect effectiveness and sentiment data of delivered advertisements and update the generation model for the next set of advertising creatives.

[0784] Components

[0785] 1. Collection Module

[0786] The server collects the parameters necessary for generating advertising creatives based on the collected product characteristics and target information. This collection module has the ability to import real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0787] 2. Generated Module

[0788] The server automatically generates ad creatives based on the collected parameters. This generation process includes selecting ad templates and incorporating information entered by marketers.

[0789] 3. Distribution Module

[0790] The server delivers the generated ad creatives to the optimal location based on specific time, weather, area, and season. This delivery module has the capability to display ads to users while they are playing videos.

[0791] 4. Effectiveness Data Collection Module

[0792] The server collects performance data for delivered ad creatives (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine. This data is used to evaluate ad performance and improve the ad generation model for the next campaign.

[0793] 5. Emotion Recognition Module

[0794] The server analyzes the emotional data of users who view the ad creatives. Emotion recognition includes analyzing the user's facial expressions and voice.

[0795] 6. Update Module

[0796] The server updates the model for generating the next ad creative based on the collected effectiveness and sentiment data. Machine learning algorithms are used to improve the model.

[0797] Hardware and software

[0798] Hardware to use:

[0799] server

[0800] User terminals (smartphones, mobile devices, etc.)

[0801] Software to use:

[0802] Requests: Obtain real-time data from an external weather information API.

[0803] CV2: Computer Vision Library. Used to display advertisements.

[0804] EmotionEngine: An emotion recognition engine that analyzes user emotion data.

[0805] AdGenerator: Software for automatically generating ad creatives.

[0806] AdOptimizer: Software that optimizes ad models and reflects the changes in subsequent ad generation.

[0807] Specific example

[0808] For example, consider advertising a new sports drink targeted at women in their 20s. The marketing person inputs product characteristics (e.g., energy replenishment effect) and target information (e.g., women in their 20s) into the system via a terminal.

[0809] The server collects sunny weather information using a weather information API and obtains target area information from a geographic information service. Then, it selects an ad template suitable for a sunny morning and generates ad creative with the theme of "a woman in her 20s enjoying running." This ad is displayed to users of a video streaming app while they are playing a video.

[0810] While the ad is playing, the emotion engine analyzes the user's facial expressions and voice to collect user emotion data (e.g., interesting, satisfied). The server also collects effectiveness data such as ad click-through rates and viewing time, and uses machine learning algorithms to update the ad generation model for the next ad.

[0811] Example of a prompt

[0812] "We need personalized ads for a new sports drink aimed at women in their 20s, emphasizing its energy-boosting effects, including scenes of running. The content should be particularly suitable for a sunny morning."

[0813] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0814] Step 1:

[0815] The user inputs product characteristics and target information via their device. This input data includes the characteristics of the product being advertised (e.g., energy boost effect) and the attributes of the target customer (e.g., women in their 20s). The server receives this input data and initializes the parameters necessary for generating the ad creative.

[0816] Step 2:

[0817] The server collects real-time data using external APIs. This includes weather information (e.g., sunny), time of day (e.g., morning), and area information (e.g., urban areas). Specifically, it uses the requests library to access the weather information API and retrieve weather data. Time information is obtained from the system's internal clock, and area information is obtained from geographic information services.

[0818] Step 3:

[0819] The server automatically generates ad creatives based on collected product characteristics, target information, and real-time data. Specifically, AdGenerator selects an appropriate ad template and passes the information entered by the marketing team as prompts to the generation AI model. This model generates personalized ad content. The output is an ad creative depicting a specific scenario (e.g., a woman in her 20s enjoying running).

[0820] Step 4:

[0821] The server displays the generated ad creative during video playback. It uses the CV2 library to overlay the ad on the video streaming app's playback screen. Specifically, it optimizes the ad display timing based on real-time data (e.g., morning). Users visually view this ad while the video is playing.

[0822] Step 5:

[0823] The server collects emotional data from users who view ad creatives. Specifically, EmotionEngine analyzes users' facial expressions and voice data to obtain emotional data such as interest and satisfaction. This data serves as an important indicator for evaluating ad performance. The output is the analyzed user emotional data.

[0824] Step 6:

[0825] The server collects performance data for delivered ad creatives. This data includes click-through rates, conversion rates, and viewing time. Specifically, AdOptimizer collects user behavior data and organizes it as performance data. The output is ad performance data.

[0826] Step 7:

[0827] The server updates the ad creative generation model for the next ad based on the collected effectiveness and sentiment data. It optimizes the ad generation model using machine learning algorithms and incorporates feedback information into the next ad generation. Specifically, AdOptimizer analyzes effectiveness and sentiment data and builds a new generative AI model. The output is the updated generative AI model.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] [Third Embodiment]

[0832] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0833] 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.

[0834] 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).

[0835] 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.

[0836] 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.

[0837] 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).

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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".

[0844] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the advertising generation model for the next campaign based on collected effectiveness data.

[0845] System Configuration

[0846] This system consists of the following main components:

[0847] 1. Input Interface

[0848] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[0849] This means that marketing personnel will manually provide the information.

[0850] 2. Data Acquisition Module

[0851] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0852] 3. Ad Creative Generation Module

[0853] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[0854] 4. Ad delivery module

[0855] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[0856] 5. Effectiveness Data Collection Module

[0857] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0858] 6. Learning Modules

[0859] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[0860] Specific example

[0861] scenario

[0862] Let's take the example of advertising a new sports drink to active women in their 20s.

[0863] 1. Input

[0864] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[0865] 2. Data Collection

[0866] The server receives product characteristics and target information, and collects the current weather ("sunny") via a weather information API, attribute information of the target area ("urban") from a geographic information service, the current time ("morning") based on the system time, and the season ("summer").

[0867] 3. Ad generation

[0868] The server selects an ad template suitable for a sunny morning and generates ad creatives themed around "women in their 20s enjoying running." For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[0869] 4. Ad delivery

[0870] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[0871] 5. Collection of effectiveness data

[0872] The server collects and analyzes effectiveness data such as click-through rates, conversion rates, and viewing time for delivered advertisements.

[0873] 6. Learning and updating

[0874] The server uses machine learning algorithms to update its model based on the collected performance data, thereby improving the accuracy of future ad creative generation.

[0875] As described above, the system of the present invention automatically generates effective advertising campaigns by utilizing product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[0876] The following describes the processing flow.

[0877] Step 1:

[0878] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[0879] Step 2:

[0880] The terminal sends the information entered by the user to the server. This allows the server to receive the necessary parameters.

[0881] Step 3:

[0882] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[0883] Step 4:

[0884] The server collects information about the target area via geographic information services. The information obtained includes "urban areas," etc.

[0885] Step 5:

[0886] The server identifies the current time zone based on the system time. In this case, for example, the time zone "morning" might be identified.

[0887] Step 6:

[0888] The server retrieves the current seasonal data. For example, it collects seasonal information such as "summer."

[0889] Step 7:

[0890] The server selects the optimal ad template based on all the collected parameters. For example, it might choose a template that includes a "running scene on a sunny day."

[0891] Step 8:

[0892] The server automatically generates specific ad creatives based on product characteristics and target attributes. For example, it might create a scene depicting "a woman in her 20s drinking a sports drink while running."

[0893] Step 9:

[0894] The server creates a preview of the generated ad creative and provides it to the user via the device.

[0895] Step 10:

[0896] The user reviews and approves the ad creative on their device. The approval information is sent from the device to the server.

[0897] Step 11:

[0898] The server delivers the ad creative at the optimal time and place. For example, the target audience might be a "fitness app," and the delivery time might be "a sunny summer morning."

[0899] Step 12:

[0900] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0901] Step 13:

[0902] The server analyzes the collected effectiveness data using machine learning algorithms. This identifies effective factors and areas for improvement.

[0903] Step 14:

[0904] The server updates its ad generation model using the results of machine learning. For example, it learns elements that further emphasize the "refreshing effect after running."

[0905] Step 15:

[0906] The server prepares to incorporate the updated model into the next ad generation. This will enable the automated generation of more effective ad creatives.

[0907] The above describes the specific processing steps of the program and the actions of each step.

[0908] (Example 1)

[0909] 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."

[0910] In today's advertising market, it's essential to generate ad creatives based on product characteristics and target information, and deliver them at the optimal time and place. However, doing this manually is extremely time-consuming and labor-intensive, and furthermore, to generate more effective ads, it's necessary to update the ad generation model to reflect past advertising performance data. Therefore, there is a need for a system that automates the ad generation process and maximizes advertising effectiveness based on collected data.

[0911] 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.

[0912] In this invention, the server includes means for a user to input product characteristics and target information via a terminal; means for transmitting the input product characteristics and target information to the server; means for collecting supplementary data from an external data source based on the transmitted information; means for updating a database based on the collected data; means for inputting prompt text into a generation AI model based on the updated data to generate advertising creatives; means for combining the generated advertising creatives with a selected advertising template; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives in real time; and means for analyzing the collected effectiveness data and updating the advertising generation model using a machine learning algorithm. This enables automatic generation of advertising creatives, delivery at the optimal timing, and model updates based on effectiveness data.

[0913] "Product characteristics" refer to the unique properties and features of a product, including its function, effect, and use.

[0914] "Target information" refers to information about a specific consumer group that is the target of marketing activities, and includes data such as age, gender, region, and interests.

[0915] "User" refers to the entity that inputs and manages information for generating advertising creatives using this system, and usually refers to a marketing professional.

[0916] A "terminal" refers to a device used to input information into or receive information from this system, and includes PCs and mobile devices.

[0917] A "server" refers to a computing system used to process information, manage databases, generate and distribute advertising creatives, and collect performance data.

[0918] "External data sources" refer to external information services that provide supplemental data required by this system, and include weather information APIs and geographic information services.

[0919] A "generative AI model" refers to an artificial intelligence model that generates advertising creatives from given prompt text.

[0920] A "prompt message" refers to a command or instruction given to the AI ​​model, which then generates appropriate advertising creatives.

