system

Abstract

To provide a system for enabling anyone to easily execute digital marketing without expert knowledge.SOLUTION: Means for receiving a merchandise concept from a user, means for automatically generating a delivery scenario in a AI based on the received merchandise concept, means for automatically generating advertisement content in the AI based on the automatically generated delivery scenario, means for adjusting the generated content and delivery scenario by a designer, means for detecting legal risks and conformity to brand guidelines of the advertisement content using the AI and presenting the detected legal risks and conformity to the brand guidelines to a legal department, means for delivering the generated advertisement content to influential target users and performing an AB test, means for evaluating delivery results with a BI tool and measuring CTR, CVR, and ROI, and means for analyzing evaluation results with the AI and improving the delivery scenario and the content.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Digital marketing has become increasingly important in recent years, but it requires a large number of personnel with specialized knowledge (e.g., marketers, designers, engineers, data analysts), making it difficult for small and medium-sized enterprises and D2C companies to implement. This has resulted in a lack of efficient ways to implement digital marketing, resulting in high costs and time expenditures. The purpose of this invention is to improve this situation and make it possible for anyone to easily implement digital marketing, even without specialized knowledge. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes the following means: a means for receiving a product concept from a user, a means for automatically generating a distribution scenario using AI based on the received product concept, a means for automatically generating advertising content using AI based on the automatically generated distribution scenario, a means for a designer to adjust the generated content and distribution scenario, a means for using AI to detect legal risks and compliance with brand guidelines in the advertising content and present the results to the legal department, a means for distributing the generated advertising content to influential target users and performing A / B testing, a means for evaluating the distribution results using a BI tool and measuring CTR, CVR, and ROI, and a means for analyzing the evaluation results using AI to improve the distribution scenario and content. This system enables anyone to carry out efficient digital marketing.

[0006] A "product concept" is a comprehensive concept that includes a product's features, value, target users, benefits, etc.

[0007] A "distribution scenario" is a scheme that plans what messages or content should be delivered to specific target users, at what timing, and through what channels.

[0008] "AI" is an abbreviation for artificial intelligence, a technology that automatically analyzes data, learns, and improves the operations it performs.

[0009] "Advertising content" refers to media materials such as text, images, and videos intended to promote products.

[0010] A "designer" is a professional who is responsible for designing visual graphics and advertising materials.

[0011] "Legal risk" refers to situations where advertising content may violate relevant laws or regulations.

[0012] A "brand guideline" is a set of rules regarding design and messaging that are used to unify the brand image of a company or product.

[0013] "AB testing" is a testing method in which two or more different versions of content are distributed simultaneously and their effectiveness is compared.

[0014] "BI tool" is an abbreviation for business intelligence tool, and is software used to analyze corporate data and support management decisions.

[0015] "CTR" stands for Click Through Rate, an indicator that shows the ratio of the number of clicks to the number of times an ad is displayed.

[0016] "CVR" stands for conversion rate, and is an indicator that shows the percentage of users who saw an advertisement and actually took action such as making a purchase or making an inquiry.

[0017] "ROI" stands for Return on Investment and is an indicator that shows the ratio of profits obtained to invested resources. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a 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.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0032] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a system that automatically executes digital marketing by inputting a product concept into AI. This system includes the processes of inputting the product concept, formulating a distribution scenario, creating content, legal and brand checks, distributing content to the target, measuring effectiveness, and making improvements based on the results.

[0040] Program processing

[0041] User side

[0042] 1. Enter the product concept

[0043] Users use the terminal to input product concepts, insights (consumer insights), benefits, and competitive comparison information.

[0044] Example: A user inputs information about a "new health drink," such as "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products" on a terminal.

[0045] Server side

[0046] 2. Data Reception and Analysis

[0047] The server compares the product concept data received from the user with internal data and external data (market data, trend data) and performs analysis.

[0048] Example: The server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[0049] 3. Generating a distribution scenario

[0050] The server automatically generates a distribution scenario using AI based on the selected target.

[0051] Example: AI generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (social media, email, etc.) for each target.

[0052] 4. Content Generation

[0053] The server uses AI to automatically generate content such as text, images, and videos based on the distribution scenario.

[0054] Example: AI generates the tagline "Easy Health" along with an image of an office worker drinking a drink.

[0055] 5. Content Selection and Tuning

[0056] The designer checks the content generated by the server and makes any final adjustments.

[0057] Example: A designer reviews the generated images and text and adjusts color, font, placement, etc.

[0058] 6. Legal Brand Check

[0059] The server uses AI to automatically detect legal risks and compliance with brand guidelines for content and presents them to the legal department.

[0060] Example: AI detects legal risks in ad copy and checks whether appropriate contact information is included. The results are reported to the legal department.

[0061] Terminal side

[0062] 7. Execution of distribution

[0063] The terminal delivers content to target users based on the distribution scenario and content received from the server and conducts AB testing.

[0064] Example: The device delivers a "quick health" version and a "post-sports recovery" version to different target groups (office workers and sports enthusiasts), and measures the effectiveness for each group.

[0065] 8. Effectiveness Measurement

[0066] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time.

[0067] Example: The server collects data after delivery, analyzes and displays the click rate and conversion rate for each target group.

[0068] Server side

[0069] 9. Analysis and improvement of results

[0070] The server uses AI to analyze the distribution results, analyze the difference between the predicted effect and the actual results, identify the cause, and automatically generate improvement measures.

[0071] Example: AI identifies that the visuals are the cause of low click-through rates on ads for office workers and suggests new images and text.

[0072] User side

[0073] 10. Final tuning

[0074] Users (especially marketers and designers) review the AI's suggestions and adjust the actual content and distribution scenarios.

[0075] Example: Marketers review suggested improvements and make manual adjustments as needed.

[0076] This invention makes it possible to efficiently carry out digital marketing even without specialized knowledge. This system automates the entire process, from product concept to distribution, evaluation, and improvement, thereby saving costs and time.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0080] Step 2:

[0081] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0082] Step 3:

[0083] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[0084] Step 4:

[0085] AI automatically generates optimal delivery scenarios for the extracted targets. Scenarios include the message, delivery channel, delivery timing, etc. Specific actions that can be generated include "delivering social media ads to office workers on weekday mornings" and "delivering email ads on weekends to sports enthusiasts."

[0086] Step 5:

[0087] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Get healthy easily" and an image of an office worker holding a health drink.

[0088] Step 6:

[0089] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and fine-tunes the color tone, font, placement, etc.

[0090] Step 7:

[0091] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0092] Step 8:

[0093] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[0094] Step 9:

[0095] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[0096] Step 10:

[0097] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[0098] Step 11:

[0099] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0100] Step 12:

[0101] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] In traditional digital marketing, the process from entering product concepts to distributing advertising content, measuring effectiveness, and making improvements is often done manually, which not only takes a great deal of time and effort but also requires specialized knowledge, resulting in problems of inefficiency.In addition, checking whether the generated advertising content complies with legal risks and brand guidelines is often done manually, which poses challenges in terms of the time and human resources required for the checking process to avoid legal risks.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes means for receiving a product concept from a user, means for automatically generating a distribution scenario based on the received product concept using a generative AI model, and means for generating advertising content based on the distribution scenario automatically generated using the generative AI model. This makes it possible to provide an environment in which a user simply inputs a product concept, and the AI ​​automatically generates a distribution scenario and advertising content, enabling a series of digital marketing processes to be executed quickly and efficiently.

[0107] A "product concept" is an idea or strategy that includes the basic purpose and characteristics of a product or service, target market, competitive analysis, etc.

[0108] "Means for receiving" refers to a function or process for acquiring data input by a user.

[0109] A "generative AI model" refers to artificial intelligence technology and algorithms that automatically generate scenarios and content based on input information from users.

[0110] A "distribution scenario" is a plan that defines what advertising content will be distributed to a specific target, at what timing, and through which channel.

[0111] "Advertising content" refers to promotional materials such as text, images, and videos created based on a distribution scenario.

[0112] A "creator" is a professional who is responsible for the final design and adjustment of advertising content.

[0113] "Legal risk" refers to the possibility that advertising content may violate laws or regulations.

[0114] "Brand guidelines" are rules regarding design and messaging established to maintain a company's brand image.

[0115] A "legal department" is a department within a company or organization that manages and deals with legal issues and risks.

[0116] "Target users" refers to the customer demographic that is anticipated when delivering advertisements, specifically the recipients of the advertisements.

[0117] "AB testing" is a method of comparing two or more versions of an advertisement or piece of content to determine which is more effective.

[0118] "Analysis tools" refer to software and platforms for collecting and analyzing data and visualizing the results.

[0119] "Click-through rate" refers to the percentage of clicks on an ad compared to the number of times it is displayed.

[0120] "Conversion rate" is the percentage of ads that result in a targeted action (such as a purchase or registration).

[0121] "Return on investment" is an indicator that evaluates how much profit is gained from the resources invested in advertising and marketing activities.

[0122] "Evaluation results" refer to various indicators (click-through rate, conversion rate, return on investment, etc.) obtained using analysis tools after advertising is delivered.

[0123] "Root cause analysis" is the process of identifying the causes of problems or lack of effectiveness with advertising or content.

[0124] "Improvement measures" are specific action plans to address identified problems and causes.

[0125] A "marketer" is a professional who is responsible for marketing activities in a company or organization.

[0126] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. The main elements that make up the system are users, devices, and servers, each of which plays a specific role.

[0127] First, the user uses a terminal to input the product concept, insights (consumer insights), benefits, and competitive comparison information. For example, for a new health drink, the user can input insights and benefits such as "maintaining health in a busy life" and "easily achieving health," as well as "comparison data with similar competitive products." This information is sent to the server via the terminal.

[0128] The server compares the received product concept data with its internal database and external data (market data, trend data) and performs an analysis. This analysis uses an AI model (e.g., machine learning algorithms, data analysis tools, etc.). Specifically, the server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[0129] Next, the server automatically generates a distribution scenario based on the selected targets using a generative AI model (e.g., natural language processing model). For example, the AI ​​could generate a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts," and select the optimal distribution channel (e.g., social media, email) for each target.

[0130] The server then uses a generative AI model to automatically generate advertising content such as text, images, and videos based on the distribution scenario. This process uses tools such as DeepArt for image generation and Synthesia for video generation. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[0131] The generated content and distribution scenarios are then checked by a designer, who makes final adjustments using design tools such as Adobe Creative Cloud to adjust color tones, fonts, and image placement.

[0132] The server then uses AI to detect legal risks and compliance with brand guidelines in the ad content. For example, it uses Compliance AI tools to check for potential legal risks in the ad copy, checks for violations of guidelines, and reports the results to the legal department.

[0133] The device then delivers content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the device delivers advertisements for "easy health" and "recovery after sports" to different target groups (office workers and sports enthusiasts) and measures the effectiveness of each.

[0134] Finally, the server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time and analyze the results. Based on this evaluation, the AI ​​analyzes the cause and presents improvement measures, and marketers and designers make final adjustments.

[0135] An example prompt is:

[0136] Please enter your product concept for a "new healthy drink." Please include specific consumer insights, benefits, and competitive comparison information.

[0137] example:

[0138] Insight: "Staying healthy in a busy life"

[0139] Benefit: "Easy to get healthy"

[0140] Competitive comparison: "Comparative data with similar competing products"

[0141] As a result, this system automates the entire process from product concept to distribution, evaluation, and improvement, resulting in significant cost and time savings.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] The user uses a terminal to input and submit a product concept. Specifically, the user enters the concept of a "new health drink," along with insights (e.g., "Maintaining health in a busy life"), benefits (e.g., "Easily achieve health"), and competitive comparison information into the form, and clicks the submit button. The input information is sent from the terminal to the server.

[0145] Input: Product concept, insights, benefits, competitive comparison information

[0146] Output: Product concept data sent to the server

[0147] Step 2:

[0148] The server analyzes the product concept data received from the user by comparing it with the internal database and external data (market data, trend data). Specifically, the server analyzes the user's input data using past sales data and consumer reviews from the internal database, as well as market trend data obtained through external APIs. An AI model is used in this analysis to select the optimal target users.

[0149] Input: Product concept data, internal database, external data

[0150] Output: Analysis results (e.g., "health-conscious working generation" and "sports enthusiasts")

[0151] Step 3:

[0152] The server automatically generates a distribution scenario based on the selected target using a generative AI model. Specifically, it uses a generative AI model (e.g., a natural language processing model) to create scenarios for a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts." It also selects the optimal distribution channel (e.g., social media, email, etc.) for each target.

[0153] Input: Analysis results, generated AI model

[0154] Output: Delivery scenario

[0155] Step 4:

[0156] The server uses the generative AI model to automatically generate advertising content based on the generated distribution scenario. Specific operations include using a natural language generation model to generate text, an image generation tool (e.g., DeepArt) to generate images, and a video generation tool (e.g., Synthesia) to generate videos. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[0157] Input: Delivery scenario, generative AI model

[0158] Output: Ad content (text, images, videos)

[0159] Step 5:

[0160] Creators adjust the content and distribution scenarios generated by the server. Specifically, creators use design tools (e.g., Adobe Creative Cloud) to adjust the color tone, font, and placement of generated images and text.

[0161] Input: Ad content, distribution scenario

[0162] Output: Adjusted advertising content, distribution scenario

[0163] Step 6:

[0164] The server uses AI to detect legal risks and compliance with brand guidelines in advertising content and presents the results to the legal department. Specifically, it uses legal risk detection tools (e.g., Compliance AI) to analyze content and checks compliance with guidelines.

[0165] Input: Tailored ad content

[0166] Output: Legal risk and brand guideline compliance detection results

[0167] Step 7:

[0168] The device delivers content to target users based on the delivery scenario and content received from the server, and performs AB testing. Specifically, an ad management tool (e.g., Facebook Ads Manager) is used for delivery, and different versions of ads are delivered to different target groups.

[0169] Input: Distribution scenario, advertising content

[0170] Output: Advertisements delivered to target users, AB test results

[0171] Step 8:

[0172] The server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time. Specifically, it collects and visualizes user data after ad delivery and analyzes the effectiveness indicators for each target group.

[0173] Input: AB test results, target user data

[0174] Output: Effectiveness measurement results (CTR, CVR, ROI)

[0175] Step 9:

[0176] The server uses AI to analyze the results of effectiveness measurements, analyzes the difference between predicted and actual results to identify the cause, and automatically generates improvement measures.Specifically, it uses an AI model (e.g., machine learning algorithm) to generate new suggestions for identified problems.For example, it may identify that the cause of a low click-through rate is visual and suggest new images and text.

[0177] Input: Effectiveness measurement results

[0178] Output: Cause analysis, improvement suggestions

[0179] Step 10:

[0180] Users (especially marketers and creators) review the AI's suggestions and make final adjustments to the actual content and distribution scenario. Specifically, marketers adjust distribution schedules and targeting based on the suggestions, and creators make suggested design improvements.