[0921] An "ad template" refers to a format that has a structure and layout for creating advertising creatives.

[0922] "Advertising creative" refers to advertising materials generated by generative AI models, and includes visuals and text.

[0923] "Effectiveness data" refers to data related to the performance of delivered advertisements, and includes click-through rates, conversion rates, and viewing time.

[0924] A "machine learning algorithm" refers to a computational method used to analyze data, identify patterns and regularities, and update advertising generation models.

[0925] This invention is a system that automatically generates advertising creatives based on product characteristics and target information, and delivers them at the appropriate time and place. This invention is primarily implemented in a form in which three subjects—a server, a terminal, and a user—each handle their respective processing steps.

[0926] The user, acting as a marketing representative, uses a device (such as a PC or mobile device) to input product characteristics and target information into an input form. For example, they might enter the characteristics of a sports drink ("energy replenishment effect") and target information ("women in their 20s") and click the submit button.

[0927] The terminal sends the entered product characteristics and target information to the server. Specifically, the data is sent to the server as an HTTP request. Based on the entered information, the server collects additional data from external data sources such as weather information APIs and geographic information services. For example, it obtains "sunny" weather data from the weather information API, "urban" area attribute information from the geographic information service, the current time ("morning") from the system clock, and seasonal information ("summer").

[0928] The collected data is stored in a database by the server and also in a temporary data store for ad generation. The server generates ad creatives by inputting prompts into the AI ​​model based on this data. An example of a prompt would be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running."

[0929] The generated ad creatives are combined with the most suitable ad templates by the server to complete the final ad material. For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[0930] The completed ad creative is delivered to target users by a server based on specific time, weather, area, and season. For example, an ad might be delivered to a fitness app frequently used by women in their 20s in urban areas on a sunny summer morning.

[0931] The effectiveness data of delivered ads (click-through rate, conversion rate, viewing time, etc.) is collected in real time by the server and stored in a database. The server analyzes the collected effectiveness data and updates the ad generation model using machine learning algorithms. This ensures that more effective creatives are generated for subsequent ad creations.

[0932] Thus, the system of the present invention automatically generates advertising campaigns based on product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[0933] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0934] Step 1:

[0935] The user enters product characteristics (e.g., "energy boosting effect") and target information (e.g., "women in their 20s") into the input form on the terminal and clicks the "Submit" button. This sends the product characteristics and target information to the server. The input is product characteristics and target information, and the output is the HTTP request sent to the server.

[0936] Step 2:

[0937] The terminal sends product characteristics and target information entered by the user to the server. Specifically, this information is sent to the server in the form of an HTTP request. The input is an HTTP request containing product characteristics and target information, and the output is the information sent to the server.

[0938] Step 3:

[0939] The server receives product characteristics and target information transmitted from the terminal. Then, based on the collected information, it gathers supplementary data (e.g., weather information, area attributes, current time, seasonal information) from external data sources (e.g., weather API, geographic information service). In this step, the input is the information from the terminal, and the output is the collected supplementary data.

[0940] Step 4:

[0941] The server updates its internal database based on the collected data and stores all the data necessary for generating ad creatives in a temporary data store. The updated database is also used for the next ad generation. The input is the collected supplemental data, and the output is the updated database and the temporary data store.

[0942] Step 5:

[0943] The server retrieves the necessary data from the temporary data store and inputs prompt text into the generation AI model to generate ad creatives. For example, the prompt text might be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running." The input is data from the temporary data store and the prompt text, and the output is the generated ad creative.

[0944] Step 6:

[0945] The server selects the optimal ad template based on the ad creatives generated by the AI ​​model. For example, it might select a visual template that matches the theme "a woman in her 20s who enjoys running." The input is the generated ad creative, and the output is the selected ad template.

[0946] Step 7:

[0947] The server combines the selected template and generated creative to create the final advertising material. Specifically, it uses HTML, CSS, and video editing software to visually integrate the advertising creative. The input is the advertising creative and the advertising template, and the output is the final advertising material.

[0948] Step 8:

[0949] The server delivers generated ad materials to target users based on specific time, weather, area, and season. For example, using the delivery platform API, ads can be delivered to fitness apps frequently used by women in their 20s in urban areas on a sunny summer morning. The input is the ad material and delivery conditions, and the output is the delivery of ads to the target users.

[0950] Step 9:

[0951] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time). The collected data is stored in a database and used for analysis. The input is the advertisement effectiveness data, and the output is the stored effectiveness data.

[0952] Step 10:

[0953] The server analyzes the collected performance data and updates the ad generation model using machine learning algorithms. This results in the generation of even more effective ad creatives in the next ad generation cycle. The input is performance data, and the output is the updated ad generation model.

[0954] (Application Example 1)

[0955] 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."

[0956] Traditional advertising systems required marketing personnel to manually set up ad creatives and select the optimal timing and location for delivery, which was time-consuming and laborious. Furthermore, collecting and analyzing performance data was cumbersome, making it difficult to incorporate the findings into subsequent ad campaigns. Moreover, with the proliferation of smart devices, real-time ad display and location-based ad delivery are required, but traditional systems were unable to efficiently handle these requirements.

[0957] 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.

[0958] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives; means for updating the generation model for the next advertising creative based on the collected effectiveness data; means for collecting location information from smart devices and optimizing advertising delivery; and means for displaying advertising creatives in real time on smart devices. This streamlines a series of operations from automatic generation to delivery, effectiveness measurement, and updating the next model, enabling real-time, location-based advertising delivery.

[0959] "Product characteristics" refer to the various attributes and features of a product that is the target of sales promotion.

[0960] "Target information" refers to information about the target customer base or market segment that will be advertised.

[0961] "Advertising creative" refers to content such as images, videos, and text used in advertisements.

[0962] "Parameters" refer to the settings and conditions necessary for generating and distributing advertising content.

[0963] "Weather" refers to local weather conditions obtained through meteorological observations.

[0964] "Area" refers to the region or location where advertisements are delivered.

[0965] "Seasons" refer to the four periods of the year (spring, summer, autumn, and winter).

[0966] "Effectiveness data" refers to data regarding the impact and response that an advertisement had on the target audience.

[0967] A "machine learning algorithm" refers to an algorithm used to train a model with a large amount of data and perform predictions and optimizations.

[0968] "Model updating" refers to the process of adjusting and improving an ad generation model based on collected effectiveness data using machine learning algorithms.

[0969] A "smart device" refers to a portable device with advanced computing capabilities (such as a smartphone or smart glasses).

[0970] "Location information" refers to data about the device's current location.

[0971] "Real-time" refers to a situation where processing or responses occur instantly without delay.

[0972] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Specific embodiments are described below.

[0973] System Configuration

[0974] This system consists of the following main components:

[0975] 1. Input Interface

[0976] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system. This allows the marketing staff to manually provide the information.

[0977] 2. Data Acquisition Module

[0978] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[0979] 3. Ad Creative Generation Module

[0980] The server selects an appropriate ad template based on the collected data and automatically generates ad creatives that reflect product characteristics and target attributes.

[0981] 4. Ad delivery module

[0982] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[0983] 5. Effectiveness Data Collection Module

[0984] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[0985] 6. Learning Modules

[0986] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[0987] 7. Smart device integration module

[0988] The server collects location information from smart devices (smartphones and smart glasses) and optimizes ad delivery based on that information. It also displays ad creatives in real time on smart devices.

[0989] Hardware and software used

[0990] The following hardware and software will be used to implement this system.

[0991] Hardware: Smartphones, smart glasses, servers

[0992] Software: Python, TensorFlow, Flask (for APIs), SQL (database)

[0993] Processing flow and specific examples

[0994] The system processes the information in the following steps.

[0995] 1. User input:

[0996] The marketing staff inputs "energy replenishment" as the product characteristic and "women in their 20s" as the target audience via a terminal.

[0997] 2. Data collection:

[0998] The server receives the entered product characteristics and target information, and collects current weather (e.g., sunny), location information (e.g., urban area), current time (e.g., morning), and season (e.g., summer) via an external API.

[0999] 3. Ad generation:

[1000] The server uses an AI model based on collected data to automatically generate advertising creatives that include scenes of a woman in her 20s enjoying running and drinking a sports drink.

[1001] 4. Ad delivery:

[1002] The server uses the location information of smart devices to deliver ads in real time within the target area. For example, it can deliver ads to fitness apps in urban areas on a sunny morning.

[1003] 5. Data collection on effectiveness:

[1004] The server collects real-time performance data from smart devices, including click-through rates, conversion rates, and viewing time for delivered advertisements.

[1005] 6. Learning and updating:

[1006] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model, thereby improving the accuracy of future ad generation.

[1007] Example prompt statements

[1008] As a concrete example, the following prompt statement can be used.

[1009] "The sports drink used in the advertisement has an energy-replenishing effect, and the target audience is women in their 20s. The weather is sunny, the area is urban, the time is currently morning, and the season is summer."

[1010] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1011] Processing steps

[1012] Step 1:

[1013] Users input product characteristics and target information through their devices. Specifically, marketing personnel use the input interface on their devices to provide the system with information such as "energy replenishment" and "women in their 20s."

[1014] Input: Product characteristics, target information

[1015] Output: Input product characteristics and target information

[1016] Step 2:

[1017] The server receives the entered product characteristics and target information and uses external APIs to collect real-time data (weather, area, time, season). For example, it obtains current weather data from a weather information API and attribute information for the target area from a geographic information service.

[1018] Input: Product characteristics, target information

[1019] Output: Weather data, area data, time data, seasonal data

[1020] Step 3:

[1021] The server automatically generates advertising creatives using an AI model based on the collected data. This involves selecting templates and combining data to create, for example, a scene of a woman in her 20s enjoying a run while drinking a sports drink.

[1022] Input: Product characteristics, target information, weather data, area data, time data, seasonal data

[1023] Output: Generated ad creative

[1024] Step 4:

[1025] The server delivers the generated ad creatives to the optimal locations based on specific time, weather, area, and season. For example, it might display ads in urban fitness apps on a sunny morning.