[0181] Input: Improvement suggestion

[0182] Output: Final adjusted ad content and distribution scenario

[0183] (Application example 1)

[0184] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0185] In the field of digital marketing, there is a demand for automation of the creation, distribution, effectiveness measurement, and improvement of effective advertising campaigns. Conventional methods require marketers to expend a lot of time and effort and specialized knowledge, resulting in inefficiency and high costs. In addition, it is difficult to measure the effectiveness of ads in real time or make quick improvements after they are delivered. This poses a challenge in maximizing the effectiveness of advertising investments.

[0186] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0187] In this invention, the server includes: means for receiving a product concept from a user; means for automatically generating a distribution scenario using AI based on the received product concept; means for automatically generating advertising content using AI based on the automatically generated distribution scenario; means for a designer to adjust the generated content and distribution scenario; means for detecting legal risks of the advertising content and compliance with brand guidelines using AI and presenting the results to the legal department; means for delivering the generated advertising content to target users via their smart devices and performing A / B testing; means for evaluating real-time data collected from the smart devices using a BI tool and measuring CTR, CVR, and ROI; and means for analyzing the evaluation results using AI and automatically improving the advertising content and distribution scenario. This enables the automation of effective advertising campaigns.

[0188] "Product concept" refers to detailed information about a product or service, such as its features, benefits, and target users.

[0189] "User" means a person or entity that utilizes the System to enter product concepts and manage advertising campaigns.

[0190] A "distribution scenario" refers to a plan for distributing content to specific target users through what channels and at what timing.

[0191] "AI" refers to artificial intelligence technology, which includes algorithms and models for automatically solving specific problems.

[0192] "Advertising Content" refers to materials such as text, images, and video created for advertising purposes.

[0193] "Designer" refers to the person who makes the final adjustments to the generated advertising content and visually optimizes it.

[0194] "Legal risk" refers to the risk that advertising content may violate the law.

[0195] "Brand guidelines" refer to standards for design and messaging established to maintain brand consistency.

[0196] "Legal Department" means the department within an organization that considers and resolves legal matters.

[0197] "Target users" refers to the group of users who are intended to receive a particular message of an advertising campaign.

[0198] "Smart devices" refers to advanced electronic devices with internet connectivity, such as smartphones, tablets, and smart glasses.

[0199] "AB testing" refers to a testing method in which different versions of advertising content are simultaneously delivered to target users and their effectiveness is compared.

[0200] "BI tool" stands for business intelligence tool and refers to software that analyzes data to support business decision-making.

[0201] "CTR" stands for click-through rate and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[0202] "CVR" stands for conversion rate and refers to the percentage of times a specific action (purchase, registration, etc.) is performed.

[0203] "ROI" stands for return on investment and refers to an indicator that financially evaluates the effectiveness of the money invested in an advertising campaign.

[0204] "Real-time data" refers to data that is collected continuously from the moment an ad is delivered.

[0205] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. This system is divided into a user side and a server side.

[0206] User side

[0207] Entering product concepts

[0208] Users use a smartphone app to input product concepts, insights, benefits, and competitive analysis information. For example, for a "new health drink," users can input "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0209] Server side

[0210] Data reception and analysis

[0211] The server analyzes the product concept data received from users by comparing it with internal and external data. This analysis uses artificial intelligence (AI) models such as TensorFlow. The optimal target users are selected based on market and trend data. As a specific example, trend data from the health drink market is analyzed to select "health-conscious working people" and "sports enthusiasts" as targets.

[0212] Generating a distribution scenario

[0213] The server automatically generates distribution scenarios using AI based on the selected target users. For example, the AI ​​generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (SNS, email, etc.) for each target.

[0214] Content Generation

[0215] The server uses AI to generate advertising content such as text, images, and videos based on a distribution scenario. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[0216] Legal Brand Check

[0217] AI is used to detect legal risks and compliance with brand guidelines in generated advertising content, and presents the results to the legal department. For example, AI can detect legal risks in advertising copy and check whether appropriate contact information is included.

[0218] Terminal side

[0219] Executing the distribution

[0220] The smartphone app delivers advertising content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the app delivers two versions, "Easy Health" and "Post-Sports Recovery," to different target groups (office workers and sports enthusiasts), and measures the effectiveness of each.

[0221] Effectiveness measurement

[0222] The server uses BI (business intelligence) tools to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered advertising content in real time. For example, the server collects data after delivery and analyzes and displays the click-through rate and conversion rate of each target group. For this purpose, BI tools such as Tableau are used.

[0223] Results analysis and improvement

[0224] The server uses AI to analyze the results of distribution, analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. For example, the AI ​​may identify that the visuals are the cause of the low click-through rate of ads aimed at office workers, and suggest new images and text.

[0225] User side

[0226] Final Tuning

[0227] Users, especially marketers and designers, review the AI ​​suggestions and adjust the actual content and distribution scenarios. For example, marketers review the suggested improvements and make manual adjustments as necessary.

[0228] Prompt Sentence Examples

[0229] Product concept: A new health drink

[0230] Consumer Insights: Busy lifestyles and the need to stay healthy

[0231] Benefit: Easy health

[0232] Competitive comparison: Comparison data with similar competing products

[0233] In this way, effective advertising campaigns can be automated and efficiently executed.

[0234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0235] Step 1:

[0236] Users use a smartphone app to input product concepts, consumer insights, profits, and competitive analysis information.

[0237] For example, the user inputs "new healthy drink" along with consumer insights and comparison data with competing products. The device then sends this data to the server.

[0238] Step 2:

[0239] The server analyzes the product concept data received from the user by comparing it with internal data and external data.

[0240] This analysis uses AI models such as TensorFlow. The server selects the optimal target users based on market and trend data. The output is a list of target users (e.g., "health-conscious working generation" or "sports enthusiasts").

[0241] Step 3:

[0242] The server automatically generates a distribution scenario using AI based on the target users.

[0243] For example, AI can generate "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and select the optimal distribution channel (e.g., social media or email) for each target. Specific distribution scenarios are generated as an output.

[0244] Step 4:

[0245] The server automatically generates advertising content using AI based on the generated distribution scenario.

[0246] Specifically, it generates advertising materials such as text, images, and videos. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink. The output is the completed advertising content.

[0247] Step 5:

[0248] Use AI to detect legal risks and compliance with brand guidelines before presenting server-generated ad content to the legal department.

[0249] For example, AI can detect legal risks and brand guideline violations in ad copy and report the results to the legal department. The output is a check result for legal risk and brand suitability.

[0250] Step 6:

[0251] The device delivers advertising content to target users based on the delivery scenario and content received from the server, and performs AB testing.

[0252] For example, we deliver two versions of the AB test, one for "easy health" and the other for "recovery after sports" to different target groups (office workers and sports enthusiasts), and measure their effectiveness. The input is the delivery scenario and content from the server, and the output is the results of the AB test.

[0253] Step 7:

[0254] The server uses a BI tool (e.g., Tableau) to measure the effectiveness of advertising content in real time.

[0255] It calculates and analyzes metrics such as click-through rate (CTR), conversion rate (CVR), and return on investment (ROI). The input is user response data to delivered advertising content, and the output is the real-time measurement results of these metrics.

[0256] Step 8:

[0257] The server uses AI to analyze the distribution results and analyze the difference between the predicted effect and the actual results.

[0258] For example, AI can identify that the low click-through rate of ads for office workers is due to visuals and suggest new images and text. The input is effectiveness measurement data, and the output is the results of an analysis of the causes and suggestions for improvement.

[0259] Step 9:

[0260] The user reviews the AI's suggestions and makes manual adjustments if necessary.

[0261] Marketers and designers review the proposed improvements and make final adjustments to the content and distribution scenario. The input is the improvement suggestions from the AI, and the output is the final adjusted advertising content and distribution scenario.

[0262] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0263] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[0264] Program processing

[0265] User side

[0266] 1. Enter the product concept

[0267] The user uses the terminal to input the product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into the form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0268] Server side

[0269] 2. Data Reception and Analysis

[0270] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0271] 3. Emotion Data Analysis

[0272] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[0273] 4. Generating a distribution scenario

[0274] The server extracts targets based on the emotional data and automatically generates optimal distribution scenarios using AI. Specifically, the emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" and generates distribution scenarios based on them.

[0275] 5. Content Generation

[0276] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[0277] 6. Content Selection and Tuning

[0278] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color, font, and placement.

[0279] 7. Legal Brand Check

[0280] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0281] Terminal side

[0282] 8. Execution of distribution

[0283] The device distributes content to target users based on the distribution scenario and content received from the server, and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[0284] 9. Measurement

[0285] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[0286] Server side

[0287] 10. Analysis and improvement of results

[0288] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0289] User side

[0290] 11. Final tuning

[0291] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[0292] This invention enables efficient digital marketing even without specialized knowledge. Furthermore, by combining it with an emotion engine, distribution scenarios and advertising content can be optimized to match user emotions, resulting in more effective digital marketing. This system automates the entire process, from product conception through distribution, evaluation, and improvement, thereby saving time and money.

[0293] The processing flow will be explained below.

[0294] Step 1:

[0295] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0296] Step 2:

[0297] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0298] Step 3:

[0299] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[0300] Step 4:

[0301] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[0302] Step 5:

[0303] Based on the extracted target and emotional data, AI automatically generates optimal distribution scenarios. The scenarios include the message, distribution channel, and distribution timing. Specific actions generated include "delivering morning social media ads to office workers with positive emotions" and "delivering weekend email ads to sports enthusiasts feeling tired."

[0304] Step 6:

[0305] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[0306] Step 7:

[0307] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and adjusts the color tone, font, and placement.

[0308] Step 8:

[0309] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0310] Step 9:

[0311] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[0312] Step 10:

[0313] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[0314] Step 11:

[0315] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[0316] Step 12:

[0317] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0318] Step 13:

[0319] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[0320] Example 2

[0321] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0322] Modern digital marketing requires efficient and effective delivery of advertising content, but traditional methods have the following problems:

[0323] 1. The process from entering product concepts to generating distribution scenarios is done manually, which is time-consuming and costly.

[0324] 2. Delivery scenarios and advertising content are created uniformly and do not respond to the emotions and needs of target users.

[0325] 3. Because effectiveness measurement and analysis are done manually, improvement measures are delayed. Also, because A / B testing and its effectiveness measurement cannot be carried out efficiently, it is difficult to optimize advertising.

[0326] The present invention aims to solve these problems and provide a system that realizes efficient and effective digital marketing.

[0327] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0328] In this invention, the server includes: means for receiving a product concept from a user; means for comparing and analyzing the received product concept with internal data and external data; means for extracting emotional data from user interactions; means for extracting targets based on the emotional data and automatically generating an optimal distribution scenario using AI; means for automatically generating advertising content using a generative AI model; means for a designer to adjust the generated content and distribution scenario; means for using AI to detect legal risks and compliance with brand guidelines of the advertising content and present it to the legal department; means for delivering the generated advertising content to target users and performing A / B testing; means for evaluating the delivery results using a BI tool and measuring CTR, CVR, and ROI; means for analyzing the evaluation results using AI and improving the distribution scenario and content; and means for marketers and designers to make final adjustments based on the AI's improvement suggestions. This enables efficient and effective digital marketing.

[0329] "Product Concept" refers to the main idea or features of the product or service you offer.

[0330] "Internal data" refers to information generated or collected within a company that is used for analysis or application within a system.

[0331] "External data" refers to information obtained from outside the company, such as data on trends and markets, that is used in analysis in combination with internal data.

[0332] "Emotional data" refers to emotional states (e.g., positive, negative) extracted from user input and interactions.

[0333] "Target" refers to a group of users to whom marketing is directed based on specific conditions or attributes.

[0334] A "distribution scenario" refers to a plan or strategy for how to deliver advertisements to a target audience.

[0335] A "generative AI model" refers to an artificial intelligence model that automatically generates content such as text, images, and videos based on pre-trained algorithms.

[0336] "Designer" refers to a professional who makes final adjustments to generated content, modifying it to meet visual satisfaction and brand guidelines.

[0337] "Legal risk" refers to potential problems that may arise from advertising content violating laws or regulations.

[0338] "Brand guidelines" refer to regulations regarding design and expression that are intended to maintain consistency in a company or product brand.

[0339] "Influential target users" refers to a specific user group for whom advertising content may have a high influence or potential effect.

[0340] "AB testing" refers to a method of comparing two or more versions of advertising content and measuring their effectiveness.

[0341] "BI tools" refers to software used for business intelligence, tools that support data analysis and report creation.

[0342] "CTR" stands for Click Through Rate, and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[0343] "CVR" stands for conversion rate, and refers to the ratio of the number of times users who clicked on an ad actually took the target action, such as purchasing or registering.

[0344] "ROI" stands for Return on Investment and refers to the ratio of return on investment for advertising and marketing initiatives.

[0345] "Final adjustment" refers to the process in which human experts make final corrections and fine-tuning to AI suggestions and automatically generated content.

[0346] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[0347] Hardware and software used

[0348] Hardware: Servers, terminals, user input devices (e.g., PCs, tablets, smartphones)

[0349] Software: Generative AI models, emotion engines, BI tools

[0350] Explanation of the program's processing steps

[0351] 1. User side

[0352] The user uses the terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user inputs the following information about a "new health drink."

[0353] Product concept: A new health drink

[0354] Insight: Staying healthy in a busy life

[0355] Benefit: Easy health

[0356] Competitive comparison information: Comparison data with similar competing products

[0357] 2. Server side

[0358] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0359] 3. Emotion Data Analysis

[0360] The server uses an emotion engine to extract emotion data from user input and user interactions. Specifically, it analyzes the tone and expression of the text entered by the user to determine the user's emotional state (e.g., positive, negative).

[0361] 4. Generating a distribution scenario

[0362] The server extracts targets based on emotional data and automatically generates optimal distribution scenarios using AI. Targets such as "office workers with positive emotions" and "sports enthusiasts feeling tired" are set using an emotion engine, and distribution scenarios are generated based on these targets.

[0363] 5. Content Generation

[0364] The server uses a generative AI model to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a catchy slogan such as "Get healthy easily" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals to match the user's emotions.

[0365] 6. Content Selection and Tuning

[0366] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color tone, font, and placement.

[0367] 7. Legal Brand Check

[0368] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​identifies legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0369] 8. Execution of distribution

[0370] The device delivers content to target users based on the delivery scenario and advertising content received from the server, and conducts AB testing.Specifically, the device delivers a "Easy Health" version and a "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[0371] 9. Measurement

[0372] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Post-delivery data is collected and the evaluation indicators for each target group are analyzed.

[0373] 10. Analysis and improvement of results

[0374] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0375] 11. Final tuning

[0376] Users (especially marketers and designers) review the AI's suggestions and adjust the final ad content and delivery scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary.