[1026] Input: Ad creative, weather data, area data, time data, seasonal data

[1027] Output: Where and when the ad was delivered.

[1028] Step 5:

[1029] The server collects real-time data on the effectiveness of delivered advertisements (click-through rates, conversion rates, viewing time, etc.). Specifically, it sends user interaction data from smart devices to the server.

[1030] Input: Where and when the ad was delivered

[1031] Output: Performance data (click-through rate, conversion rate, viewing time, etc.)

[1032] Step 6:

[1033] The server uses machine learning algorithms to update the ad generation model for the next campaign based on the collected performance data. During this process, it analyzes the performance data and incorporates newly discovered patterns and trends into the model.

[1034] Input: Effect data

[1035] Output: Updated ad generation model

[1036] Step 7:

[1037] The server collects location information from smart devices and optimizes ad delivery based on that information. For example, it uses location data from smart glasses to deliver ads to users in specific locations.

[1038] Input: Location information

[1039] Output: Optimized ad delivery strategy

[1040] Step 8:

[1041] The server displays ad creatives in real time on smart devices. It dynamically displays ads on smartphone and smart glasses displays, providing users with an effective advertising experience.

[1042] Input: Ad creative, location information

[1043] Output: Ad creative displayed on smart devices

[1044] The above outlines the specific processing steps based on application examples. Through the specific actions performed in each step and the resulting data processing and calculations, a sophisticated advertising delivery system can be realized.

[1045] 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.

[1046] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[1047] System Configuration

[1048] This system consists of the following main components:

[1049] 1. Input Interface

[1050] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[1051] This means that marketing personnel will manually provide the information.

[1052] 2. Data Acquisition Module

[1053] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[1054] 3. Ad Creative Generation Module

[1055] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[1056] 4. Emotional Engine

[1057] The server is equipped with an emotion engine that analyzes user facial expressions and voice data to recognize user emotions. User emotion data is used for personalizing ad creatives and collecting effectiveness data.

[1058] 5. Ad delivery module

[1059] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. These delivery destinations include, for example, fitness apps and social media platforms.

[1060] 6. Effectiveness Data Collection Module

[1061] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine.

[1062] 7. Learning Modules

[1063] The server analyzes the collected effectiveness and sentiment data and uses machine learning algorithms to update the next ad generation model.

[1064] Specific example

[1065] scenario

[1066] Let's take the example of advertising a new sports drink to active women in their 20s.

[1067] 1. Input

[1068] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[1069] 2. Data Collection

[1070] The server receives product characteristics and target information, and collects current weather information (e.g., "sunny") via a weather information API, target area information (e.g., "urban area") from geographic information services, and the current time of day (e.g., "morning") and season (e.g., "summer") based on system time.

[1071] 3. Ad generation

[1072] The server selects an ad template suitable for a sunny morning and generates ad creatives based on the theme of "a woman in her 20s enjoying running." The content includes a scene of the woman in her 20s drinking a sports drink while running.

[1073] 4. Emotion recognition

[1074] The server analyzes the user's facial expressions and voice, and uses an emotion engine to recognize the user's emotions. For example, it can determine whether a user viewing an advertisement is expressing emotions such as "interesting" or "satisfied."

[1075] 5. Ad delivery

[1076] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[1077] 6. Collection of effectiveness data

[1078] The server collects effectiveness data such as click-through rates, conversion rates, and viewing time for delivered ads, and also collects user sentiment data using an emotion engine.

[1079] 7. Learning and updating

[1080] The server analyzes the collected effectiveness and sentiment data using machine learning algorithms and incorporates the findings into the next update of the ad generation model. For example, it might enhance elements that users found "interesting."

[1081] The system of this invention enables marketers to deploy advertising campaigns quickly and effectively, and to maximize advertising effectiveness using real-time feedback and user sentiment data.

[1082] The following describes the processing flow.

[1083] Step 1:

[1084] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[1085] Step 2:

[1086] The terminal sends product characteristics and target information entered by the user to the server. This allows the server to receive the necessary parameters.

[1087] Step 3:

[1088] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[1089] Step 4:

[1090] The server collects information about the target area via geographic information services. The information obtained includes "urban areas," etc.

[1091] Step 5:

[1092] The server identifies the current time zone based on the system time. In this case, for example, the time zone "morning" might be identified.

[1093] Step 6:

[1094] The server retrieves the current seasonal data. For example, it collects seasonal information such as "summer."

[1095] Step 7:

[1096] The server selects the optimal ad template based on all the collected parameters. For example, it might choose a template that includes a "running scene on a sunny day."

[1097] Step 8:

[1098] The server automatically generates specific ad creatives based on product characteristics and target attributes. For example, it might create a scene depicting "a woman in her 20s drinking a sports drink while running."

[1099] Step 9:

[1100] The server creates a preview of the generated ad creative and provides it to the user via the device.

[1101] Step 10:

[1102] The user reviews and approves the ad creative on their device. The approval information is sent from the device to the server.

[1103] Step 11:

[1104] The server delivers the ad creative at the optimal time and place. For example, the target audience might be a "fitness app," and the delivery time might be "a sunny summer morning."

[1105] Step 12:

[1106] Simultaneously with streaming, the server activates an emotion engine to analyze the user's facial expressions and voice data in real time. It identifies whether the user is expressing emotions such as interest or satisfaction.

[1107] Step 13:

[1108] The server collects data on the effectiveness of the delivered advertisements. This data includes click-through rates, conversion rates, and viewing time.

[1109] Step 14:

[1110] The server stores user sentiment data collected by the sentiment engine along with effectiveness data. For example, it records the emotions a user expressed when viewing an advertisement (interested, satisfied, indifferent, etc.).

[1111] Step 15:

[1112] The server analyzes the collected effectiveness and sentiment data using machine learning algorithms and incorporates the findings into the next update of the ad generation model. For example, the model is improved to particularly highlight elements that users found "interesting."

[1113] Step 16:

[1114] Based on the updated model, the server further optimizes the next ad creative based on newly collected parameters and sentiment data, preparing it for automated generation.

[1115] The above describes the specific processing steps and their respective operations in a system that combines emotional engines.

[1116] (Example 2)

[1117] 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."

[1118] Traditional advertising delivery systems could automatically generate ads based on product characteristics and target information, but they lacked sufficient personalization to maximize the effectiveness of the generated ads. Furthermore, when updating the ad creative generation model based on post-delivery performance data, user sentiment data was not effectively utilized. As a result, ad effectiveness was limited, making it difficult to optimize the performance of advertising campaigns.

[1119] 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.

[1120] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for analyzing user sentiment data using a generation AI model and personalizing the advertising creatives; means for collecting effectiveness data and user sentiment data of the delivered advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and sentiment data. This enables real-time optimization of advertising performance and personalization based on user sentiment.

[1121] "Product characteristics" refer to the features and attributes of the product or service being advertised.

[1122] "Target information" refers to data about a specific consumer group targeted for advertising purposes.

[1123] "Advertising creative" refers to the content, including the content and design of the advertisement.

[1124] "Parameters" refer to various pieces of information and settings that influence the generation of advertising creatives.

[1125] "Real-time data" refers to dynamic data acquired at a given moment, such as current weather, time, area, and season.

[1126] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate advertising creatives.

[1127] An "emotion engine" refers to a technology or system that analyzes a user's facial expressions and voice data to recognize their emotions.

[1128] "Effectiveness data" refers to data that shows the results of ad delivery (such as click-through rate, conversion rate, and viewing time).

[1129] A "machine learning algorithm" refers to a computational method used to train a model based on collected data and perform predictions and classifications.

[1130] "Personalization" refers to individually optimizing content and services according to the user's characteristics and circumstances.

[1131] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[1132] This system functions through terminals used by marketing personnel, servers, and terminals used by users to view advertisements. Hardware includes personal computers or smartphones used by marketing personnel, cloud servers or data center servers, and smartphones or tablets for users to view advertisements. Software includes generative AI models for generating ad creatives, an emotion engine for analyzing user sentiment, API call programs for leveraging external APIs, and machine learning algorithms for collecting and analyzing performance data.

[1133] Specific example

[1134] scenario

[1135] Let's take the example of advertising a new sports drink to active women in their 20s.

[1136] 1. Input

[1137] The user inputs information about the sports drink's characteristics (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device. Specifically, they log in to a dedicated marketing interface, fill in the product name, characteristics, and target information in a form, and click the submit button.

[1138] 2. Data Collection

[1139] The server receives product characteristics and target information, and collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time.

[1140] 3. Ad generation

[1141] The server uses a generative AI model to generate ad creatives based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running."

[1142] 4. Emotion recognition

[1143] The server analyzes facial and audio data collected from the user's device and uses an emotion engine to recognize the user's emotions. Specifically, it captures facial data using face recognition technology when users view advertisements and analyzes audio data using audio analysis technology. This allows it to identify emotions such as whether the user finds the advertisement interesting or satisfied.

[1144] 5. Ad delivery

[1145] The server delivers the generated ad creatives at the optimal time and location. Specifically, ads will be delivered to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. Delivery will be done in real time using the app's ad slots.

[1146] 6. Collection of effectiveness data

[1147] The server collects real-time data on the effectiveness of delivered advertisements. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. This clearly shows how interested users were in the advertisements.

[1148] 7. Learning and updating

[1149] The server analyzes the collected effectiveness and sentiment data to update the ad generation model for the next campaign. Specifically, it uses machine learning algorithms to train the collected data and improve the model's performance. For example, it adjusts the generation AI model to enhance elements that users find "interesting."

[1150] Example of a prompt

[1151] "Create a new sports drink advertisement targeting women in their 20s. The ad should include a scene of drinking the sports drink while running, emphasizing its energy-boosting effects."

[1152] This system allows marketers to deploy advertising campaigns quickly and effectively, maximizing advertising effectiveness using real-time feedback and user sentiment data.

[1153] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1154] Step 1:

[1155] The user inputs product characteristics and target information via their device. The user logs into the marketing interface, enters the product name, characteristics (e.g., "energy boosting effect"), and target information (e.g., "women in their 20s"), and clicks the submit button. The entered information is sent from the device to the server. The input data includes the product name, product characteristics, and target information. The output data is this information stored on the server.