[0377] Examples of prompt statements

[0378] For example, a possible prompt for an AI model might be:

[0379] Create a marketing campaign for a new health drink. The product concept should be "Staying healthy in a busy life," the benefit should be "Getting healthy easily," and include comparative information about competing products. Target office workers and sports enthusiasts.

[0380] This system makes it possible to carry out digital marketing efficiently even without specialized knowledge. In addition, by combining it with an emotion engine, it is possible to optimize delivery scenarios and advertising content in response to user emotions, resulting in more effective digital marketing. Automating the entire process from product concept to delivery, evaluation, and improvement can save costs and time.

[0381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0382] Step 1:

[0383] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a dedicated form. The input data includes the product concept, insights (e.g., maintaining health in a busy lifestyle), benefits (e.g., easily achieving health), and competitive comparison information (e.g., comparison data with similar competing products). The input data is sent to the server.

[0384] Output: The product concept data entered by the user is sent to the server.

[0385] Step 2:

[0386] The server stores the product concept data received from the user in an internal database. Then, the server uses APIs to obtain related external data (market data, trend data), collects market trends and past advertising data, and stores it in the database.

[0387] Input: Product concept data entered by the user

[0388] Output: Product concept data stored in an internal database and retrieved external data

[0389] Step 3:

[0390] The server uses an emotion engine to extract emotion data from user input data and user interactions by analyzing the tone and expression of the user-entered text and identifying the user's emotional state (e.g., positive, negative).

[0391] Input: User-entered product concept data and external data

[0392] Output: User emotion data

[0393] Step 4:

[0394] The server extracts targets based on emotional data and automatically generates optimal distribution scenarios using AI. Using an emotion engine, targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" are set, and distribution scenarios are generated based on those targets.

[0395] Input: User emotion data

[0396] Output: AI-generated delivery scenarios

[0397] Step 5:

[0398] The server uses a generative AI model to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a tagline such as "Get healthy easily" and an image of an office worker drinking a drink.

[0399] Input: AI-generated delivery scenario

[0400] Output: Ad content generated by the generative AI model

[0401] Step 6:

[0402] The server sends the generated advertising content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and adjusts the color tone, font, placement, etc. The adjusted content is then sent back to the server.

[0403] Input: Ad content generated by a generative AI model

[0404] Output: Ad content finalized by designer

[0405] Step 7:

[0406] The server uses AI to automatically detect legal risks and compliance with brand guidelines in the generated advertising content. The AI ​​identifies areas of legal risk in the ad copy and checks whether appropriate contact information is included.

[0407] Input: Ad content finalized by designer

[0408] Output: Legal risk and brand guideline compliance detection results

[0409] Step 8:

[0410] The device delivers content to target users based on the delivery scenario and advertising content received from the server, and conducts AB testing. Specifically, the device delivers a "Easy Health" version and a "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[0411] Input: Delivery scenario and ad content

[0412] Output: Content delivery results to target users

[0413] Step 9:

[0414] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Post-delivery data is collected and the evaluation indicators for each target group are analyzed.

[0415] Input: Distribution result data

[0416] Output: Evaluation metrics such as CTR, CVR, ROI, etc.

[0417] Step 10:

[0418] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in advertisements aimed at office workers and suggests new images and text.

[0419] Input: Evaluation metrics such as CTR, CVR, ROI, etc.

[0420] Output: AI-generated improvement measures

[0421] Step 11:

[0422] Users (especially marketers and designers) review the AI's suggestions and adjust the final ad content and delivery scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary.

[0423] Input: AI-generated improvement measures

[0424] Output: Final adjusted ad content and delivery scenario

[0425] (Application example 2)

[0426] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0427] Modern digital marketing requires the delivery of advertisements tailored to diverse product concepts, and in particular the generation of delivery scenarios and advertising content that take emotions into account. However, conventional systems lack the functionality to properly analyze and reflect user emotions, making it difficult to effectively approach target users. Furthermore, this requires a lot of effort from designers and marketers, making efficient marketing activities difficult.

[0428] The specification processing by the specification 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 receiving a product concept from a user; means for automatically generating a distribution scenario using AI based on the received product concept; means for automatically generating advertising content using AI based on the automatically generated distribution scenario; means for a designer to adjust the generated content and distribution scenario; means for using AI to detect the legal risks of the advertising content and its conformity with brand guidelines and present them to the legal department; means for delivering the generated advertising content to influential target users and performing AB testing; means for evaluating the delivery results using a BI tool and measuring CTR, CVR, and ROI; means for analyzing the evaluation results using AI and improving the delivery scenario and content; and means for analyzing user emotion data in real time and generating advertising content based on the data. This makes it possible to generate and improve optimal delivery scenarios and advertising content according to user emotions.

[0429] "Product concept" refers to the basic idea, features, and value proposition of a product.

[0430] A "delivery scenario" refers to a plan or strategy for effectively delivering advertisements or content to specific target users.

[0431] "Automatic generation with AI" refers to the process of using artificial intelligence technology to generate scenarios and content based on data and information without manual operation.

[0432] "Advertising Content" refers to media such as text, images, and video created as part of a marketing effort.

[0433] "Designer adjustments" refers to experts reviewing the generated content and scenarios and making any necessary corrections or optimizations.

[0434] "Legal risk" refers to the possibility that an ad may violate laws, regulations, or other laws.

[0435] "Brand guidelines" refer to guidelines and rules established to maintain the brand image of a company or product.

[0436] A "legal department" refers to a department within a company that specializes in assessing and responding to legal risks.

[0437] "AB testing" refers to a method of simultaneously delivering two or more versions of advertising content and comparing and analyzing their effectiveness.

[0438] "CTR" stands for click-through rate, which refers to the percentage of ads that are clicked on.

[0439] "CVR" stands for conversion rate, which refers to the percentage of ads that achieve the intended goal (such as a purchase or registration).

[0440] "ROI" stands for return on investment, and refers to the profits brought by advertising or marketing activities divided by the amount invested.

[0441] "BI tools" refers to business intelligence tools, software that supports data analysis and reporting.

[0442] "Emotion data" refers to information that represents the user's emotional state.

[0443] "Real-time analysis" refers to analyzing data as it is entered.

[0444] "Influential target users" refer to users who have a strong interest in the content of advertisements and content and are likely to influence purchasing behavior and attitudes.

[0445] The present invention is a system for automatically generating optimal advertising content in response to a user's emotions and distributing the content. A specific embodiment of this system is described below.

[0446] System configuration

[0447] This system includes a user terminal, a server, and an interface that allows manual adjustments by the designer. The user terminal refers to a smartphone or PC, and the server is a computer equipped with a high-performance processor and storage.

[0448] Hardware and Software

[0449] Hardware: smartphones, PCs, servers

[0450] Software: OpenAI API, Python, TextBlob, Pandas, BI tools

[0451] Data processing and calculation

[0452] User device:

[0453] Users use the terminal to input product concept, insights, benefits, and competitive comparison information. For example, a user might enter information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0454] server:

[0455] The server stores the product concept data received from the user in an internal database and acquires related external data (market data, trend data). It collects market trends and past advertising data and stores them in the database.

[0456] The server then uses an emotion engine to extract emotional data from the user's input data and interactions. It uses the TextBlob library to parse the emotional state, such as positive or negative, from the tone and expression of the text entered by the user.

[0457] The server then uses AI to extract targets based on the emotional data and automatically generates the optimal broadcast scenario. The emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired," and generates a broadcast scenario based on those targets.

[0458] The server then uses the OpenAI API to automatically generate advertising content, including text, images, and videos, that reflect the product concept and emotional data. For example, the AI ​​generates a tagline such as "Easily achieve good health" and an image of an office worker drinking a drink.

[0459] The generated content is then sent to a designer via a user interface, who adjusts color, font, placement, etc. After this adjustment, the server uses AI to automatically detect legal risks and compliance with brand guidelines for the ad content and presents the results to the legal department.

[0460] User device:

[0461] Finally, the user device distributes the content to the target users based on the distribution scenario and content received from the server, and performs A / B testing. For example, a "Easy Health" version and a "Post-Sports Recovery" version are distributed to different target groups, and the effectiveness for each group is measured.

[0462] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. The delivery results are collected and the evaluation indicators for each target group are analyzed.

[0463] Improved evaluation results:

[0464] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. For example, the AI ​​may identify that there is a problem with the visuals in an advertisement for office workers and suggest new images and text.

[0465] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Marketers review the suggested improvements and make manual adjustments as necessary.

[0466] Examples of prompts:

[0467] Product concept: Maintaining health in a busy lifestyle

[0468] Target audience: office workers and sports enthusiasts

[0469] User Emotion: Positive Mood

[0470] Generated ad text:

[0471] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0472] Step 1:

[0473] Users use their smartphones or computers to input product concepts, insights, benefits, and competitive comparison information. Specifically, they enter information such as "a new health drink," "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products" into a form. This input data is then sent to the server.

[0474] Step 2:

[0475] The server stores the received product concept data in an internal database. At the same time, it acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database. The input is the user's concept data, and the output is the saved internal database.

[0476] Step 3:

[0477] The server uses an emotion engine to extract emotion data from user input data and user interactions. Specifically, it uses the TextBlob library to analyze the user's emotional state (positive, negative, etc.) from the tone and expression of the text entered by the user. The input is the user's text data, and the output is the analyzed emotion data.

[0478] Step 4:

[0479] The server uses AI to extract targets based on the emotional data and automatically generates the optimal distribution scenario. Specifically, the emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" and generates a distribution scenario based on them. The input is emotional data and the output is a distribution scenario.

[0480] Step 5:

[0481] The server uses the OpenAI API to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a catchphrase such as "Get healthy easily" and an image of an office worker drinking a drink. The input is the distribution scenario, and the output is the advertising content.

[0482] Step 6:

[0483] The generated content is sent to the designer through a user interface, who adjusts color, font, placement, etc. Specifically, the designer reviews the generated images and text and makes any necessary corrections. The input is the advertising content, and the output is the adjusted advertising content.

[0484] Step 7:

[0485] The server uses AI to automatically detect legal risks in advertising content and compliance with brand guidelines, and presents the results to the legal department. Specifically, the AI ​​detects and reports legal risks and violations of brand guidelines in advertising copy. The input is the adjusted advertising content, and the output is the legal risk detection results.

[0486] Step 8:

[0487] The user device delivers content to target users based on the delivery scenario and content received from the server, and conducts AB testing. Specifically, a "Easy Health" version and a "Post-Sports Recovery" version are delivered to different target groups, and the effectiveness for each group is measured. The input is the delivery scenario and advertising content, and the output is the AB test results.

[0488] Step 9:

[0489] The server uses a BI tool to measure the CTR, CVR, ROI, etc. of the delivered content in real time. Specifically, it collects post-delivery data and analyzes the evaluation indicators for each target group. The input is the AB test results, and the output is the evaluation indicators.

[0490] Step 10:

[0491] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in advertisements for office workers and suggests new images and text. The input is the evaluation index, and the output is the improvement measures.

[0492] Step 11:

[0493] Users (marketers and designers) review the AI's suggestions and adjust the final content and distribution scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary. The input is the improvements, and the output is the final adjusted content and distribution scenario.

[0494] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0495] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0496] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0497] [Second embodiment]

[0498] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0499] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0500] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0501] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0502] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0504] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0505] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0506] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0507] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0508] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0509] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0510] This invention is a system that automatically executes digital marketing by inputting a product concept into AI. This system includes the processes of inputting the product concept, formulating a distribution scenario, creating content, legal and brand checks, distributing content to the target, measuring effectiveness, and making improvements based on the results.

[0511] Program processing

[0512] User side

[0513] 1. Enter the product concept

[0514] Users use the terminal to input product concepts, insights (consumer insights), benefits, and competitive comparison information.

[0515] Example: A user inputs information about a "new health drink," such as "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products" on a terminal.

[0516] Server side

[0517] 2. Data Reception and Analysis

[0518] The server compares the product concept data received from the user with internal data and external data (market data, trend data) and performs analysis.

[0519] Example: The server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[0520] 3. Generating a distribution scenario

[0521] The server automatically generates a distribution scenario using AI based on the selected target.

[0522] Example: AI generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (social media, email, etc.) for each target.

[0523] 4. Content Generation

[0524] The server uses AI to automatically generate content such as text, images, and videos based on the distribution scenario.

[0525] Example: AI generates the tagline "Easy Health" along with an image of an office worker drinking a drink.

[0526] 5. Content Selection and Tuning

[0527] The designer checks the content generated by the server and makes any final adjustments.

[0528] Example: A designer reviews the generated images and text and adjusts color, font, placement, etc.

[0529] 6. Legal Brand Check

[0530] The server uses AI to automatically detect legal risks and compliance with brand guidelines for content and presents them to the legal department.

[0531] Example: AI detects legal risks in ad copy and checks whether appropriate contact information is included. The results are reported to the legal department.

[0532] Terminal side

[0533] 7. Execution of distribution

[0534] The terminal delivers content to target users based on the distribution scenario and content received from the server and conducts AB testing.

[0535] Example: The device delivers a "quick health" version and a "post-sports recovery" version to different target groups (office workers and sports enthusiasts), and measures the effectiveness for each group.

[0536] 8. Effectiveness Measurement

[0537] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time.

[0538] Example: The server collects data after delivery, analyzes and displays the click rate and conversion rate for each target group.

[0539] Server side

[0540] 9. Analysis and improvement of results

[0541] The server uses AI to analyze the distribution results, analyze the difference between the predicted effect and the actual results, identify the cause, and automatically generate improvement measures.

[0542] Example: AI identifies that the visuals are the cause of low click-through rates on ads for office workers and suggests new images and text.

[0543] User side

[0544] 10. Final tuning

[0545] Users (especially marketers and designers) review the AI's suggestions and adjust the actual content and distribution scenarios.

[0546] Example: Marketers review suggested improvements and make manual adjustments as needed.

[0547] This invention makes it possible to efficiently carry out digital marketing even without specialized knowledge. This system automates the entire process, from product concept to distribution, evaluation, and improvement, thereby saving costs and time.

[0548] The processing flow will be explained below.

[0549] Step 1:

[0550] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0551] Step 2:

[0552] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0553] Step 3:

[0554] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[0555] Step 4:

[0556] AI automatically generates optimal delivery scenarios for the extracted targets. Scenarios include the message, delivery channel, delivery timing, etc. Specific actions that can be generated include "delivering social media ads to office workers on weekday mornings" and "delivering email ads on weekends to sports enthusiasts."

[0557] Step 5:

[0558] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Get healthy easily" and an image of an office worker holding a health drink.

[0559] Step 6:

[0560] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and fine-tunes the color tone, font, placement, etc.