[1156] Step 2:

[1157] The server collects real-time data from external APIs and internal databases based on the received product characteristics and target information. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time. The input data consists of product characteristics, target information, and data from external APIs, while the output data is real-time data that integrates this information.

[1158] Step 3:

[1159] The server generates ad creatives using a generative AI model based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running." The input data consists of product characteristics, target information, real-time data, and prompts for the generative AI model, while the output data is the generated ad creative.

[1160] Step 4:

[1161] The server analyzes facial and audio data collected from the user's device to recognize the user's emotions. Using an emotion engine, it captures facial data using face recognition technology and analyzes audio data using audio analysis technology. Specifically, it captures video of the user's face while they are viewing an advertisement and records their voice. The input data consists of the user's facial and audio data, and the output data is the analyzed emotion data of the user.

[1162] Step 5:

[1163] The server delivers the generated ad creatives at the optimal time and location. Specifically, it delivers ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. The app's ad slots are used for delivery. Input data includes the generated ad creatives, real-time data, and sentiment data, while output data is the delivered ad creatives.

[1164] Step 6:

[1165] The server collects real-time data on the effectiveness of delivered advertisements and user sentiment data. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. The input data consists of user response data and sentiment data to delivered advertisements, and the output data is the integrated effectiveness data.

[1166] Step 7:

[1167] The server updates the ad generation model for the next generation based on the collected effectiveness and sentiment data. Specifically, it uses machine learning algorithms to analyze the collected data, uses it as training data for the model, and improves the model's performance. The input data is integrated effectiveness and sentiment data, and the output data is the updated ad generation model.

[1168] (Application Example 2)

[1169] 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."

[1170] Existing ad delivery systems do not adequately personalize or optimize ad timing, making it difficult to generate and deliver ad creatives that take into account user emotions and real-time environmental data. Furthermore, feedback on ad effectiveness is not reflected in real time, making it difficult to utilize this feedback for future ad generation. As a result, resources are wasted without maximizing ad effectiveness.

[1171] 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. In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for displaying the generated advertising creatives during video playback; means for collecting effectiveness data of the delivered advertising creatives; means for analyzing the emotional data of users who view the collected advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and emotional data. This enables advertising personalization and delivery at the optimal timing, and maximizes advertising effectiveness by utilizing user emotional data as feedback.

[1172] "Product characteristics" refer to information that describes the attributes and features of a particular product.

[1173] "Target information" refers to information about the target customers to whom a particular advertisement should be directed.

[1174] "Advertising creative" is a general term for the content and design of advertisements created for marketing purposes.

[1175] "Parameters" refer to the variables and settings necessary for generating and delivering advertising creatives.

[1176] "Specific time" refers to the specific time or time slot selected for delivering advertisements.

[1177] "Weather" refers to the weather conditions at the time the advertisement is delivered.

[1178] "Area" refers to the geographical location or region where an advertisement is delivered.

[1179] "Seasons" refer to the cycle of spring, summer, autumn, and winter throughout the year.

[1180] "Optimal location" refers to the distribution destination selected to maximize the effectiveness of the advertisement.

[1181] "Distribution" refers to the act of publishing and distributing advertising creatives to selected locations and media.

[1182] "Effectiveness data" refers to data used to measure the results of delivered advertisements.

[1183] "Emotional data" refers to data that represents the emotional state of users viewing advertisements.

[1184] "Analysis" refers to the act of processing data and deriving information or insights from it.

[1185] "Update" refers to the act of improving or revising an existing ad generation model based on new information.

[1186] "Video playback" refers to the act of playing digital video content.

[1187] This invention is a system that generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, this system aims to collect effectiveness and sentiment data of delivered advertisements and update the generation model for the next set of advertising creatives.

[1188] Components

[1189] 1. Collection Module

[1190] The server collects the parameters necessary for generating advertising creatives based on the collected product characteristics and target information. This collection module has the ability to import real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[1191] 2. Generated Module

[1192] The server automatically generates ad creatives based on the collected parameters. This generation process includes selecting ad templates and incorporating information entered by marketers.

[1193] 3. Distribution Module

[1194] The server delivers the generated ad creatives to the optimal location based on specific time, weather, area, and season. This delivery module has the capability to display ads to users while they are playing videos.

[1195] 4. Effectiveness Data Collection Module

[1196] The server collects performance data for delivered ad creatives (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine. This data is used to evaluate ad performance and improve the ad generation model for the next campaign.

[1197] 5. Emotion Recognition Module

[1198] The server analyzes the emotional data of users who view the ad creatives. Emotion recognition includes analyzing the user's facial expressions and voice.

[1199] 6. Update Module

[1200] The server updates the model for generating the next ad creative based on the collected effectiveness and sentiment data. Machine learning algorithms are used to improve the model.

[1201] Hardware and software

[1202] Hardware to use:

[1203] server

[1204] User terminals (smartphones, mobile devices, etc.)

[1205] Software to use:

[1206] Requests: Obtain real-time data from an external weather information API.

[1207] CV2: Computer Vision Library. Used to display advertisements.

[1208] EmotionEngine: An emotion recognition engine that analyzes user emotion data.

[1209] AdGenerator: Software for automatically generating ad creatives.

[1210] AdOptimizer: Software that optimizes ad models and reflects the changes in subsequent ad generation.

[1211] Specific example

[1212] For example, consider advertising a new sports drink targeted at women in their 20s. The marketing person inputs product characteristics (e.g., energy replenishment effect) and target information (e.g., women in their 20s) into the system via a terminal.

[1213] The server collects sunny weather information using a weather information API and obtains target area information from a geographic information service. Then, it selects an ad template suitable for a sunny morning and generates ad creative with the theme of "a woman in her 20s enjoying running." This ad is displayed to users of a video streaming app while they are playing a video.

[1214] While the ad is playing, the emotion engine analyzes the user's facial expressions and voice to collect user emotion data (e.g., interesting, satisfied). The server also collects effectiveness data such as ad click-through rates and viewing time, and uses machine learning algorithms to update the ad generation model for the next ad.

[1215] Example of a prompt

[1216] "We need personalized ads for a new sports drink aimed at women in their 20s, emphasizing its energy-boosting effects, including scenes of running. The content should be particularly suitable for a sunny morning."

[1217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1218] Step 1:

[1219] The user inputs product characteristics and target information via their device. This input data includes the characteristics of the product being advertised (e.g., energy boost effect) and the attributes of the target customer (e.g., women in their 20s). The server receives this input data and initializes the parameters necessary for generating the ad creative.

[1220] Step 2:

[1221] The server collects real-time data using external APIs. This includes weather information (e.g., sunny), time of day (e.g., morning), and area information (e.g., urban areas). Specifically, it uses the requests library to access the weather information API and retrieve weather data. Time information is obtained from the system's internal clock, and area information is obtained from geographic information services.

[1222] Step 3:

[1223] The server automatically generates ad creatives based on collected product characteristics, target information, and real-time data. Specifically, AdGenerator selects an appropriate ad template and passes the information entered by the marketing team as prompts to the generation AI model. This model generates personalized ad content. The output is an ad creative depicting a specific scenario (e.g., a woman in her 20s enjoying running).

[1224] Step 4:

[1225] The server displays the generated ad creative during video playback. It uses the CV2 library to overlay the ad on the video streaming app's playback screen. Specifically, it optimizes the ad display timing based on real-time data (e.g., morning). Users visually view this ad while the video is playing.

[1226] Step 5:

[1227] The server collects emotional data from users who view ad creatives. Specifically, EmotionEngine analyzes users' facial expressions and voice data to obtain emotional data such as interest and satisfaction. This data serves as an important indicator for evaluating ad performance. The output is the analyzed user emotional data.

[1228] Step 6:

[1229] The server collects performance data for delivered ad creatives. This data includes click-through rates, conversion rates, and viewing time. Specifically, AdOptimizer collects user behavior data and organizes it as performance data. The output is ad performance data.

[1230] Step 7:

[1231] The server updates the ad creative generation model for the next ad based on the collected effectiveness and sentiment data. It optimizes the ad generation model using machine learning algorithms and incorporates feedback information into the next ad generation. Specifically, AdOptimizer analyzes effectiveness and sentiment data and builds a new generative AI model. The output is the updated generative AI model.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] [Fourth Embodiment]

[1236] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1237] 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.

[1238] 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).

[1239] 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.

[1240] 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.

[1241] 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).

[1242] 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.

[1243] 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.

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] 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".

[1249] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the advertising generation model for the next campaign based on collected effectiveness data.

[1250] System Configuration

[1251] This system consists of the following main components:

[1252] 1. Input Interface

[1253] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[1254] This means that marketing personnel will manually provide the information.

[1255] 2. Data Acquisition Module

[1256] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[1257] 3. Ad Creative Generation Module

[1258] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[1259] 4. Ad delivery module

[1260] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[1261] 5. Effectiveness Data Collection Module

[1262] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[1263] 6. Learning Modules

[1264] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[1265] Specific example

[1266] scenario

[1267] Let's take the example of advertising a new sports drink to active women in their 20s.

[1268] 1. Input

[1269] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[1270] 2. Data Collection

[1271] The server receives product characteristics and target information, and collects the current weather ("sunny") via a weather information API, attribute information of the target area ("urban") from a geographic information service, the current time ("morning") based on the system time, and the season ("summer").

[1272] 3. Ad generation

[1273] The server selects an ad template suitable for a sunny morning and generates ad creatives themed around "women in their 20s enjoying running." For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[1274] 4. Ad delivery

[1275] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[1276] 5. Collection of effectiveness data

[1277] The server collects and analyzes effectiveness data such as click-through rates, conversion rates, and viewing time for delivered advertisements.

[1278] 6. Learning and updating

[1279] The server uses machine learning algorithms to update its model based on the collected performance data, thereby improving the accuracy of future ad creative generation.

[1280] As described above, the system of the present invention automatically generates effective advertising campaigns by utilizing product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[1281] The following describes the processing flow.