[0561] Step 7:

[0562] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0563] Step 8:

[0564] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[0565] Step 9:

[0566] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[0567] Step 10:

[0568] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[0569] Step 11:

[0570] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0571] Step 12:

[0572] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[0573] Example 1

[0574] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0575] In traditional digital marketing, the process from entering product concepts to distributing advertising content, measuring effectiveness, and making improvements is often done manually, which not only takes a great deal of time and effort but also requires specialized knowledge, resulting in problems of inefficiency.In addition, checking whether the generated advertising content complies with legal risks and brand guidelines is often done manually, which poses challenges in terms of the time and human resources required for the checking process to avoid legal risks.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0577] In this invention, the server includes means for receiving a product concept from a user, means for automatically generating a distribution scenario based on the received product concept using a generative AI model, and means for generating advertising content based on the distribution scenario automatically generated using the generative AI model. This makes it possible to provide an environment in which a user simply inputs a product concept, and the AI ​​automatically generates a distribution scenario and advertising content, enabling a series of digital marketing processes to be executed quickly and efficiently.

[0578] A "product concept" is an idea or strategy that includes the basic purpose and characteristics of a product or service, target market, competitive analysis, etc.

[0579] "Means for receiving" refers to a function or process for acquiring data input by a user.

[0580] A "generative AI model" refers to artificial intelligence technology and algorithms that automatically generate scenarios and content based on input information from users.

[0581] A "distribution scenario" is a plan that defines what advertising content will be distributed to a specific target, at what timing, and through which channel.

[0582] "Advertising content" refers to promotional materials such as text, images, and videos created based on a distribution scenario.

[0583] A "creator" is a professional who is responsible for the final design and adjustment of advertising content.

[0584] "Legal risk" refers to the possibility that advertising content may violate laws or regulations.

[0585] "Brand guidelines" are rules regarding design and messaging established to maintain a company's brand image.

[0586] A "legal department" is a department within a company or organization that manages and deals with legal issues and risks.

[0587] "Target users" refers to the customer demographic that is anticipated when delivering advertisements, specifically the recipients of the advertisements.

[0588] "AB testing" is a method of comparing two or more versions of an advertisement or piece of content to determine which is more effective.

[0589] "Analysis tools" refer to software and platforms for collecting and analyzing data and visualizing the results.

[0590] "Click-through rate" refers to the percentage of clicks on an ad compared to the number of times it is displayed.

[0591] "Conversion rate" is the percentage of ads that result in a targeted action (such as a purchase or registration).

[0592] "Return on investment" is an indicator that evaluates how much profit is gained from the resources invested in advertising and marketing activities.

[0593] "Evaluation results" refer to various indicators (click-through rate, conversion rate, return on investment, etc.) obtained using analysis tools after advertising is delivered.

[0594] "Root cause analysis" is the process of identifying the causes of problems or lack of effectiveness with advertising or content.

[0595] "Improvement measures" are specific action plans to address identified problems and causes.

[0596] A "marketer" is a professional who is responsible for marketing activities in a company or organization.

[0597] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. The main elements that make up the system are users, devices, and servers, each of which plays a specific role.

[0598] First, the user uses a terminal to input the product concept, insights (consumer insights), benefits, and competitive comparison information. For example, for a new health drink, the user can input insights and benefits such as "maintaining health in a busy life" and "easily achieving health," as well as "comparison data with similar competitive products." This information is sent to the server via the terminal.

[0599] The server compares the received product concept data with its internal database and external data (market data, trend data) and performs an analysis. This analysis uses an AI model (e.g., machine learning algorithms, data analysis tools, etc.). Specifically, the server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[0600] Next, the server automatically generates a distribution scenario based on the selected targets using a generative AI model (e.g., natural language processing model). For example, the AI ​​could generate a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts," and select the optimal distribution channel (e.g., social media, email) for each target.

[0601] The server then uses a generative AI model to automatically generate advertising content such as text, images, and videos based on the distribution scenario. This process uses tools such as DeepArt for image generation and Synthesia for video generation. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[0602] The generated content and distribution scenarios are then checked by a designer, who makes final adjustments using design tools such as Adobe Creative Cloud to adjust color tones, fonts, and image placement.

[0603] The server then uses AI to detect legal risks and compliance with brand guidelines in the ad content. For example, it uses Compliance AI tools to check for potential legal risks in the ad copy, checks for violations of guidelines, and reports the results to the legal department.

[0604] The device then delivers content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the device delivers advertisements for "easy health" and "recovery after sports" to different target groups (office workers and sports enthusiasts) and measures the effectiveness of each.

[0605] Finally, the server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time and analyze the results. Based on this evaluation, the AI ​​analyzes the cause and presents improvement measures, and marketers and designers make final adjustments.

[0606] An example prompt is:

[0607] Please enter your product concept for a "new healthy drink." Please include specific consumer insights, benefits, and competitive comparison information.

[0608] example:

[0609] Insight: "Staying healthy in a busy life"

[0610] Benefit: "Easy to get healthy"

[0611] Competitive comparison: "Comparative data with similar competing products"

[0612] As a result, this system automates the entire process from product concept to distribution, evaluation, and improvement, resulting in significant cost and time savings.

[0613] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0614] Step 1:

[0615] The user uses a terminal to input and submit a product concept. Specifically, the user enters the concept of a "new health drink," along with insights (e.g., "Maintaining health in a busy life"), benefits (e.g., "Easily achieve health"), and competitive comparison information into the form, and clicks the submit button. The input information is sent from the terminal to the server.

[0616] Input: Product concept, insights, benefits, competitive comparison information

[0617] Output: Product concept data sent to the server

[0618] Step 2:

[0619] The server analyzes the product concept data received from the user by comparing it with the internal database and external data (market data, trend data). Specifically, the server analyzes the user's input data using past sales data and consumer reviews from the internal database, as well as market trend data obtained through external APIs. An AI model is used in this analysis to select the optimal target users.

[0620] Input: Product concept data, internal database, external data

[0621] Output: Analysis results (e.g., "health-conscious working generation" and "sports enthusiasts")

[0622] Step 3:

[0623] The server automatically generates a distribution scenario based on the selected target using a generative AI model. Specifically, it uses a generative AI model (e.g., a natural language processing model) to create scenarios for a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts." It also selects the optimal distribution channel (e.g., social media, email, etc.) for each target.

[0624] Input: Analysis results, generated AI model

[0625] Output: Delivery scenario

[0626] Step 4:

[0627] The server uses the generative AI model to automatically generate advertising content based on the generated distribution scenario. Specific operations include using a natural language generation model to generate text, an image generation tool (e.g., DeepArt) to generate images, and a video generation tool (e.g., Synthesia) to generate videos. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[0628] Input: Delivery scenario, generative AI model

[0629] Output: Ad content (text, images, videos)

[0630] Step 5:

[0631] Creators adjust the content and distribution scenarios generated by the server. Specifically, creators use design tools (e.g., Adobe Creative Cloud) to adjust the color tone, font, and placement of generated images and text.

[0632] Input: Ad content, distribution scenario

[0633] Output: Adjusted advertising content, distribution scenario

[0634] Step 6:

[0635] The server uses AI to detect legal risks and compliance with brand guidelines in advertising content and presents the results to the legal department. Specifically, it uses legal risk detection tools (e.g., Compliance AI) to analyze content and checks compliance with guidelines.

[0636] Input: Tailored ad content

[0637] Output: Legal risk and brand guideline compliance detection results

[0638] Step 7:

[0639] The device delivers content to target users based on the delivery scenario and content received from the server, and performs AB testing. Specifically, an ad management tool (e.g., Facebook Ads Manager) is used for delivery, and different versions of ads are delivered to different target groups.

[0640] Input: Distribution scenario, advertising content

[0641] Output: Advertisements delivered to target users, AB test results

[0642] Step 8:

[0643] The server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time. Specifically, it collects and visualizes user data after ad delivery and analyzes the effectiveness indicators for each target group.

[0644] Input: AB test results, target user data

[0645] Output: Effectiveness measurement results (CTR, CVR, ROI)

[0646] Step 9:

[0647] The server uses AI to analyze the results of effectiveness measurements, analyzes the difference between predicted and actual results to identify the cause, and automatically generates improvement measures.Specifically, it uses an AI model (e.g., machine learning algorithm) to generate new suggestions for identified problems.For example, it may identify that the cause of a low click-through rate is visual and suggest new images and text.

[0648] Input: Effectiveness measurement results

[0649] Output: Cause analysis, improvement suggestions

[0650] Step 10:

[0651] Users (especially marketers and creators) review the AI's suggestions and make final adjustments to the actual content and distribution scenario. Specifically, marketers adjust distribution schedules and targeting based on the suggestions, and creators make suggested design improvements.

[0652] Input: Improvement suggestion

[0653] Output: Final adjusted ad content and distribution scenario

[0654] (Application example 1)

[0655] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0656] In the field of digital marketing, there is a demand for automation of the creation, distribution, effectiveness measurement, and improvement of effective advertising campaigns. Conventional methods require marketers to expend a lot of time and effort and specialized knowledge, resulting in inefficiency and high costs. In addition, it is difficult to measure the effectiveness of ads in real time or make quick improvements after they are delivered. This poses a challenge in maximizing the effectiveness of advertising investments.

[0657] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0658] In this invention, the server includes: means for receiving a product concept from a user; means for automatically generating a distribution scenario using AI based on the received product concept; means for automatically generating advertising content using AI based on the automatically generated distribution scenario; means for a designer to adjust the generated content and distribution scenario; means for detecting legal risks of the advertising content and compliance with brand guidelines using AI and presenting the results to the legal department; means for delivering the generated advertising content to target users via their smart devices and performing A / B testing; means for evaluating real-time data collected from the smart devices using a BI tool and measuring CTR, CVR, and ROI; and means for analyzing the evaluation results using AI and automatically improving the advertising content and distribution scenario. This enables the automation of effective advertising campaigns.

[0659] "Product concept" refers to detailed information about a product or service, such as its features, benefits, and target users.

[0660] "User" means a person or entity that utilizes the System to enter product concepts and manage advertising campaigns.

[0661] A "distribution scenario" refers to a plan for distributing content to specific target users through what channels and at what timing.

[0662] "AI" refers to artificial intelligence technology, which includes algorithms and models for automatically solving specific problems.

[0663] "Advertising Content" refers to materials such as text, images, and video created for advertising purposes.

[0664] "Designer" refers to the person who makes the final adjustments to the generated advertising content and visually optimizes it.

[0665] "Legal risk" refers to the risk that advertising content may violate the law.

[0666] "Brand guidelines" refer to standards for design and messaging established to maintain brand consistency.

[0667] "Legal Department" means the department within an organization that considers and resolves legal matters.

[0668] "Target users" refers to the group of users who are intended to receive a particular message of an advertising campaign.

[0669] "Smart devices" refers to advanced electronic devices with internet connectivity, such as smartphones, tablets, and smart glasses.

[0670] "AB testing" refers to a testing method in which different versions of advertising content are simultaneously delivered to target users and their effectiveness is compared.

[0671] "BI tool" stands for business intelligence tool and refers to software that analyzes data to support business decision-making.

[0672] "CTR" stands for click-through rate and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[0673] "CVR" stands for conversion rate and refers to the percentage of times a specific action (purchase, registration, etc.) is performed.

[0674] "ROI" stands for return on investment and refers to an indicator that financially evaluates the effectiveness of the money invested in an advertising campaign.

[0675] "Real-time data" refers to data that is collected continuously from the moment an ad is delivered.

[0676] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. This system is divided into a user side and a server side.

[0677] User side

[0678] Entering product concepts

[0679] Users use a smartphone app to input product concepts, insights, benefits, and competitive analysis information. For example, for a "new health drink," users can input "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0680] Server side

[0681] Data reception and analysis

[0682] The server analyzes the product concept data received from users by comparing it with internal and external data. This analysis uses artificial intelligence (AI) models such as TensorFlow. The optimal target users are selected based on market and trend data. As a specific example, trend data from the health drink market is analyzed to select "health-conscious working people" and "sports enthusiasts" as targets.

[0683] Generating a distribution scenario

[0684] The server automatically generates distribution scenarios using AI based on the selected target users. For example, the AI ​​generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (SNS, email, etc.) for each target.

[0685] Content Generation

[0686] The server uses AI to generate advertising content such as text, images, and videos based on a distribution scenario. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[0687] Legal Brand Check

[0688] AI is used to detect legal risks and compliance with brand guidelines in generated advertising content, and presents the results to the legal department. For example, AI can detect legal risks in advertising copy and check whether appropriate contact information is included.

[0689] Terminal side

[0690] Executing the distribution

[0691] The smartphone app delivers advertising content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the app delivers two versions, "Easy Health" and "Post-Sports Recovery," to different target groups (office workers and sports enthusiasts), and measures the effectiveness of each.

[0692] Effectiveness measurement

[0693] The server uses BI (business intelligence) tools to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered advertising content in real time. For example, the server collects data after delivery and analyzes and displays the click-through rate and conversion rate of each target group. For this purpose, BI tools such as Tableau are used.

[0694] Results analysis and improvement

[0695] The server uses AI to analyze the results of distribution, analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. For example, the AI ​​may identify that the visuals are the cause of the low click-through rate of ads aimed at office workers, and suggest new images and text.

[0696] User side

[0697] Final Tuning

[0698] Users, especially marketers and designers, review the AI ​​suggestions and adjust the actual content and distribution scenarios. For example, marketers review the suggested improvements and make manual adjustments as necessary.

[0699] Prompt Sentence Examples

[0700] Product concept: A new health drink

[0701] Consumer Insights: Busy lifestyles and the need to stay healthy

[0702] Benefit: Easy health

[0703] Competitive comparison: Comparison data with similar competing products

[0704] In this way, effective advertising campaigns can be automated and efficiently executed.

[0705] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0706] Step 1:

[0707] Users use a smartphone app to input product concepts, consumer insights, profits, and competitive analysis information.

[0708] For example, the user inputs "new healthy drink" along with consumer insights and comparison data with competing products. The device then sends this data to the server.

[0709] Step 2:

[0710] The server analyzes the product concept data received from the user by comparing it with internal data and external data.

[0711] This analysis uses AI models such as TensorFlow. The server selects the optimal target users based on market and trend data. The output is a list of target users (e.g., "health-conscious working generation" or "sports enthusiasts").

[0712] Step 3:

[0713] The server automatically generates a distribution scenario using AI based on the target users.

[0714] For example, AI can generate "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and select the optimal distribution channel (e.g., social media or email) for each target. Specific distribution scenarios are generated as an output.

[0715] Step 4:

[0716] The server automatically generates advertising content using AI based on the generated distribution scenario.

[0717] Specifically, it generates advertising materials such as text, images, and videos. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink. The output is the completed advertising content.

[0718] Step 5:

[0719] Use AI to detect legal risks and compliance with brand guidelines before presenting server-generated ad content to the legal department.

[0720] For example, AI can detect legal risks and brand guideline violations in ad copy and report the results to the legal department. The output is a check result for legal risk and brand suitability.

[0721] Step 6:

[0722] The device delivers advertising content to target users based on the delivery scenario and content received from the server, and performs AB testing.

[0723] For example, we deliver two versions of the AB test, one for "easy health" and the other for "recovery after sports" to different target groups (office workers and sports enthusiasts), and measure their effectiveness. The input is the delivery scenario and content from the server, and the output is the results of the AB test.

[0724] Step 7:

[0725] The server uses a BI tool (e.g., Tableau) to measure the effectiveness of advertising content in real time.

[0726] It calculates and analyzes metrics such as click-through rate (CTR), conversion rate (CVR), and return on investment (ROI). The input is user response data to delivered advertising content, and the output is the real-time measurement results of these metrics.

[0727] Step 8:

[0728] The server uses AI to analyze the distribution results and analyze the difference between the predicted effect and the actual results.

[0729] For example, AI can identify that the low click-through rate of ads for office workers is due to visuals and suggest new images and text. The input is effectiveness measurement data, and the output is the results of an analysis of the causes and suggestions for improvement.

[0730] Step 9:

[0731] The user reviews the AI's suggestions and makes manual adjustments if necessary.

[0732] Marketers and designers review the proposed improvements and make final adjustments to the content and distribution scenario. The input is the improvement suggestions from the AI, and the output is the final adjusted advertising content and distribution scenario.

[0733] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0734] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[0735] Program processing

[0736] User side

[0737] 1. Enter the product concept

[0738] The user uses the terminal to input the product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into the form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0739] Server side

[0740] 2. Data Reception and Analysis

[0741] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0742] 3. Emotion Data Analysis

[0743] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[0744] 4. Generating a distribution scenario

[0745] The server extracts targets based on the emotional data and automatically generates optimal distribution scenarios using AI. Specifically, the emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" and generates distribution scenarios based on them.

[0746] 5. Content Generation

[0747] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[0748] 6. Content Selection and Tuning

[0749] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color, font, and placement.

[0750] 7. Legal Brand Check

[0751] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0752] Terminal side

[0753] 8. Execution of distribution

[0754] The device distributes content to target users based on the distribution scenario and content received from the server, and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[0755] 9. Measurement

[0756] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[0757] Server side

[0758] 10. Analysis and improvement of results

[0759] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0760] User side

[0761] 11. Final tuning

[0762] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[0763] This invention enables efficient digital marketing even without specialized knowledge. Furthermore, by combining it with an emotion engine, distribution scenarios and advertising content can be optimized to match user emotions, resulting in more effective digital marketing. This system automates the entire process, from product conception through distribution, evaluation, and improvement, thereby saving time and money.

[0764] The processing flow will be explained below.

[0765] Step 1:

[0766] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0767] Step 2:

[0768] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0769] Step 3:

[0770] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[0771] Step 4:

[0772] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[0773] Step 5:

[0774] Based on the extracted target and emotional data, AI automatically generates optimal distribution scenarios. The scenarios include the message, distribution channel, and distribution timing. Specific actions generated include "delivering morning social media ads to office workers with positive emotions" and "delivering weekend email ads to sports enthusiasts feeling tired."

[0775] Step 6:

[0776] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[0777] Step 7:

[0778] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and adjusts the color tone, font, and placement.

[0779] Step 8:

[0780] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0781] Step 9:

[0782] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[0783] Step 10:

[0784] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[0785] Step 11:

[0786] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[0787] Step 12:

[0788] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0789] Step 13:

[0790] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[0791] Example 2

[0792] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0793] Modern digital marketing requires efficient and effective delivery of advertising content, but traditional methods have the following problems:

[0794] 1. The process from entering product concepts to generating distribution scenarios is done manually, which is time-consuming and costly.

[0795] 2. Delivery scenarios and advertising content are created uniformly and do not respond to the emotions and needs of target users.

[0796] 3. Because effectiveness measurement and analysis are done manually, improvement measures are delayed. Also, because A / B testing and its effectiveness measurement cannot be carried out efficiently, it is difficult to optimize advertising.

[0797] The present invention aims to solve these problems and provide a system that realizes efficient and effective digital marketing.

[0798] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0799] In this invention, the server includes: means for receiving a product concept from a user; means for comparing and analyzing the received product concept with internal data and external data; means for extracting emotional data from user interactions; means for extracting targets based on the emotional data and automatically generating an optimal distribution scenario using AI; means for automatically generating advertising content using a generative AI model; means for a designer to adjust the generated content and distribution scenario; means for using AI to detect legal risks and compliance with brand guidelines of the advertising content and present it to the legal department; means for delivering the generated advertising content to target users and performing A / B testing; means for evaluating the delivery results using a BI tool and measuring CTR, CVR, and ROI; means for analyzing the evaluation results using AI and improving the distribution scenario and content; and means for marketers and designers to make final adjustments based on the AI's improvement suggestions. This enables efficient and effective digital marketing.

[0800] "Product Concept" refers to the main idea or features of the product or service you offer.

[0801] "Internal data" refers to information generated or collected within a company that is used for analysis or application within a system.

[0802] "External data" refers to information obtained from outside the company, such as data on trends and markets, that is used in analysis in combination with internal data.

[0803] "Emotional data" refers to emotional states (e.g., positive, negative) extracted from user input and interactions.

[0804] "Target" refers to a group of users to whom marketing is directed based on specific conditions or attributes.

[0805] A "distribution scenario" refers to a plan or strategy for how to deliver advertisements to a target audience.

[0806] A "generative AI model" refers to an artificial intelligence model that automatically generates content such as text, images, and videos based on pre-trained algorithms.

[0807] "Designer" refers to a professional who makes final adjustments to generated content, modifying it to meet visual satisfaction and brand guidelines.

[0808] "Legal risk" refers to potential problems that may arise from advertising content violating laws or regulations.

[0809] "Brand guidelines" refer to regulations regarding design and expression that are intended to maintain consistency in a company or product brand.

[0810] "Influential target users" refers to a specific user group for whom advertising content may have a high influence or potential effect.

[0811] "AB testing" refers to a method of comparing two or more versions of advertising content and measuring their effectiveness.

[0812] "BI tools" refers to software used for business intelligence, tools that support data analysis and report creation.

[0813] "CTR" stands for Click Through Rate, and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[0814] "CVR" stands for conversion rate, and refers to the ratio of the number of times users who clicked on an ad actually took the target action, such as purchasing or registering.

[0815] "ROI" stands for Return on Investment and refers to the ratio of return on investment for advertising and marketing initiatives.

[0816] "Final adjustment" refers to the process in which human experts make final corrections and fine-tuning to AI suggestions and automatically generated content.

[0817] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[0818] Hardware and software used

[0819] Hardware: Servers, terminals, user input devices (e.g., PCs, tablets, smartphones)

[0820] Software: Generative AI models, emotion engines, BI tools

[0821] Explanation of the program's processing steps

[0822] 1. User side

[0823] The user uses the terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user inputs the following information about a "new health drink."

[0824] Product concept: A new health drink

[0825] Insight: Staying healthy in a busy life

[0826] Benefit: Easy health

[0827] Competitive comparison information: Comparison data with similar competing products

[0828] 2. Server side

[0829] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[0830] 3. Emotion Data Analysis

[0831] The server uses an emotion engine to extract emotion data from user input and user interactions. Specifically, it analyzes the tone and expression of the text entered by the user to determine the user's emotional state (e.g., positive, negative).

[0832] 4. Generating a distribution scenario

[0833] The server extracts targets based on emotional data and automatically generates optimal distribution scenarios using AI. Targets such as "office workers with positive emotions" and "sports enthusiasts feeling tired" are set using an emotion engine, and distribution scenarios are generated based on these targets.

[0834] 5. Content Generation

[0835] The server uses a generative AI model to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a catchy slogan such as "Get healthy easily" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals to match the user's emotions.

[0836] 6. Content Selection and Tuning

[0837] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color tone, font, and placement.

[0838] 7. Legal Brand Check

[0839] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​identifies legal risk areas in the ad copy and checks whether appropriate contact information is included.

[0840] 8. Execution of distribution

[0841] The device delivers content to target users based on the delivery scenario and advertising content received from the server, and conducts AB testing.Specifically, the device delivers a "Easy Health" version and a "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[0842] 9. Measurement

[0843] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Post-delivery data is collected and the evaluation indicators for each target group are analyzed.

[0844] 10. Analysis and improvement of results

[0845] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[0846] 11. Final tuning

[0847] Users (especially marketers and designers) review the AI's suggestions and adjust the final ad content and delivery scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary.

[0848] Examples of prompt statements

[0849] For example, a possible prompt for an AI model might be:

[0850] Create a marketing campaign for a new health drink. The product concept should be "Staying healthy in a busy life," the benefit should be "Getting healthy easily," and include comparative information about competing products. Target office workers and sports enthusiasts.

[0851] This system makes it possible to carry out digital marketing efficiently even without specialized knowledge. In addition, by combining it with an emotion engine, it is possible to optimize delivery scenarios and advertising content in response to user emotions, resulting in more effective digital marketing. Automating the entire process from product concept to delivery, evaluation, and improvement can save costs and time.

[0852] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0853] Step 1:

[0854] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a dedicated form. The input data includes the product concept, insights (e.g., maintaining health in a busy lifestyle), benefits (e.g., easily achieving health), and competitive comparison information (e.g., comparison data with similar competing products). The input data is sent to the server.

[0855] Output: The product concept data entered by the user is sent to the server.

[0856] Step 2:

[0857] The server stores the product concept data received from the user in an internal database. Then, the server uses APIs to obtain related external data (market data, trend data), collects market trends and past advertising data, and stores it in the database.

[0858] Input: Product concept data entered by the user

[0859] Output: Product concept data stored in an internal database and retrieved external data

[0860] Step 3:

[0861] The server uses an emotion engine to extract emotion data from user input data and user interactions by analyzing the tone and expression of the user-entered text and identifying the user's emotional state (e.g., positive, negative).

[0862] Input: User-entered product concept data and external data

[0863] Output: User emotion data

[0864] Step 4:

[0865] The server extracts targets based on emotional data and automatically generates optimal distribution scenarios using AI. Using an emotion engine, targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" are set, and distribution scenarios are generated based on those targets.

[0866] Input: User emotion data

[0867] Output: AI-generated delivery scenarios

[0868] Step 5:

[0869] The server uses a generative AI model to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a tagline such as "Get healthy easily" and an image of an office worker drinking a drink.

[0870] Input: AI-generated delivery scenario

[0871] Output: Ad content generated by the generative AI model

[0872] Step 6:

[0873] The server sends the generated advertising content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and adjusts the color tone, font, placement, etc. The adjusted content is then sent back to the server.

[0874] Input: Ad content generated by a generative AI model

[0875] Output: Ad content finalized by designer

[0876] Step 7:

[0877] The server uses AI to automatically detect legal risks and compliance with brand guidelines in the generated advertising content. The AI ​​identifies areas of legal risk in the ad copy and checks whether appropriate contact information is included.

[0878] Input: Ad content finalized by designer

[0879] Output: Legal risk and brand guideline compliance detection results

[0880] Step 8:

[0881] The device delivers content to target users based on the delivery scenario and advertising content received from the server, and conducts AB testing. Specifically, the device delivers a "Easy Health" version and a "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[0882] Input: Delivery scenario and ad content

[0883] Output: Content delivery results to target users

[0884] Step 9:

[0885] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Post-delivery data is collected and the evaluation indicators for each target group are analyzed.

[0886] Input: Distribution result data

[0887] Output: Evaluation metrics such as CTR, CVR, ROI, etc.

[0888] Step 10:

[0889] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in advertisements aimed at office workers and suggests new images and text.

[0890] Input: Evaluation metrics such as CTR, CVR, ROI, etc.

[0891] Output: AI-generated improvement measures

[0892] Step 11:

[0893] Users (especially marketers and designers) review the AI's suggestions and adjust the final ad content and delivery scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary.

[0894] Input: AI-generated improvement measures

[0895] Output: Final adjusted ad content and delivery scenario

[0896] (Application example 2)

[0897] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0898] Modern digital marketing requires the delivery of advertisements tailored to diverse product concepts, and in particular the generation of delivery scenarios and advertising content that take emotions into account. However, conventional systems lack the functionality to properly analyze and reflect user emotions, making it difficult to effectively approach target users. Furthermore, this requires a lot of effort from designers and marketers, making efficient marketing activities difficult.

[0899] The specification processing by the specification 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 receiving a product concept from a user; means for automatically generating a distribution scenario using AI based on the received product concept; means for automatically generating advertising content using AI based on the automatically generated distribution scenario; means for a designer to adjust the generated content and distribution scenario; means for using AI to detect the legal risks of the advertising content and its conformity with brand guidelines and present them to the legal department; means for delivering the generated advertising content to influential target users and performing AB testing; means for evaluating the delivery results using a BI tool and measuring CTR, CVR, and ROI; means for analyzing the evaluation results using AI and improving the delivery scenario and content; and means for analyzing user emotion data in real time and generating advertising content based on the data. This makes it possible to generate and improve optimal delivery scenarios and advertising content according to user emotions.

[0900] "Product concept" refers to the basic idea, features, and value proposition of a product.

[0901] A "delivery scenario" refers to a plan or strategy for effectively delivering advertisements or content to specific target users.

[0902] "Automatic generation with AI" refers to the process of using artificial intelligence technology to generate scenarios and content based on data and information without manual operation.

[0903] "Advertising Content" refers to media such as text, images, and video created as part of a marketing effort.

[0904] "Designer adjustments" refers to experts reviewing the generated content and scenarios and making any necessary corrections or optimizations.

[0905] "Legal risk" refers to the possibility that an ad may violate laws, regulations, or other laws.

[0906] "Brand guidelines" refer to guidelines and rules established to maintain the brand image of a company or product.

[0907] A "legal department" refers to a department within a company that specializes in assessing and responding to legal risks.

[0908] "AB testing" refers to a method of simultaneously delivering two or more versions of advertising content and comparing and analyzing their effectiveness.

[0909] "CTR" stands for click-through rate, which refers to the percentage of ads that are clicked on.

[0910] "CVR" stands for conversion rate, which refers to the percentage of ads that achieve the intended goal (such as a purchase or registration).

[0911] "ROI" stands for return on investment, and refers to the profits brought by advertising or marketing activities divided by the amount invested.

[0912] "BI tools" refers to business intelligence tools, software that supports data analysis and reporting.

[0913] "Emotion data" refers to information that represents the user's emotional state.

[0914] "Real-time analysis" refers to analyzing data as it is entered.

[0915] "Influential target users" refer to users who have a strong interest in the content of advertisements and content and are likely to influence purchasing behavior and attitudes.