[1282] Step 1:

[1283] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[1284] Step 2:

[1285] The terminal sends the information entered by the user to the server. This allows the server to receive the necessary parameters.

[1286] Step 3:

[1287] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[1288] Step 4:

[1289] The server collects information about the target area via geographic information services. The information obtained includes "urban areas," etc.

[1290] Step 5:

[1291] The server identifies the current time zone based on the system time. In this case, for example, the time zone "morning" might be identified.

[1292] Step 6:

[1293] The server retrieves the current seasonal data. For example, it collects seasonal information such as "summer."

[1294] Step 7:

[1295] The server selects the optimal ad template based on all the collected parameters. For example, it might choose a template that includes a "running scene on a sunny day."

[1296] Step 8:

[1297] The server automatically generates specific ad creatives based on product characteristics and target attributes. For example, it might create a scene depicting "a woman in her 20s drinking a sports drink while running."

[1298] Step 9:

[1299] The server creates a preview of the generated ad creative and provides it to the user via the device.

[1300] Step 10:

[1301] The user reviews and approves the ad creative on their device. The approval information is sent from the device to the server.

[1302] Step 11:

[1303] The server delivers the ad creative at the optimal time and place. For example, the target audience might be a "fitness app," and the delivery time might be "a sunny summer morning."

[1304] Step 12:

[1305] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[1306] Step 13:

[1307] The server analyzes the collected effectiveness data using machine learning algorithms. This identifies effective factors and areas for improvement.

[1308] Step 14:

[1309] The server updates its ad generation model using the results of machine learning. For example, it learns elements that further emphasize the "refreshing effect after running."

[1310] Step 15:

[1311] The server prepares to incorporate the updated model into the next ad generation. This will enable the automated generation of more effective ad creatives.

[1312] The above describes the specific processing steps of the program and the actions of each step.

[1313] (Example 1)

[1314] 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".

[1315] In today's advertising market, it's essential to generate ad creatives based on product characteristics and target information, and deliver them at the optimal time and place. However, doing this manually is extremely time-consuming and labor-intensive, and furthermore, to generate more effective ads, it's necessary to update the ad generation model to reflect past advertising performance data. Therefore, there is a need for a system that automates the ad generation process and maximizes advertising effectiveness based on collected data.

[1316] 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.

[1317] In this invention, the server includes means for a user to input product characteristics and target information via a terminal; means for transmitting the input product characteristics and target information to the server; means for collecting supplementary data from an external data source based on the transmitted information; means for updating a database based on the collected data; means for inputting prompt text into a generation AI model based on the updated data to generate advertising creatives; means for combining the generated advertising creatives with a selected advertising template; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives in real time; and means for analyzing the collected effectiveness data and updating the advertising generation model using a machine learning algorithm. This enables automatic generation of advertising creatives, delivery at the optimal timing, and model updates based on effectiveness data.

[1318] "Product characteristics" refer to the unique properties and features of a product, including its function, effect, and use.

[1319] "Target information" refers to information about a specific consumer group that is the target of marketing activities, and includes data such as age, gender, region, and interests.

[1320] "User" refers to the entity that inputs and manages information for generating advertising creatives using this system, and usually refers to a marketing professional.

[1321] A "terminal" refers to a device used to input information into or receive information from this system, and includes PCs and mobile devices.

[1322] A "server" refers to a computing system used to process information, manage databases, generate and distribute advertising creatives, and collect performance data.

[1323] "External data sources" refer to external information services that provide supplemental data required by this system, and include weather information APIs and geographic information services.

[1324] A "generative AI model" refers to an artificial intelligence model that generates advertising creatives from given prompt text.

[1325] A "prompt message" refers to a command or instruction given to the AI ​​model, which then generates appropriate advertising creatives.

[1326] An "ad template" refers to a format that has a structure and layout for creating advertising creatives.

[1327] "Advertising creative" refers to advertising materials generated by generative AI models, and includes visuals and text.

[1328] "Effectiveness data" refers to data related to the performance of delivered advertisements, and includes click-through rates, conversion rates, and viewing time.

[1329] A "machine learning algorithm" refers to a computational method used to analyze data, identify patterns and regularities, and update advertising generation models.

[1330] This invention is a system that automatically generates advertising creatives based on product characteristics and target information, and delivers them at the appropriate time and place. This invention is primarily implemented in a form in which three subjects—a server, a terminal, and a user—each handle their respective processing steps.

[1331] The user, acting as a marketing representative, uses a device (such as a PC or mobile device) to input product characteristics and target information into an input form. For example, they might enter the characteristics of a sports drink ("energy replenishment effect") and target information ("women in their 20s") and click the submit button.

[1332] The terminal sends the entered product characteristics and target information to the server. Specifically, the data is sent to the server as an HTTP request. Based on the entered information, the server collects additional data from external data sources such as weather information APIs and geographic information services. For example, it obtains "sunny" weather data from the weather information API, "urban" area attribute information from the geographic information service, the current time ("morning") from the system clock, and seasonal information ("summer").

[1333] The collected data is stored in a database by the server and also in a temporary data store for ad generation. The server generates ad creatives by inputting prompts into the AI ​​model based on this data. An example of a prompt would be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running."

[1334] The generated ad creatives are combined with the most suitable ad templates by the server to complete the final ad material. For example, the video might include a scene of a woman enjoying a run on a refreshing morning and drinking a sports drink.

[1335] The completed ad creative is delivered to target users by a server based on specific time, weather, area, and season. For example, an ad might be delivered to a fitness app frequently used by women in their 20s in urban areas on a sunny summer morning.

[1336] The effectiveness data of delivered ads (click-through rate, conversion rate, viewing time, etc.) is collected in real time by the server and stored in a database. The server analyzes the collected effectiveness data and updates the ad generation model using machine learning algorithms. This ensures that more effective creatives are generated for subsequent ad creations.

[1337] Thus, the system of the present invention automatically generates advertising campaigns based on product characteristics and target information, and maximizes advertising effectiveness through real-time feedback.

[1338] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1339] Step 1:

[1340] The user enters product characteristics (e.g., "energy boosting effect") and target information (e.g., "women in their 20s") into the input form on the terminal and clicks the "Submit" button. This sends the product characteristics and target information to the server. The input is product characteristics and target information, and the output is the HTTP request sent to the server.

[1341] Step 2:

[1342] The terminal sends product characteristics and target information entered by the user to the server. Specifically, this information is sent to the server in the form of an HTTP request. The input is an HTTP request containing product characteristics and target information, and the output is the information sent to the server.

[1343] Step 3:

[1344] The server receives product characteristics and target information transmitted from the terminal. Then, based on the collected information, it gathers supplementary data (e.g., weather information, area attributes, current time, seasonal information) from external data sources (e.g., weather API, geographic information service). In this step, the input is the information from the terminal, and the output is the collected supplementary data.

[1345] Step 4:

[1346] The server updates its internal database based on the collected data and stores all the data necessary for generating ad creatives in a temporary data store. The updated database is also used for the next ad generation. The input is the collected supplemental data, and the output is the updated database and the temporary data store.

[1347] Step 5:

[1348] The server retrieves the necessary data from the temporary data store and inputs prompt text into the generation AI model to generate ad creatives. For example, the prompt text might be: "We want to create an ad for a sports drink aimed at women in their 20s. Its characteristics include energy replenishment, and the target area is urban. The current weather is sunny, and it is morning. Considering the summer season, we want to automatically generate ad creatives themed around women in their 20s who enjoy running." The input is data from the temporary data store and the prompt text, and the output is the generated ad creative.

[1349] Step 6:

[1350] The server selects the optimal ad template based on the ad creatives generated by the AI ​​model. For example, it might select a visual template that matches the theme "a woman in her 20s who enjoys running." The input is the generated ad creative, and the output is the selected ad template.

[1351] Step 7:

[1352] The server combines the selected template and generated creative to create the final advertising material. Specifically, it uses HTML, CSS, and video editing software to visually integrate the advertising creative. The input is the advertising creative and the advertising template, and the output is the final advertising material.

[1353] Step 8:

[1354] The server delivers generated ad materials to target users based on specific time, weather, area, and season. For example, using the delivery platform API, ads can be delivered to fitness apps frequently used by women in their 20s in urban areas on a sunny summer morning. The input is the ad material and delivery conditions, and the output is the delivery of ads to the target users.

[1355] Step 9:

[1356] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time). The collected data is stored in a database and used for analysis. The input is the advertisement effectiveness data, and the output is the stored effectiveness data.

[1357] Step 10:

[1358] The server analyzes the collected performance data and updates the ad generation model using machine learning algorithms. This results in the generation of even more effective ad creatives in the next ad generation cycle. The input is performance data, and the output is the updated ad generation model.

[1359] (Application Example 1)

[1360] 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".

[1361] Traditional advertising systems required marketing personnel to manually set up ad creatives and select the optimal timing and location for delivery, which was time-consuming and laborious. Furthermore, collecting and analyzing performance data was cumbersome, making it difficult to incorporate the findings into subsequent ad campaigns. Moreover, with the proliferation of smart devices, real-time ad display and location-based ad delivery are required, but traditional systems were unable to efficiently handle these requirements.

[1362] 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.

[1363] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on a specific time, weather, area, and season; means for collecting effectiveness data of the delivered advertising creatives; means for updating the generation model for the next advertising creative based on the collected effectiveness data; means for collecting location information from smart devices and optimizing advertising delivery; and means for displaying advertising creatives in real time on smart devices. This streamlines a series of operations from automatic generation to delivery, effectiveness measurement, and updating the next model, enabling real-time, location-based advertising delivery.

[1364] "Product characteristics" refer to the various attributes and features of a product that is the target of sales promotion.

[1365] "Target information" refers to information about the target customer base or market segment that will be advertised.

[1366] "Advertising creative" refers to content such as images, videos, and text used in advertisements.

[1367] "Parameters" refer to the settings and conditions necessary for generating and distributing advertising content.

[1368] "Weather" refers to local weather conditions obtained through meteorological observations.

[1369] "Area" refers to the region or location where advertisements are delivered.