[0916] The present invention is a system for automatically generating optimal advertising content in response to a user's emotions and distributing the content. A specific embodiment of this system is described below.

[0917] System configuration

[0918] This system includes a user terminal, a server, and an interface that allows manual adjustments by the designer. The user terminal refers to a smartphone or PC, and the server is a computer equipped with a high-performance processor and storage.

[0919] Hardware and Software

[0920] Hardware: smartphones, PCs, servers

[0921] Software: OpenAI API, Python, TextBlob, Pandas, BI tools

[0922] Data processing and calculation

[0923] User device:

[0924] Users use the terminal to input product concept, insights, benefits, and competitive comparison information. For example, a user might enter information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[0925] server:

[0926] The server stores the product concept data received from the user in an internal database and acquires related external data (market data, trend data). It collects market trends and past advertising data and stores them in the database.

[0927] The server then uses an emotion engine to extract emotional data from the user's input data and interactions. It uses the TextBlob library to parse the emotional state, such as positive or negative, from the tone and expression of the text entered by the user.

[0928] The server then uses AI to extract targets based on the emotional data and automatically generates the optimal broadcast scenario. The emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired," and generates a broadcast scenario based on those targets.

[0929] The server then uses the OpenAI API to automatically generate advertising content, including text, images, and videos, that reflect the product concept and emotional data. For example, the AI ​​generates a tagline such as "Easily achieve good health" and an image of an office worker drinking a drink.

[0930] The generated content is then sent to a designer via a user interface, who adjusts color, font, placement, etc. After this adjustment, the server uses AI to automatically detect legal risks and compliance with brand guidelines for the ad content and presents the results to the legal department.

[0931] User device:

[0932] Finally, the user device distributes the content to the target users based on the distribution scenario and content received from the server, and performs A / B testing. For example, a "Easy Health" version and a "Post-Sports Recovery" version are distributed to different target groups, and the effectiveness for each group is measured.

[0933] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. The delivery results are collected and the evaluation indicators for each target group are analyzed.

[0934] Improved evaluation results:

[0935] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. For example, the AI ​​may identify that there is a problem with the visuals in an advertisement for office workers and suggest new images and text.

[0936] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Marketers review the suggested improvements and make manual adjustments as necessary.

[0937] Examples of prompts:

[0938] Product concept: Maintaining health in a busy lifestyle

[0939] Target audience: office workers and sports enthusiasts

[0940] User Emotion: Positive Mood

[0941] Generated ad text:

[0942] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0943] Step 1:

[0944] Users use their smartphones or computers to input product concepts, insights, benefits, and competitive comparison information. Specifically, they enter information such as "a new health drink," "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products" into a form. This input data is then sent to the server.

[0945] Step 2:

[0946] The server stores the received product concept data in an internal database. At the same time, it acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database. The input is the user's concept data, and the output is the saved internal database.

[0947] Step 3:

[0948] The server uses an emotion engine to extract emotion data from user input data and user interactions. Specifically, it uses the TextBlob library to analyze the user's emotional state (positive, negative, etc.) from the tone and expression of the text entered by the user. The input is the user's text data, and the output is the analyzed emotion data.

[0949] Step 4:

[0950] The server uses AI to extract targets based on the emotional data and automatically generates the optimal distribution scenario. Specifically, the emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" and generates a distribution scenario based on them. The input is emotional data and the output is a distribution scenario.

[0951] Step 5:

[0952] The server uses the OpenAI API to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a catchphrase such as "Get healthy easily" and an image of an office worker drinking a drink. The input is the distribution scenario, and the output is the advertising content.

[0953] Step 6:

[0954] The generated content is sent to the designer through a user interface, who adjusts color, font, placement, etc. Specifically, the designer reviews the generated images and text and makes any necessary corrections. The input is the advertising content, and the output is the adjusted advertising content.

[0955] Step 7:

[0956] The server uses AI to automatically detect legal risks in advertising content and compliance with brand guidelines, and presents the results to the legal department. Specifically, the AI ​​detects and reports legal risks and violations of brand guidelines in advertising copy. The input is the adjusted advertising content, and the output is the legal risk detection results.

[0957] Step 8:

[0958] The user device delivers content to target users based on the delivery scenario and content received from the server, and conducts AB testing. Specifically, a "Easy Health" version and a "Post-Sports Recovery" version are delivered to different target groups, and the effectiveness for each group is measured. The input is the delivery scenario and advertising content, and the output is the AB test results.

[0959] Step 9:

[0960] The server uses a BI tool to measure the CTR, CVR, ROI, etc. of the delivered content in real time. Specifically, it collects post-delivery data and analyzes the evaluation indicators for each target group. The input is the AB test results, and the output is the evaluation indicators.

[0961] Step 10:

[0962] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in advertisements for office workers and suggests new images and text. The input is the evaluation index, and the output is the improvement measures.

[0963] Step 11:

[0964] Users (marketers and designers) review the AI's suggestions and adjust the final content and distribution scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary. The input is the improvements, and the output is the final adjusted content and distribution scenario.

[0965] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0966] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0967] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0968] [Third embodiment]

[0969] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0970] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0971] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0972] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0973] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0974] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0975] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0976] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0977] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0978] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0979] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0980] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0981] This invention is a system that automatically executes digital marketing by inputting a product concept into AI. This system includes the processes of inputting the product concept, formulating a distribution scenario, creating content, legal and brand checks, distributing content to the target, measuring effectiveness, and making improvements based on the results.

[0982] Program processing

[0983] User side

[0984] 1. Enter the product concept

[0985] Users use the terminal to input product concepts, insights (consumer insights), benefits, and competitive comparison information.

[0986] Example: A user inputs information about a "new health drink," such as "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products" on a terminal.

[0987] Server side

[0988] 2. Data Reception and Analysis

[0989] The server compares the product concept data received from the user with internal data and external data (market data, trend data) and performs analysis.

[0990] Example: The server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[0991] 3. Generating a distribution scenario

[0992] The server automatically generates a distribution scenario using AI based on the selected target.

[0993] Example: AI generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (social media, email, etc.) for each target.

[0994] 4. Content Generation

[0995] The server uses AI to automatically generate content such as text, images, and videos based on the distribution scenario.

[0996] Example: AI generates the tagline "Easy Health" along with an image of an office worker drinking a drink.

[0997] 5. Content Selection and Tuning

[0998] The designer checks the content generated by the server and makes any final adjustments.

[0999] Example: A designer reviews the generated images and text and adjusts color, font, placement, etc.

[1000] 6. Legal Brand Check

[1001] The server uses AI to automatically detect legal risks and compliance with brand guidelines for content and presents them to the legal department.

[1002] Example: AI detects legal risks in ad copy and checks whether appropriate contact information is included. The results are reported to the legal department.

[1003] Terminal side

[1004] 7. Execution of distribution

[1005] The terminal delivers content to target users based on the distribution scenario and content received from the server and conducts AB testing.

[1006] Example: The device delivers a "quick health" version and a "post-sports recovery" version to different target groups (office workers and sports enthusiasts), and measures the effectiveness for each group.

[1007] 8. Effectiveness Measurement

[1008] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time.

[1009] Example: The server collects data after delivery, analyzes and displays the click rate and conversion rate for each target group.

[1010] Server side

[1011] 9. Analysis and improvement of results

[1012] The server uses AI to analyze the distribution results, analyze the difference between the predicted effect and the actual results, identify the cause, and automatically generate improvement measures.

[1013] Example: AI identifies that the visuals are the cause of low click-through rates on ads for office workers and suggests new images and text.

[1014] User side

[1015] 10. Final tuning

[1016] Users (especially marketers and designers) review the AI's suggestions and adjust the actual content and distribution scenarios.

[1017] Example: Marketers review suggested improvements and make manual adjustments as needed.

[1018] This invention makes it possible to efficiently carry out digital marketing even without specialized knowledge. This system automates the entire process, from product concept to distribution, evaluation, and improvement, thereby saving costs and time.

[1019] The processing flow will be explained below.

[1020] Step 1:

[1021] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1022] Step 2:

[1023] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1024] Step 3:

[1025] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[1026] Step 4:

[1027] AI automatically generates optimal delivery scenarios for the extracted targets. Scenarios include the message, delivery channel, delivery timing, etc. Specific actions that can be generated include "delivering social media ads to office workers on weekday mornings" and "delivering email ads on weekends to sports enthusiasts."

[1028] Step 5:

[1029] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Get healthy easily" and an image of an office worker holding a health drink.

[1030] Step 6:

[1031] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and fine-tunes the color tone, font, placement, etc.

[1032] Step 7:

[1033] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1034] Step 8:

[1035] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[1036] Step 9:

[1037] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[1038] Step 10:

[1039] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[1040] Step 11:

[1041] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1042] Step 12:

[1043] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[1044] Example 1

[1045] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1046] In traditional digital marketing, the process from entering product concepts to distributing advertising content, measuring effectiveness, and making improvements is often done manually, which not only takes a great deal of time and effort but also requires specialized knowledge, resulting in problems of inefficiency.In addition, checking whether the generated advertising content complies with legal risks and brand guidelines is often done manually, which poses challenges in terms of the time and human resources required for the checking process to avoid legal risks.

[1047] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1048] In this invention, the server includes means for receiving a product concept from a user, means for automatically generating a distribution scenario based on the received product concept using a generative AI model, and means for generating advertising content based on the distribution scenario automatically generated using the generative AI model. This makes it possible to provide an environment in which a user simply inputs a product concept, and the AI ​​automatically generates a distribution scenario and advertising content, enabling a series of digital marketing processes to be executed quickly and efficiently.

[1049] A "product concept" is an idea or strategy that includes the basic purpose and characteristics of a product or service, target market, competitive analysis, etc.

[1050] "Means for receiving" refers to a function or process for acquiring data input by a user.

[1051] A "generative AI model" refers to artificial intelligence technology and algorithms that automatically generate scenarios and content based on input information from users.

[1052] A "distribution scenario" is a plan that defines what advertising content will be distributed to a specific target, at what timing, and through which channel.

[1053] "Advertising content" refers to promotional materials such as text, images, and videos created based on a distribution scenario.

[1054] A "creator" is a professional who is responsible for the final design and adjustment of advertising content.

[1055] "Legal risk" refers to the possibility that advertising content may violate laws or regulations.

[1056] "Brand guidelines" are rules regarding design and messaging established to maintain a company's brand image.

[1057] A "legal department" is a department within a company or organization that manages and deals with legal issues and risks.

[1058] "Target users" refers to the customer demographic that is anticipated when delivering advertisements, specifically the recipients of the advertisements.

[1059] "AB testing" is a method of comparing two or more versions of an advertisement or piece of content to determine which is more effective.

[1060] "Analysis tools" refer to software and platforms for collecting and analyzing data and visualizing the results.

[1061] "Click-through rate" refers to the percentage of clicks on an ad compared to the number of times it is displayed.

[1062] "Conversion rate" is the percentage of ads that result in a targeted action (such as a purchase or registration).

[1063] "Return on investment" is an indicator that evaluates how much profit is gained from the resources invested in advertising and marketing activities.

[1064] "Evaluation results" refer to various indicators (click-through rate, conversion rate, return on investment, etc.) obtained using analysis tools after advertising is delivered.

[1065] "Root cause analysis" is the process of identifying the causes of problems or lack of effectiveness with advertising or content.

[1066] "Improvement measures" are specific action plans to address identified problems and causes.

[1067] A "marketer" is a professional who is responsible for marketing activities in a company or organization.

[1068] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. The main elements that make up the system are users, devices, and servers, each of which plays a specific role.

[1069] First, the user uses a terminal to input the product concept, insights (consumer insights), benefits, and competitive comparison information. For example, for a new health drink, the user can input insights and benefits such as "maintaining health in a busy life" and "easily achieving health," as well as "comparison data with similar competitive products." This information is sent to the server via the terminal.

[1070] The server compares the received product concept data with its internal database and external data (market data, trend data) and performs an analysis. This analysis uses an AI model (e.g., machine learning algorithms, data analysis tools, etc.). Specifically, the server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[1071] Next, the server automatically generates a distribution scenario based on the selected targets using a generative AI model (e.g., natural language processing model). For example, the AI ​​could generate a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts," and select the optimal distribution channel (e.g., social media, email) for each target.

[1072] The server then uses a generative AI model to automatically generate advertising content such as text, images, and videos based on the distribution scenario. This process uses tools such as DeepArt for image generation and Synthesia for video generation. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[1073] The generated content and distribution scenarios are then checked by a designer, who makes final adjustments using design tools such as Adobe Creative Cloud to adjust color tones, fonts, and image placement.

[1074] The server then uses AI to detect legal risks and compliance with brand guidelines in the ad content. For example, it uses Compliance AI tools to check for potential legal risks in the ad copy, checks for violations of guidelines, and reports the results to the legal department.

[1075] The device then delivers content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the device delivers advertisements for "easy health" and "recovery after sports" to different target groups (office workers and sports enthusiasts) and measures the effectiveness of each.

[1076] Finally, the server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time and analyze the results. Based on this evaluation, the AI ​​analyzes the cause and presents improvement measures, and marketers and designers make final adjustments.

[1077] An example prompt is:

[1078] Please enter your product concept for a "new healthy drink." Please include specific consumer insights, benefits, and competitive comparison information.

[1079] example:

[1080] Insight: "Staying healthy in a busy life"

[1081] Benefit: "Easy to get healthy"

[1082] Competitive comparison: "Comparative data with similar competing products"

[1083] As a result, this system automates the entire process from product concept to distribution, evaluation, and improvement, resulting in significant cost and time savings.

[1084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1085] Step 1:

[1086] The user uses a terminal to input and submit a product concept. Specifically, the user enters the concept of a "new health drink," along with insights (e.g., "Maintaining health in a busy life"), benefits (e.g., "Easily achieve health"), and competitive comparison information into the form, and clicks the submit button. The input information is sent from the terminal to the server.

[1087] Input: Product concept, insights, benefits, competitive comparison information

[1088] Output: Product concept data sent to the server

[1089] Step 2:

[1090] The server analyzes the product concept data received from the user by comparing it with the internal database and external data (market data, trend data). Specifically, the server analyzes the user's input data using past sales data and consumer reviews from the internal database, as well as market trend data obtained through external APIs. An AI model is used in this analysis to select the optimal target users.

[1091] Input: Product concept data, internal database, external data

[1092] Output: Analysis results (e.g., "health-conscious working generation" and "sports enthusiasts")

[1093] Step 3:

[1094] The server automatically generates a distribution scenario based on the selected target using a generative AI model. Specifically, it uses a generative AI model (e.g., a natural language processing model) to create scenarios for a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts." It also selects the optimal distribution channel (e.g., social media, email, etc.) for each target.

[1095] Input: Analysis results, generated AI model

[1096] Output: Delivery scenario

[1097] Step 4:

[1098] The server uses the generative AI model to automatically generate advertising content based on the generated distribution scenario. Specific operations include using a natural language generation model to generate text, an image generation tool (e.g., DeepArt) to generate images, and a video generation tool (e.g., Synthesia) to generate videos. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[1099] Input: Delivery scenario, generative AI model

[1100] Output: Ad content (text, images, videos)

[1101] Step 5:

[1102] Creators adjust the content and distribution scenarios generated by the server. Specifically, creators use design tools (e.g., Adobe Creative Cloud) to adjust the color tone, font, and placement of generated images and text.

[1103] Input: Ad content, distribution scenario

[1104] Output: Adjusted advertising content, distribution scenario

[1105] Step 6:

[1106] The server uses AI to detect legal risks and compliance with brand guidelines in advertising content and presents the results to the legal department. Specifically, it uses legal risk detection tools (e.g., Compliance AI) to analyze content and checks compliance with guidelines.

[1107] Input: Tailored ad content

[1108] Output: Legal risk and brand guideline compliance detection results

[1109] Step 7:

[1110] The device delivers content to target users based on the delivery scenario and content received from the server, and performs AB testing. Specifically, an ad management tool (e.g., Facebook Ads Manager) is used for delivery, and different versions of ads are delivered to different target groups.

[1111] Input: Distribution scenario, advertising content

[1112] Output: Advertisements delivered to target users, AB test results

[1113] Step 8:

[1114] The server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time. Specifically, it collects and visualizes user data after ad delivery and analyzes the effectiveness indicators for each target group.

[1115] Input: AB test results, target user data

[1116] Output: Effectiveness measurement results (CTR, CVR, ROI)

[1117] Step 9:

[1118] The server uses AI to analyze the results of effectiveness measurements, analyzes the difference between predicted and actual results to identify the cause, and automatically generates improvement measures.Specifically, it uses an AI model (e.g., machine learning algorithm) to generate new suggestions for identified problems.For example, it may identify that the cause of a low click-through rate is visual and suggest new images and text.

[1119] Input: Effectiveness measurement results

[1120] Output: Cause analysis, improvement suggestions

[1121] Step 10:

[1122] Users (especially marketers and creators) review the AI's suggestions and make final adjustments to the actual content and distribution scenario. Specifically, marketers adjust distribution schedules and targeting based on the suggestions, and creators make suggested design improvements.

[1123] Input: Improvement suggestion

[1124] Output: Final adjusted ad content and distribution scenario

[1125] (Application example 1)

[1126] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1127] In the field of digital marketing, there is a demand for automation of the creation, distribution, effectiveness measurement, and improvement of effective advertising campaigns. Conventional methods require marketers to expend a lot of time and effort and specialized knowledge, resulting in inefficiency and high costs. In addition, it is difficult to measure the effectiveness of ads in real time or make quick improvements after they are delivered. This poses a challenge in maximizing the effectiveness of advertising investments.

[1128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1129] In this invention, the server includes: means for receiving a product concept from a user; means for automatically generating a distribution scenario using AI based on the received product concept; means for automatically generating advertising content using AI based on the automatically generated distribution scenario; means for a designer to adjust the generated content and distribution scenario; means for detecting legal risks of the advertising content and compliance with brand guidelines using AI and presenting the results to the legal department; means for delivering the generated advertising content to target users via their smart devices and performing A / B testing; means for evaluating real-time data collected from the smart devices using a BI tool and measuring CTR, CVR, and ROI; and means for analyzing the evaluation results using AI and automatically improving the advertising content and distribution scenario. This enables the automation of effective advertising campaigns.

[1130] "Product concept" refers to detailed information about a product or service, such as its features, benefits, and target users.

[1131] "User" means a person or entity that utilizes the System to enter product concepts and manage advertising campaigns.

[1132] A "distribution scenario" refers to a plan for distributing content to specific target users through what channels and at what timing.

[1133] "AI" refers to artificial intelligence technology, which includes algorithms and models for automatically solving specific problems.

[1134] "Advertising Content" refers to materials such as text, images, and video created for advertising purposes.

[1135] "Designer" refers to the person who makes the final adjustments to the generated advertising content and visually optimizes it.

[1136] "Legal risk" refers to the risk that advertising content may violate the law.

[1137] "Brand guidelines" refer to standards for design and messaging established to maintain brand consistency.

[1138] "Legal Department" means the department within an organization that considers and resolves legal matters.

[1139] "Target users" refers to the group of users who are intended to receive a particular message of an advertising campaign.

[1140] "Smart devices" refers to advanced electronic devices with internet connectivity, such as smartphones, tablets, and smart glasses.

[1141] "AB testing" refers to a testing method in which different versions of advertising content are simultaneously delivered to target users and their effectiveness is compared.

[1142] "BI tool" stands for business intelligence tool and refers to software that analyzes data to support business decision-making.

[1143] "CTR" stands for click-through rate and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[1144] "CVR" stands for conversion rate and refers to the percentage of times a specific action (purchase, registration, etc.) is performed.

[1145] "ROI" stands for return on investment and refers to an indicator that financially evaluates the effectiveness of the money invested in an advertising campaign.

[1146] "Real-time data" refers to data that is collected continuously from the moment an ad is delivered.

[1147] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. This system is divided into a user side and a server side.

[1148] User side

[1149] Entering product concepts

[1150] Users use a smartphone app to input product concepts, insights, benefits, and competitive analysis information. For example, for a "new health drink," users can input "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1151] Server side

[1152] Data reception and analysis

[1153] The server analyzes the product concept data received from users by comparing it with internal and external data. This analysis uses artificial intelligence (AI) models such as TensorFlow. The optimal target users are selected based on market and trend data. As a specific example, trend data from the health drink market is analyzed to select "health-conscious working people" and "sports enthusiasts" as targets.

[1154] Generating a distribution scenario

[1155] The server automatically generates distribution scenarios using AI based on the selected target users. For example, the AI ​​generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (SNS, email, etc.) for each target.

[1156] Content Generation

[1157] The server uses AI to generate advertising content such as text, images, and videos based on a distribution scenario. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[1158] Legal Brand Check

[1159] AI is used to detect legal risks and compliance with brand guidelines in generated advertising content, and presents the results to the legal department. For example, AI can detect legal risks in advertising copy and check whether appropriate contact information is included.

[1160] Terminal side

[1161] Executing the distribution

[1162] The smartphone app delivers advertising content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the app delivers two versions, "Easy Health" and "Post-Sports Recovery," to different target groups (office workers and sports enthusiasts), and measures the effectiveness of each.

[1163] Effectiveness measurement

[1164] The server uses BI (business intelligence) tools to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered advertising content in real time. For example, the server collects data after delivery and analyzes and displays the click-through rate and conversion rate of each target group. For this purpose, BI tools such as Tableau are used.

[1165] Results analysis and improvement

[1166] The server uses AI to analyze the results of distribution, analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. For example, the AI ​​may identify that the visuals are the cause of the low click-through rate of ads aimed at office workers, and suggest new images and text.

[1167] User side

[1168] Final Tuning

[1169] Users, especially marketers and designers, review the AI ​​suggestions and adjust the actual content and distribution scenarios. For example, marketers review the suggested improvements and make manual adjustments as necessary.

[1170] Prompt Sentence Examples

[1171] Product concept: A new health drink

[1172] Consumer Insights: Busy lifestyles and the need to stay healthy

[1173] Benefit: Easy health

[1174] Competitive comparison: Comparison data with similar competing products

[1175] In this way, effective advertising campaigns can be automated and efficiently executed.

[1176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1177] Step 1:

[1178] Users use a smartphone app to input product concepts, consumer insights, profits, and competitive analysis information.

[1179] For example, the user inputs "new healthy drink" along with consumer insights and comparison data with competing products. The device then sends this data to the server.

[1180] Step 2:

[1181] The server analyzes the product concept data received from the user by comparing it with internal data and external data.

[1182] This analysis uses AI models such as TensorFlow. The server selects the optimal target users based on market and trend data. The output is a list of target users (e.g., "health-conscious working generation" or "sports enthusiasts").

[1183] Step 3:

[1184] The server automatically generates a distribution scenario using AI based on the target users.

[1185] For example, AI can generate "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and select the optimal distribution channel (e.g., social media or email) for each target. Specific distribution scenarios are generated as an output.

[1186] Step 4:

[1187] The server automatically generates advertising content using AI based on the generated distribution scenario.

[1188] Specifically, it generates advertising materials such as text, images, and videos. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink. The output is the completed advertising content.

[1189] Step 5:

[1190] Use AI to detect legal risks and compliance with brand guidelines before presenting server-generated ad content to the legal department.

[1191] For example, AI can detect legal risks and brand guideline violations in ad copy and report the results to the legal department. The output is a check result for legal risk and brand suitability.

[1192] Step 6:

[1193] The device delivers advertising content to target users based on the delivery scenario and content received from the server, and performs AB testing.

[1194] For example, we deliver two versions of the AB test, one for "easy health" and the other for "recovery after sports" to different target groups (office workers and sports enthusiasts), and measure their effectiveness. The input is the delivery scenario and content from the server, and the output is the results of the AB test.

[1195] Step 7:

[1196] The server uses a BI tool (e.g., Tableau) to measure the effectiveness of advertising content in real time.

[1197] It calculates and analyzes metrics such as click-through rate (CTR), conversion rate (CVR), and return on investment (ROI). The input is user response data to delivered advertising content, and the output is the real-time measurement results of these metrics.

[1198] Step 8:

[1199] The server uses AI to analyze the distribution results and analyze the difference between the predicted effect and the actual results.

[1200] For example, AI can identify that the low click-through rate of ads for office workers is due to visuals and suggest new images and text. The input is effectiveness measurement data, and the output is the results of an analysis of the causes and suggestions for improvement.

[1201] Step 9:

[1202] The user reviews the AI's suggestions and makes manual adjustments if necessary.

[1203] Marketers and designers review the proposed improvements and make final adjustments to the content and distribution scenario. The input is the improvement suggestions from the AI, and the output is the final adjusted advertising content and distribution scenario.

[1204] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1205] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[1206] Program processing

[1207] User side

[1208] 1. Enter the product concept

[1209] The user uses the terminal to input the product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into the form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1210] Server side

[1211] 2. Data Reception and Analysis

[1212] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1213] 3. Emotion Data Analysis

[1214] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[1215] 4. Generating a distribution scenario

[1216] The server extracts targets based on the emotional data and automatically generates optimal distribution scenarios using AI. Specifically, the emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" and generates distribution scenarios based on them.

[1217] 5. Content Generation

[1218] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[1219] 6. Content Selection and Tuning

[1220] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color, font, and placement.

[1221] 7. Legal Brand Check

[1222] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1223] Terminal side

[1224] 8. Execution of distribution

[1225] The device distributes content to target users based on the distribution scenario and content received from the server, and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[1226] 9. Measurement

[1227] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[1228] Server side

[1229] 10. Analysis and improvement of results

[1230] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1231] User side

[1232] 11. Final tuning

[1233] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[1234] This invention enables efficient digital marketing even without specialized knowledge. Furthermore, by combining it with an emotion engine, distribution scenarios and advertising content can be optimized to match user emotions, resulting in more effective digital marketing. This system automates the entire process, from product conception through distribution, evaluation, and improvement, thereby saving time and money.

[1235] The processing flow will be explained below.

[1236] Step 1:

[1237] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1238] Step 2:

[1239] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1240] Step 3:

[1241] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[1242] Step 4:

[1243] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[1244] Step 5:

[1245] Based on the extracted target and emotional data, AI automatically generates optimal distribution scenarios. The scenarios include the message, distribution channel, and distribution timing. Specific actions generated include "delivering morning social media ads to office workers with positive emotions" and "delivering weekend email ads to sports enthusiasts feeling tired."

[1246] Step 6:

[1247] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[1248] Step 7:

[1249] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and adjusts the color tone, font, and placement.

[1250] Step 8:

[1251] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1252] Step 9:

[1253] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[1254] Step 10:

[1255] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[1256] Step 11:

[1257] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[1258] Step 12:

[1259] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1260] Step 13:

[1261] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[1262] Example 2

[1263] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1264] Modern digital marketing requires efficient and effective delivery of advertising content, but traditional methods have the following problems:

[1265] 1. The process from entering product concepts to generating distribution scenarios is done manually, which is time-consuming and costly.

[1266] 2. Delivery scenarios and advertising content are created uniformly and do not respond to the emotions and needs of target users.

[1267] 3. Because effectiveness measurement and analysis are done manually, improvement measures are delayed. Also, because A / B testing and its effectiveness measurement cannot be carried out efficiently, it is difficult to optimize advertising.

[1268] The present invention aims to solve these problems and provide a system that realizes efficient and effective digital marketing.

[1269] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1270] In this invention, the server includes: means for receiving a product concept from a user; means for comparing and analyzing the received product concept with internal data and external data; means for extracting emotional data from user interactions; means for extracting targets based on the emotional data and automatically generating an optimal distribution scenario using AI; means for automatically generating advertising content using a generative AI model; means for a designer to adjust the generated content and distribution scenario; means for using AI to detect legal risks and compliance with brand guidelines of the advertising content and present it to the legal department; means for delivering the generated advertising content to target users and performing A / B testing; means for evaluating the delivery results using a BI tool and measuring CTR, CVR, and ROI; means for analyzing the evaluation results using AI and improving the distribution scenario and content; and means for marketers and designers to make final adjustments based on the AI's improvement suggestions. This enables efficient and effective digital marketing.

[1271] "Product Concept" refers to the main idea or features of the product or service you offer.

[1272] "Internal data" refers to information generated or collected within a company that is used for analysis or application within a system.

[1273] "External data" refers to information obtained from outside the company, such as data on trends and markets, that is used in analysis in combination with internal data.

[1274] "Emotional data" refers to emotional states (e.g., positive, negative) extracted from user input and interactions.

[1275] "Target" refers to a group of users to whom marketing is directed based on specific conditions or attributes.

[1276] A "distribution scenario" refers to a plan or strategy for how to deliver advertisements to a target audience.

[1277] A "generative AI model" refers to an artificial intelligence model that automatically generates content such as text, images, and videos based on pre-trained algorithms.

[1278] "Designer" refers to a professional who makes final adjustments to generated content, modifying it to meet visual satisfaction and brand guidelines.

[1279] "Legal risk" refers to potential problems that may arise from advertising content violating laws or regulations.

[1280] "Brand guidelines" refer to regulations regarding design and expression that are intended to maintain consistency in a company or product brand.

[1281] "Influential target users" refers to a specific user group for whom advertising content may have a high influence or potential effect.

[1282] "AB testing" refers to a method of comparing two or more versions of advertising content and measuring their effectiveness.