[1370] "Seasons" refer to the four periods of the year (spring, summer, autumn, and winter).

[1371] "Effectiveness data" refers to data regarding the impact and response that an advertisement had on the target audience.

[1372] A "machine learning algorithm" refers to an algorithm used to train a model with a large amount of data and perform predictions and optimizations.

[1373] "Model updating" refers to the process of adjusting and improving an ad generation model based on collected effectiveness data using machine learning algorithms.

[1374] A "smart device" refers to a portable device with advanced computing capabilities (such as a smartphone or smart glasses).

[1375] "Location information" refers to data about the device's current location.

[1376] "Real-time" refers to a situation where processing or responses occur instantly without delay.

[1377] This invention is a system that automatically generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Specific embodiments are described below.

[1378] System Configuration

[1379] This system consists of the following main components:

[1380] 1. Input Interface

[1381] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system. This allows the marketing staff to manually provide the information.

[1382] 2. Data Acquisition Module

[1383] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[1384] 3. Ad Creative Generation Module

[1385] The server selects an appropriate ad template based on the collected data and automatically generates ad creatives that reflect product characteristics and target attributes.

[1386] 4. Ad delivery module

[1387] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. Potential delivery destinations include fitness apps and social media.

[1388] 5. Effectiveness Data Collection Module

[1389] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.).

[1390] 6. Learning Modules

[1391] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model for the next campaign.

[1392] 7. Smart device integration module

[1393] The server collects location information from smart devices (smartphones and smart glasses) and optimizes ad delivery based on that information. It also displays ad creatives in real time on smart devices.

[1394] Hardware and software used

[1395] The following hardware and software will be used to implement this system.

[1396] Hardware: Smartphones, smart glasses, servers

[1397] Software: Python, TensorFlow, Flask (for APIs), SQL (database)

[1398] Processing flow and specific examples

[1399] The system processes the information in the following steps.

[1400] 1. User input:

[1401] The marketing staff inputs "energy replenishment" as the product characteristic and "women in their 20s" as the target audience via a terminal.

[1402] 2. Data collection:

[1403] The server receives the entered product characteristics and target information, and collects current weather (e.g., sunny), location information (e.g., urban area), current time (e.g., morning), and season (e.g., summer) via an external API.

[1404] 3. Ad generation:

[1405] The server uses an AI model based on collected data to automatically generate advertising creatives that include scenes of a woman in her 20s enjoying running and drinking a sports drink.

[1406] 4. Ad delivery:

[1407] The server uses the location information of smart devices to deliver ads in real time within the target area. For example, it can deliver ads to fitness apps in urban areas on a sunny morning.

[1408] 5. Data collection on effectiveness:

[1409] The server collects real-time performance data from smart devices, including click-through rates, conversion rates, and viewing time for delivered advertisements.

[1410] 6. Learning and updating:

[1411] The server analyzes the collected effectiveness data and uses machine learning algorithms to update the ad generation model, thereby improving the accuracy of future ad generation.

[1412] Example prompt statements

[1413] As a concrete example, the following prompt statement can be used.

[1414] "The sports drink used in the advertisement has an energy-replenishing effect, and the target audience is women in their 20s. The weather is sunny, the area is urban, the time is currently morning, and the season is summer."

[1415] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1416] Processing steps

[1417] Step 1:

[1418] Users input product characteristics and target information through their devices. Specifically, marketing personnel use the input interface on their devices to provide the system with information such as "energy replenishment" and "women in their 20s."

[1419] Input: Product characteristics, target information

[1420] Output: Input product characteristics and target information

[1421] Step 2:

[1422] The server receives the entered product characteristics and target information and uses external APIs to collect real-time data (weather, area, time, season). For example, it obtains current weather data from a weather information API and attribute information for the target area from a geographic information service.

[1423] Input: Product characteristics, target information

[1424] Output: Weather data, area data, time data, seasonal data

[1425] Step 3:

[1426] The server automatically generates advertising creatives using an AI model based on the collected data. This involves selecting templates and combining data to create, for example, a scene of a woman in her 20s enjoying a run while drinking a sports drink.

[1427] Input: Product characteristics, target information, weather data, area data, time data, seasonal data

[1428] Output: Generated ad creative

[1429] Step 4:

[1430] The server delivers the generated ad creatives to the optimal locations based on specific time, weather, area, and season. For example, it might display ads in urban fitness apps on a sunny morning.

[1431] Input: Ad creative, weather data, area data, time data, seasonal data

[1432] Output: Where and when the ad was delivered.

[1433] Step 5:

[1434] The server collects real-time data on the effectiveness of delivered advertisements (click-through rates, conversion rates, viewing time, etc.). Specifically, it sends user interaction data from smart devices to the server.

[1435] Input: Where and when the ad was delivered

[1436] Output: Performance data (click-through rate, conversion rate, viewing time, etc.)

[1437] Step 6:

[1438] The server uses machine learning algorithms to update the ad generation model for the next campaign based on the collected performance data. During this process, it analyzes the performance data and incorporates newly discovered patterns and trends into the model.

[1439] Input: Effect data

[1440] Output: Updated ad generation model

[1441] Step 7:

[1442] The server collects location information from smart devices and optimizes ad delivery based on that information. For example, it uses location data from smart glasses to deliver ads to users in specific locations.

[1443] Input: Location information

[1444] Output: Optimized ad delivery strategy

[1445] Step 8:

[1446] The server displays ad creatives in real time on smart devices. It dynamically displays ads on smartphone and smart glasses displays, providing users with an effective advertising experience.

[1447] Input: Ad creative, location information

[1448] Output: Ad creative displayed on smart devices

[1449] The above outlines the specific processing steps based on application examples. Through the specific actions performed in each step and the resulting data processing and calculations, a sophisticated advertising delivery system can be realized.

[1450] 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.

[1451] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[1452] System Configuration

[1453] This system consists of the following main components:

[1454] 1. Input Interface

[1455] The terminal (the marketing staff's PC or mobile device) has an interface for inputting product characteristics and target information into the system.

[1456] This means that marketing personnel will manually provide the information.

[1457] 2. Data Acquisition Module

[1458] The server receives collected product characteristics and target information, and further collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[1459] 3. Ad Creative Generation Module

[1460] Based on the collected data, the server selects an appropriate ad template and automatically generates ad creatives that reflect product characteristics and target attributes.

[1461] 4. Emotional Engine

[1462] The server is equipped with an emotion engine that analyzes user facial expressions and voice data to recognize user emotions. User emotion data is used for personalizing ad creatives and collecting effectiveness data.

[1463] 5. Ad delivery module

[1464] The server delivers the generated ad creatives to the most suitable locations based on specific time, weather, area, and season. These delivery destinations include, for example, fitness apps and social media platforms.

[1465] 6. Effectiveness Data Collection Module

[1466] The server collects real-time data on the effectiveness of delivered advertisements (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine.

[1467] 7. Learning Modules

[1468] The server analyzes the collected effectiveness and sentiment data and uses machine learning algorithms to update the next ad generation model.

[1469] Specific example

[1470] scenario

[1471] Let's take the example of advertising a new sports drink to active women in their 20s.

[1472] 1. Input

[1473] The user inputs information about the characteristics of the sports drink (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device.

[1474] 2. Data Collection

[1475] The server receives product characteristics and target information, and collects current weather information (e.g., "sunny") via a weather information API, target area information (e.g., "urban area") from geographic information services, and the current time of day (e.g., "morning") and season (e.g., "summer") based on system time.

[1476] 3. Ad generation

[1477] The server selects an ad template suitable for a sunny morning and generates ad creatives based on the theme of "a woman in her 20s enjoying running." The content includes a scene of the woman in her 20s drinking a sports drink while running.

[1478] 4. Emotion recognition

[1479] The server analyzes the user's facial expressions and voice, and uses an emotion engine to recognize the user's emotions. For example, it can determine whether a user viewing an advertisement is expressing emotions such as "interesting" or "satisfied."

[1480] 5. Ad delivery

[1481] The server will deliver ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings.

[1482] 6. Collection of effectiveness data

[1483] The server collects effectiveness data such as click-through rates, conversion rates, and viewing time for delivered ads, and also collects user sentiment data using an emotion engine.

[1484] 7. Learning and updating

[1485] The server analyzes the collected effectiveness and sentiment data using machine learning algorithms and incorporates the findings into the next update of the ad generation model. For example, it might enhance elements that users found "interesting."

[1486] The system of this invention enables marketers to deploy advertising campaigns quickly and effectively, and to maximize advertising effectiveness using real-time feedback and user sentiment data.

[1487] The following describes the processing flow.

[1488] Step 1:

[1489] Users input product characteristics and target information using their devices. For example, they might provide the system with "energy replenishment effect" as a product characteristic and "active women in their 20s" as target information.

[1490] Step 2:

[1491] The terminal sends product characteristics and target information entered by the user to the server. This allows the server to receive the necessary parameters.

[1492] Step 3:

[1493] The server uses a weather information API to collect current weather data. For example, it retrieves weather information indicating "sunny."

[1494] Step 4:

[1495] The server collects information about the target area via geographic information services. The information obtained includes "urban areas," etc.

[1496] Step 5:

[1497] The server identifies the current time zone based on the system time. In this case, for example, the time zone "morning" might be identified.

[1498] Step 6:

[1499] The server retrieves the current seasonal data. For example, it collects seasonal information such as "summer."

[1500] Step 7:

[1501] The server selects the optimal ad template based on all the collected parameters. For example, it might choose a template that includes a "running scene on a sunny day."

[1502] Step 8:

[1503] The server automatically generates specific ad creatives based on product characteristics and target attributes. For example, it might create a scene depicting "a woman in her 20s drinking a sports drink while running."

[1504] Step 9:

[1505] The server creates a preview of the generated ad creative and provides it to the user via the device.

[1506] Step 10:

[1507] The user reviews and approves the ad creative on their device. The approval information is sent from the device to the server.

[1508] Step 11:

[1509] The server delivers the ad creative at the optimal time and place. For example, the target audience might be a "fitness app," and the delivery time might be "a sunny summer morning."

[1510] Step 12:

[1511] Simultaneously with streaming, the server activates an emotion engine to analyze the user's facial expressions and voice data in real time. It identifies whether the user is expressing emotions such as interest or satisfaction.

[1512] Step 13:

[1513] The server collects data on the effectiveness of the delivered advertisements. This data includes click-through rates, conversion rates, and viewing time.

[1514] Step 14:

[1515] The server stores user sentiment data collected by the sentiment engine along with effectiveness data. For example, it records the emotions a user expressed when viewing an advertisement (interested, satisfied, indifferent, etc.).

[1516] Step 15:

[1517] The server analyzes the collected effectiveness and sentiment data using machine learning algorithms and incorporates the findings into the next update of the ad generation model. For example, the model is improved to particularly highlight elements that users found "interesting."

[1518] Step 16:

[1519] Based on the updated model, the server further optimizes the next ad creative based on newly collected parameters and sentiment data, preparing it for automated generation.

[1520] The above describes the specific processing steps and their respective operations in a system that combines emotional engines.

[1521] (Example 2)

[1522] 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".

[1523] Traditional advertising delivery systems could automatically generate ads based on product characteristics and target information, but they lacked sufficient personalization to maximize the effectiveness of the generated ads. Furthermore, when updating the ad creative generation model based on post-delivery performance data, user sentiment data was not effectively utilized. As a result, ad effectiveness was limited, making it difficult to optimize the performance of advertising campaigns.

[1524] 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.

[1525] In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for analyzing user sentiment data using a generation AI model and personalizing the advertising creatives; means for collecting effectiveness data and user sentiment data of the delivered advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and sentiment data. This enables real-time optimization of advertising performance and personalization based on user sentiment.

[1526] "Product characteristics" refer to the features and attributes of the product or service being advertised.

[1527] "Target information" refers to data about a specific consumer group targeted for advertising purposes.

[1528] "Advertising creative" refers to the content, including the content and design of the advertisement.

[1529] "Parameters" refer to various pieces of information and settings that influence the generation of advertising creatives.

[1530] "Real-time data" refers to dynamic data acquired at a given moment, such as current weather, time, area, and season.

[1531] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate advertising creatives.

[1532] An "emotion engine" refers to a technology or system that analyzes a user's facial expressions and voice data to recognize their emotions.

[1533] "Effectiveness data" refers to data that shows the results of ad delivery (such as click-through rate, conversion rate, and viewing time).

[1534] A "machine learning algorithm" refers to a computational method used to train a model based on collected data and perform predictions and classifications.

[1535] "Personalization" refers to individually optimizing content and services according to the user's characteristics and circumstances.

[1536] This invention is a system that automatically generates advertising creatives using an emotion engine based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, it aims to maximize advertising effectiveness by updating the next advertising generation model based on collected effectiveness data and user emotion data.

[1537] This system functions through terminals used by marketing personnel, servers, and terminals used by users to view advertisements. Hardware includes personal computers or smartphones used by marketing personnel, cloud servers or data center servers, and smartphones or tablets for users to view advertisements. Software includes generative AI models for generating ad creatives, an emotion engine for analyzing user sentiment, API call programs for leveraging external APIs, and machine learning algorithms for collecting and analyzing performance data.

[1538] Specific example

[1539] scenario

[1540] Let's take the example of advertising a new sports drink to active women in their 20s.

[1541] 1. Input

[1542] The user inputs information about the sports drink's characteristics (e.g., "energy replenishment effect") and target information (e.g., "women in their 20s") into the system via their device. Specifically, they log in to a dedicated marketing interface, fill in the product name, characteristics, and target information in a form, and click the submit button.

[1543] 2. Data Collection

[1544] The server receives product characteristics and target information, and collects real-time data (weather, time, area, season, etc.) from external APIs and internal databases. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time.

[1545] 3. Ad generation

[1546] The server uses a generative AI model to generate ad creatives based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running."

[1547] 4. Emotion recognition

[1548] The server analyzes facial and audio data collected from the user's device and uses an emotion engine to recognize the user's emotions. Specifically, it captures facial data using face recognition technology when users view advertisements and analyzes audio data using audio analysis technology. This allows it to identify emotions such as whether the user finds the advertisement interesting or satisfied.

[1549] 5. Ad delivery

[1550] The server delivers the generated ad creatives at the optimal time and location. Specifically, ads will be delivered to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. Delivery will be done in real time using the app's ad slots.

[1551] 6. Collection of effectiveness data

[1552] The server collects real-time data on the effectiveness of delivered advertisements. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. This clearly shows how interested users were in the advertisements.

[1553] 7. Learning and updating

[1554] The server analyzes the collected effectiveness and sentiment data to update the ad generation model for the next campaign. Specifically, it uses machine learning algorithms to train the collected data and improve the model's performance. For example, it adjusts the generation AI model to enhance elements that users find "interesting."

[1555] Example of a prompt

[1556] "Create a new sports drink advertisement targeting women in their 20s. The ad should include a scene of drinking the sports drink while running, emphasizing its energy-boosting effects."

[1557] This system allows marketers to deploy advertising campaigns quickly and effectively, maximizing advertising effectiveness using real-time feedback and user sentiment data.

[1558] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1559] Step 1:

[1560] The user inputs product characteristics and target information via their device. The user logs into the marketing interface, enters the product name, characteristics (e.g., "energy boosting effect"), and target information (e.g., "women in their 20s"), and clicks the submit button. The entered information is sent from the device to the server. The input data includes the product name, product characteristics, and target information. The output data is this information stored on the server.

[1561] Step 2:

[1562] The server collects real-time data from external APIs and internal databases based on the received product characteristics and target information. Specifically, it obtains current weather information (e.g., "sunny") from a weather information API, target area information (e.g., "urban area") from a geographic information service, and the current time of day (e.g., "morning") and season (e.g., "summer") based on the system time. The input data consists of product characteristics, target information, and data from external APIs, while the output data is real-time data that integrates this information.

[1563] Step 3:

[1564] The server generates ad creatives using a generative AI model based on the collected data. Specifically, it selects an appropriate ad template from a template library and automatically generates an ad creative depicting a woman in her 20s enjoying running and drinking a sports drink, based on the theme of "women in their 20s enjoying running." The input data consists of product characteristics, target information, real-time data, and prompts for the generative AI model, while the output data is the generated ad creative.

[1565] Step 4:

[1566] The server analyzes facial and audio data collected from the user's device to recognize the user's emotions. Using an emotion engine, it captures facial data using face recognition technology and analyzes audio data using audio analysis technology. Specifically, it captures video of the user's face while they are viewing an advertisement and records their voice. The input data consists of the user's facial and audio data, and the output data is the analyzed emotion data of the user.

[1567] Step 5:

[1568] The server delivers the generated ad creatives at the optimal time and location. Specifically, it delivers ads to fitness apps frequently used by women in their 20s in urban areas on sunny summer mornings. The app's ad slots are used for delivery. Input data includes the generated ad creatives, real-time data, and sentiment data, while output data is the delivered ad creatives.

[1569] Step 6:

[1570] The server collects real-time data on the effectiveness of delivered advertisements and user sentiment data. Specifically, it acquires data on click-through rates, conversion rates, and viewing time, and also integrates user sentiment data collected using a sentiment engine. The input data consists of user response data and sentiment data to delivered advertisements, and the output data is the integrated effectiveness data.

[1571] Step 7:

[1572] The server updates the ad generation model for the next generation based on the collected effectiveness and sentiment data. Specifically, it uses machine learning algorithms to analyze the collected data, uses it as training data for the model, and improves the model's performance. The input data is integrated effectiveness and sentiment data, and the output data is the updated ad generation model.

[1573] (Application Example 2)

[1574] 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".

[1575] Existing ad delivery systems do not adequately personalize or optimize ad timing, making it difficult to generate and deliver ad creatives that take into account user emotions and real-time environmental data. Furthermore, feedback on ad effectiveness is not reflected in real time, making it difficult to utilize this feedback for future ad generation. As a result, resources are wasted without maximizing ad effectiveness.

[1576] 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. In this invention, the server includes means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information; means for automatically generating advertising creatives based on the collected parameters; means for delivering the generated advertising creatives to the optimal location based on specific time, weather, area, and season; means for displaying the generated advertising creatives during video playback; means for collecting effectiveness data of the delivered advertising creatives; means for analyzing the emotional data of users who view the collected advertising creatives; and means for updating the generation model for the next advertising creative based on the collected effectiveness data and emotional data. This enables advertising personalization and delivery at the optimal timing, and maximizes advertising effectiveness by utilizing user emotional data as feedback.

[1577] "Product characteristics" refer to information that describes the attributes and features of a particular product.

[1578] "Target information" refers to information about the target customers to whom a particular advertisement should be directed.

[1579] "Advertising creative" is a general term for the content and design of advertisements created for marketing purposes.

[1580] "Parameters" refer to the variables and settings necessary for generating and delivering advertising creatives.

[1581] "Specific time" refers to the specific time or time slot selected for delivering advertisements.

[1582] "Weather" refers to the weather conditions at the time the advertisement is delivered.

[1583] "Area" refers to the geographical location or region where an advertisement is delivered.

[1584] "Seasons" refer to the cycle of spring, summer, autumn, and winter throughout the year.

[1585] "Optimal location" refers to the distribution destination selected to maximize the effectiveness of the advertisement.

[1586] "Distribution" refers to the act of publishing and distributing advertising creatives to selected locations and media.

[1587] "Effectiveness data" refers to data used to measure the results of delivered advertisements.

[1588] "Emotional data" refers to data that represents the emotional state of users viewing advertisements.

[1589] "Analysis" refers to the act of processing data and deriving information or insights from it.

[1590] "Update" refers to the act of improving or revising an existing ad generation model based on new information.

[1591] "Video playback" refers to the act of playing digital video content.

[1592] This invention is a system that generates advertising creatives based on product characteristics and target information set by marketing personnel, and delivers them at the optimal time and place. Furthermore, this system aims to collect effectiveness and sentiment data of delivered advertisements and update the generation model for the next set of advertising creatives.

[1593] Components

[1594] 1. Collection Module

[1595] The server collects the parameters necessary for generating advertising creatives based on the collected product characteristics and target information. This collection module has the ability to import real-time data (weather, time, area, season, etc.) from external APIs and internal databases.

[1596] 2. Generated Module

[1597] The server automatically generates ad creatives based on the collected parameters. This generation process includes selecting ad templates and incorporating information entered by marketers.

[1598] 3. Distribution Module

[1599] The server delivers the generated ad creatives to the optimal location based on specific time, weather, area, and season. This delivery module has the capability to display ads to users while they are playing videos.

[1600] 4. Effectiveness Data Collection Module

[1601] The server collects performance data for delivered ad creatives (click-through rate, conversion rate, viewing time, etc.) and user sentiment data from the sentiment engine. This data is used to evaluate ad performance and improve the ad generation model for the next campaign.

[1602] 5. Emotion Recognition Module

[1603] The server analyzes the emotional data of users who view the ad creatives. Emotion recognition includes analyzing the user's facial expressions and voice.

[1604] 6. Update Module

[1605] The server updates the model for generating the next ad creative based on the collected effectiveness and sentiment data. Machine learning algorithms are used to improve the model.

[1606] Hardware and software

[1607] Hardware to use:

[1608] server

[1609] User terminals (smartphones, mobile devices, etc.)

[1610] Software to use:

[1611] Requests: Obtain real-time data from an external weather information API.

[1612] CV2: Computer Vision Library. Used to display advertisements.

[1613] EmotionEngine: An emotion recognition engine that analyzes user emotion data.

[1614] AdGenerator: Software for automatically generating ad creatives.

[1615] AdOptimizer: Software that optimizes ad models and reflects the changes in subsequent ad generation.

[1616] Specific example

[1617] For example, consider advertising a new sports drink targeted at women in their 20s. The marketing person inputs product characteristics (e.g., energy replenishment effect) and target information (e.g., women in their 20s) into the system via a terminal.

[1618] The server collects sunny weather information using a weather information API and obtains target area information from a geographic information service. Then, it selects an ad template suitable for a sunny morning and generates ad creative with the theme of "a woman in her 20s enjoying running." This ad is displayed to users of a video streaming app while they are playing a video.

[1619] While the ad is playing, the emotion engine analyzes the user's facial expressions and voice to collect user emotion data (e.g., interesting, satisfied). The server also collects effectiveness data such as ad click-through rates and viewing time, and uses machine learning algorithms to update the ad generation model for the next ad.

[1620] Example of a prompt

[1621] "We need personalized ads for a new sports drink aimed at women in their 20s, emphasizing its energy-boosting effects, including scenes of running. The content should be particularly suitable for a sunny morning."

[1622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1623] Step 1:

[1624] The user inputs product characteristics and target information via their device. This input data includes the characteristics of the product being advertised (e.g., energy boost effect) and the attributes of the target customer (e.g., women in their 20s). The server receives this input data and initializes the parameters necessary for generating the ad creative.

[1625] Step 2:

[1626] The server collects real-time data using external APIs. This includes weather information (e.g., sunny), time of day (e.g., morning), and area information (e.g., urban areas). Specifically, it uses the requests library to access the weather information API and retrieve weather data. Time information is obtained from the system's internal clock, and area information is obtained from geographic information services.

[1627] Step 3:

[1628] The server automatically generates ad creatives based on collected product characteristics, target information, and real-time data. Specifically, AdGenerator selects an appropriate ad template and passes the information entered by the marketing team as prompts to the generation AI model. This model generates personalized ad content. The output is an ad creative depicting a specific scenario (e.g., a woman in her 20s enjoying running).

[1629] Step 4:

[1630] The server displays the generated ad creative during video playback. It uses the CV2 library to overlay the ad on the video streaming app's playback screen. Specifically, it optimizes the ad display timing based on real-time data (e.g., morning). Users visually view this ad while the video is playing.

[1631] Step 5:

[1632] The server collects emotional data from users who view ad creatives. Specifically, EmotionEngine analyzes users' facial expressions and voice data to obtain emotional data such as interest and satisfaction. This data serves as an important indicator for evaluating ad performance. The output is the analyzed user emotional data.

[1633] Step 6:

[1634] The server collects performance data for delivered ad creatives. This data includes click-through rates, conversion rates, and viewing time. Specifically, AdOptimizer collects user behavior data and organizes it as performance data. The output is ad performance data.

[1635] Step 7:

[1636] The server updates the ad creative generation model for the next ad based on the collected effectiveness and sentiment data. It optimizes the ad generation model using machine learning algorithms and incorporates feedback information into the next ad generation. Specifically, AdOptimizer analyzes effectiveness and sentiment data and builds a new generative AI model. The output is the updated generative AI model.

[1637] 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.

[1638] 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.

[1639] 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 robot 414.

[1640] 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.

[1641] 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.

[1642] 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.

[1643] 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.

[1644] 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.

[1645] 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."

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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.

[1652] 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.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1658] The following is further disclosed regarding the embodiments described above.

[1659] (Claim 1)

[1660] A means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information,

[1661] A method for automatically generating ad creatives based on collected parameters,

[1662] A means of delivering generated ad creatives to the optimal location based on specific time, weather, area, and season,

[1663] A means of collecting data on the effectiveness of delivered advertising creatives,

[1664] A means to update the generation model for the next advertising creative based on the collected effectiveness data,

[1665] A system that includes this.

[1666] (Claim 2)

[1667] The system according to claim 1, further comprising means for having a marketing person input product characteristics and target information.

[1668] (Claim 3)

[1669] The system according to claim 1, further comprising means for analyzing the effectiveness data of delivered advertising creatives based on a machine learning algorithm.

[1670] "Example 1"

[1671] (Claim 1)

[1672] A means for users to input product characteristics and target information via a terminal,

[1673] A means for transmitting the entered product characteristics and target information to a server,

[1674] A means of collecting supplementary data from external data sources based on the transmitted information,

[1675] A means of updating the database based on the collected data,

[1676] A method for generating ad creatives by inputting prompt text into a generation AI model based on updated data,

[1677] A method for combining the generated ad creative with a selected ad template,

[1678] A means of delivering generated ad creatives to the optimal location based on specific time, weather, area, and season,

[1679] A means of collecting real-time data on the effectiveness of delivered ad creatives,

[1680] A means of analyzing collected effectiveness data and updating the ad generation model using machine learning algorithms,

[1681] A system that includes this.

[1682] (Claim 2)

[1683] The system according to claim 1, further comprising means for having a marketing person input product characteristics and target information.

[1684] (Claim 3)

[1685] The system according to claim 1, further comprising means for analyzing the effectiveness data of delivered advertising creatives based on a machine learning algorithm.

[1686] "Application Example 1"

[1687] (Claim 1)

[1688] A means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information,

[1689] A method for automatically generating ad creatives based on collected parameters,

[1690] A means of delivering generated ad creatives to the optimal location based on specific time, weather, area, and season,

[1691] A means of collecting data on the effectiveness of delivered advertising creatives,

[1692] A means to update the generation model for the next advertising creative based on the collected effectiveness data,

[1693] A means of collecting location information from smart devices and optimizing ad delivery,

[1694] A means of displaying advertising creatives in real time on smart devices,

[1695] A system that includes this.

[1696] (Claim 2)

[1697] The system according to claim 1, further comprising means for having a marketing person input product characteristics and target information.

[1698] (Claim 3)

[1699] The system according to claim 1, further comprising means for analyzing the effectiveness data of delivered advertising creatives based on a machine learning algorithm.

[1700] "Example 2 of combining an emotion engine"

[1701] (Claim 1)

[1702] A means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information,

[1703] A method for automatically generating ad creatives based on collected parameters,

[1704] A means of delivering generated ad creatives to the optimal location based on specific time, weather, area, and season,

[1705] A means of analyzing user sentiment data using generative AI models to personalize advertising creatives,

[1706] A means for collecting effectiveness data and user sentiment data for delivered advertising creatives,

[1707] A means of updating the generation model for the next advertising creative based on collected effectiveness data and sentiment data,

[1708] A system that includes this.

[1709] (Claim 2)

[1710] The system according to claim 1, further comprising means for having a marketing person input product characteristics and target information.

[1711] (Claim 3)

[1712] The system according to claim 1, further comprising means for updating the generation model for the next advertising creative using a machine learning algorithm based on the effectiveness data of the delivered advertising creative and user sentiment data.

[1713] "Application example 2 when combining with an emotional engine"

[1714] (Claim 1)

[1715] A means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information,

[1716] A method for automatically generating ad creatives based on collected parameters,

[1717] A means of delivering generated ad creatives to the optimal location based on specific time, weather, area, and season,

[1718] A means of displaying the generated ad creative during video playback,

[1719] A means of collecting data on the effectiveness of delivered advertising creatives,

[1720] A means of analyzing the emotional data of users who view the collected advertising creatives,

[1721] A means to update the generation model for the next advertising creative based on the collected effectiveness data and sentiment data,

[1722] A system that includes this.

[1723] (Claim 2)

[1724] The system according to claim 1, further comprising means for having a marketing person input product characteristics and target information.

[1725] (Claim 3)

[1726] The system according to claim 1, further comprising means for analyzing the effectiveness data and sentiment data of delivered advertising creatives based on a machine learning algorithm. [Explanation of Symbols]

[1727] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting parameters necessary for generating advertising creatives based on collected product characteristics and target information, A method for automatically generating ad creatives based on collected parameters, A means of delivering generated ad creatives to the optimal location based on specific time, weather, area, and season, A means of collecting data on the effectiveness of delivered advertising creatives, A means to update the generation model for the next advertising creative based on the collected effectiveness data, A system that includes this.

2. The system according to claim 1, further comprising means for having a marketing person input product characteristics and target information.

3. The system according to claim 1, further comprising means for analyzing the effectiveness data of delivered advertising creatives based on a machine learning algorithm.

Images