[1283] "BI tools" refers to software used for business intelligence, tools that support data analysis and report creation.

[1284] "CTR" stands for Click Through Rate, and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[1285] "CVR" stands for conversion rate, and refers to the ratio of the number of times users who clicked on an ad actually took the target action, such as purchasing or registering.

[1286] "ROI" stands for Return on Investment and refers to the ratio of return on investment for advertising and marketing initiatives.

[1287] "Final adjustment" refers to the process in which human experts make final corrections and fine-tuning to AI suggestions and automatically generated content.

[1288] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[1289] Hardware and software used

[1290] Hardware: Servers, terminals, user input devices (e.g., PCs, tablets, smartphones)

[1291] Software: Generative AI models, emotion engines, BI tools

[1292] Explanation of the program's processing steps

[1293] 1. User side

[1294] The user uses the terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user inputs the following information about a "new health drink."

[1295] Product concept: A new health drink

[1296] Insight: Staying healthy in a busy life

[1297] Benefit: Easy health

[1298] Competitive comparison information: Comparison data with similar competing products

[1299] 2. Server side

[1300] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1301] 3. Emotion Data Analysis

[1302] The server uses an emotion engine to extract emotion data from user input and user interactions. Specifically, it analyzes the tone and expression of the text entered by the user to determine the user's emotional state (e.g., positive, negative).

[1303] 4. Generating a distribution scenario

[1304] The server extracts targets based on emotional data and automatically generates optimal distribution scenarios using AI. Targets such as "office workers with positive emotions" and "sports enthusiasts feeling tired" are set using an emotion engine, and distribution scenarios are generated based on these targets.

[1305] 5. Content Generation

[1306] The server uses a generative AI model to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a catchy slogan such as "Get healthy easily" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals to match the user's emotions.

[1307] 6. Content Selection and Tuning

[1308] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color tone, font, and placement.

[1309] 7. Legal Brand Check

[1310] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​identifies legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1311] 8. Execution of distribution

[1312] The device delivers content to target users based on the delivery scenario and advertising content received from the server, and conducts AB testing.Specifically, the device delivers a "Easy Health" version and a "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[1313] 9. Measurement

[1314] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Post-delivery data is collected and the evaluation indicators for each target group are analyzed.

[1315] 10. Analysis and improvement of results

[1316] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1317] 11. Final tuning

[1318] Users (especially marketers and designers) review the AI's suggestions and adjust the final ad content and delivery scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary.

[1319] Examples of prompt statements

[1320] For example, a possible prompt for an AI model might be:

[1321] Create a marketing campaign for a new health drink. The product concept should be "Staying healthy in a busy life," the benefit should be "Getting healthy easily," and include comparative information about competing products. Target office workers and sports enthusiasts.

[1322] This system makes it possible to carry out digital marketing efficiently even without specialized knowledge. In addition, by combining it with an emotion engine, it is possible to optimize delivery scenarios and advertising content in response to user emotions, resulting in more effective digital marketing. Automating the entire process from product concept to delivery, evaluation, and improvement can save costs and time.

[1323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1324] Step 1:

[1325] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a dedicated form. The input data includes the product concept, insights (e.g., maintaining health in a busy lifestyle), benefits (e.g., easily achieving health), and competitive comparison information (e.g., comparison data with similar competing products). The input data is sent to the server.

[1326] Output: The product concept data entered by the user is sent to the server.

[1327] Step 2:

[1328] The server stores the product concept data received from the user in an internal database. Then, the server uses APIs to obtain related external data (market data, trend data), collects market trends and past advertising data, and stores it in the database.

[1329] Input: Product concept data entered by the user

[1330] Output: Product concept data stored in an internal database and retrieved external data

[1331] Step 3:

[1332] The server uses an emotion engine to extract emotion data from user input data and user interactions by analyzing the tone and expression of the user-entered text and identifying the user's emotional state (e.g., positive, negative).

[1333] Input: User-entered product concept data and external data

[1334] Output: User emotion data

[1335] Step 4:

[1336] The server extracts targets based on emotional data and automatically generates optimal distribution scenarios using AI. Using an emotion engine, targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" are set, and distribution scenarios are generated based on those targets.

[1337] Input: User emotion data

[1338] Output: AI-generated delivery scenarios

[1339] Step 5:

[1340] The server uses a generative AI model to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a tagline such as "Get healthy easily" and an image of an office worker drinking a drink.

[1341] Input: AI-generated delivery scenario

[1342] Output: Ad content generated by the generative AI model

[1343] Step 6:

[1344] The server sends the generated advertising content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and adjusts the color tone, font, placement, etc. The adjusted content is then sent back to the server.

[1345] Input: Ad content generated by a generative AI model

[1346] Output: Ad content finalized by designer

[1347] Step 7:

[1348] The server uses AI to automatically detect legal risks and compliance with brand guidelines in the generated advertising content. The AI ​​identifies areas of legal risk in the ad copy and checks whether appropriate contact information is included.

[1349] Input: Ad content finalized by designer

[1350] Output: Legal risk and brand guideline compliance detection results

[1351] Step 8:

[1352] The device delivers content to target users based on the delivery scenario and advertising content received from the server, and conducts AB testing. Specifically, the device delivers a "Easy Health" version and a "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[1353] Input: Delivery scenario and ad content

[1354] Output: Content delivery results to target users

[1355] Step 9:

[1356] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Post-delivery data is collected and the evaluation indicators for each target group are analyzed.

[1357] Input: Distribution result data

[1358] Output: Evaluation metrics such as CTR, CVR, ROI, etc.

[1359] Step 10:

[1360] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in advertisements aimed at office workers and suggests new images and text.

[1361] Input: Evaluation metrics such as CTR, CVR, ROI, etc.

[1362] Output: AI-generated improvement measures

[1363] Step 11:

[1364] Users (especially marketers and designers) review the AI's suggestions and adjust the final ad content and delivery scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary.

[1365] Input: AI-generated improvement measures

[1366] Output: Final adjusted ad content and delivery scenario

[1367] (Application example 2)

[1368] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1369] Modern digital marketing requires the delivery of advertisements tailored to diverse product concepts, and in particular the generation of delivery scenarios and advertising content that take emotions into account. However, conventional systems lack the functionality to properly analyze and reflect user emotions, making it difficult to effectively approach target users. Furthermore, this requires a lot of effort from designers and marketers, making efficient marketing activities difficult.

[1370] The specification processing by the specification 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 receiving a product concept from a user; means for automatically generating a distribution scenario using AI based on the received product concept; means for automatically generating advertising content using AI based on the automatically generated distribution scenario; means for a designer to adjust the generated content and distribution scenario; means for using AI to detect the legal risks of the advertising content and its conformity with brand guidelines and present them to the legal department; means for delivering the generated advertising content to influential target users and performing AB testing; means for evaluating the delivery results using a BI tool and measuring CTR, CVR, and ROI; means for analyzing the evaluation results using AI and improving the delivery scenario and content; and means for analyzing user emotion data in real time and generating advertising content based on the data. This makes it possible to generate and improve optimal delivery scenarios and advertising content according to user emotions.

[1371] "Product concept" refers to the basic idea, features, and value proposition of a product.

[1372] A "delivery scenario" refers to a plan or strategy for effectively delivering advertisements or content to specific target users.

[1373] "Automatic generation with AI" refers to the process of using artificial intelligence technology to generate scenarios and content based on data and information without manual operation.

[1374] "Advertising Content" refers to media such as text, images, and video created as part of a marketing effort.

[1375] "Designer adjustments" refers to experts reviewing the generated content and scenarios and making any necessary corrections or optimizations.

[1376] "Legal risk" refers to the possibility that an ad may violate laws, regulations, or other laws.

[1377] "Brand guidelines" refer to guidelines and rules established to maintain the brand image of a company or product.

[1378] A "legal department" refers to a department within a company that specializes in assessing and responding to legal risks.

[1379] "AB testing" refers to a method of simultaneously delivering two or more versions of advertising content and comparing and analyzing their effectiveness.

[1380] "CTR" stands for click-through rate, which refers to the percentage of ads that are clicked on.

[1381] "CVR" stands for conversion rate, which refers to the percentage of ads that achieve the intended goal (such as a purchase or registration).

[1382] "ROI" stands for return on investment, and refers to the profits brought by advertising or marketing activities divided by the amount invested.

[1383] "BI tools" refers to business intelligence tools, software that supports data analysis and reporting.

[1384] "Emotion data" refers to information that represents the user's emotional state.

[1385] "Real-time analysis" refers to analyzing data as it is entered.

[1386] "Influential target users" refer to users who have a strong interest in the content of advertisements and content and are likely to influence purchasing behavior and attitudes.

[1387] The present invention is a system for automatically generating optimal advertising content in response to a user's emotions and distributing the content. A specific embodiment of this system is described below.

[1388] System configuration

[1389] This system includes a user terminal, a server, and an interface that allows manual adjustments by the designer. The user terminal refers to a smartphone or PC, and the server is a computer equipped with a high-performance processor and storage.

[1390] Hardware and Software

[1391] Hardware: smartphones, PCs, servers

[1392] Software: OpenAI API, Python, TextBlob, Pandas, BI tools

[1393] Data processing and calculation

[1394] User device:

[1395] Users use the terminal to input product concept, insights, benefits, and competitive comparison information. For example, a user might enter information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1396] server:

[1397] The server stores the product concept data received from the user in an internal database and acquires related external data (market data, trend data). It collects market trends and past advertising data and stores them in the database.

[1398] The server then uses an emotion engine to extract emotional data from the user's input data and interactions. It uses the TextBlob library to parse the emotional state, such as positive or negative, from the tone and expression of the text entered by the user.

[1399] The server then uses AI to extract targets based on the emotional data and automatically generates the optimal broadcast scenario. The emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired," and generates a broadcast scenario based on those targets.

[1400] The server then uses the OpenAI API to automatically generate advertising content, including text, images, and videos, that reflect the product concept and emotional data. For example, the AI ​​generates a tagline such as "Easily achieve good health" and an image of an office worker drinking a drink.

[1401] The generated content is then sent to a designer via a user interface, who adjusts color, font, placement, etc. After this adjustment, the server uses AI to automatically detect legal risks and compliance with brand guidelines for the ad content and presents the results to the legal department.

[1402] User device:

[1403] Finally, the user device distributes the content to the target users based on the distribution scenario and content received from the server, and performs A / B testing. For example, a "Easy Health" version and a "Post-Sports Recovery" version are distributed to different target groups, and the effectiveness for each group is measured.

[1404] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. The delivery results are collected and the evaluation indicators for each target group are analyzed.

[1405] Improved evaluation results:

[1406] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. For example, the AI ​​may identify that there is a problem with the visuals in an advertisement for office workers and suggest new images and text.

[1407] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Marketers review the suggested improvements and make manual adjustments as necessary.

[1408] Examples of prompts:

[1409] Product concept: Maintaining health in a busy lifestyle

[1410] Target audience: office workers and sports enthusiasts

[1411] User Emotion: Positive Mood

[1412] Generated ad text:

[1413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1414] Step 1:

[1415] Users use their smartphones or computers to input product concepts, insights, benefits, and competitive comparison information. Specifically, they enter information such as "a new health drink," "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products" into a form. This input data is then sent to the server.

[1416] Step 2:

[1417] The server stores the received product concept data in an internal database. At the same time, it acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database. The input is the user's concept data, and the output is the saved internal database.

[1418] Step 3:

[1419] The server uses an emotion engine to extract emotion data from user input data and user interactions. Specifically, it uses the TextBlob library to analyze the user's emotional state (positive, negative, etc.) from the tone and expression of the text entered by the user. The input is the user's text data, and the output is the analyzed emotion data.

[1420] Step 4:

[1421] The server uses AI to extract targets based on the emotional data and automatically generates the optimal distribution scenario. Specifically, the emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" and generates a distribution scenario based on them. The input is emotional data and the output is a distribution scenario.

[1422] Step 5:

[1423] The server uses the OpenAI API to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a catchphrase such as "Get healthy easily" and an image of an office worker drinking a drink. The input is the distribution scenario, and the output is the advertising content.

[1424] Step 6:

[1425] The generated content is sent to the designer through a user interface, who adjusts color, font, placement, etc. Specifically, the designer reviews the generated images and text and makes any necessary corrections. The input is the advertising content, and the output is the adjusted advertising content.

[1426] Step 7:

[1427] The server uses AI to automatically detect legal risks in advertising content and compliance with brand guidelines, and presents the results to the legal department. Specifically, the AI ​​detects and reports legal risks and violations of brand guidelines in advertising copy. The input is the adjusted advertising content, and the output is the legal risk detection results.

[1428] Step 8:

[1429] The user device delivers content to target users based on the delivery scenario and content received from the server, and conducts AB testing. Specifically, a "Easy Health" version and a "Post-Sports Recovery" version are delivered to different target groups, and the effectiveness for each group is measured. The input is the delivery scenario and advertising content, and the output is the AB test results.

[1430] Step 9:

[1431] The server uses a BI tool to measure the CTR, CVR, ROI, etc. of the delivered content in real time. Specifically, it collects post-delivery data and analyzes the evaluation indicators for each target group. The input is the AB test results, and the output is the evaluation indicators.

[1432] Step 10:

[1433] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in advertisements for office workers and suggests new images and text. The input is the evaluation index, and the output is the improvement measures.

[1434] Step 11:

[1435] Users (marketers and designers) review the AI's suggestions and adjust the final content and distribution scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary. The input is the improvements, and the output is the final adjusted content and distribution scenario.

[1436] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1437] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1438] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1439] [Fourth embodiment]

[1440] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1441] 7, a 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.

[1442] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1443] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1444] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1446] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1447] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1448] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1449] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1450] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1451] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1452] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1453] This invention is a system that automatically executes digital marketing by inputting a product concept into AI. This system includes the processes of inputting the product concept, formulating a distribution scenario, creating content, legal and brand checks, distributing content to the target, measuring effectiveness, and making improvements based on the results.

[1454] Program processing

[1455] User side

[1456] 1. Enter the product concept

[1457] Users use the terminal to input product concepts, insights (consumer insights), benefits, and competitive comparison information.

[1458] Example: A user inputs information about a "new health drink," such as "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products" on a terminal.

[1459] Server side

[1460] 2. Data Reception and Analysis

[1461] The server compares the product concept data received from the user with internal data and external data (market data, trend data) and performs analysis.

[1462] Example: The server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[1463] 3. Generating a distribution scenario

[1464] The server automatically generates a distribution scenario using AI based on the selected target.

[1465] Example: AI generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (social media, email, etc.) for each target.

[1466] 4. Content Generation

[1467] The server uses AI to automatically generate content such as text, images, and videos based on the distribution scenario.

[1468] Example: AI generates the tagline "Easy Health" along with an image of an office worker drinking a drink.

[1469] 5. Content Selection and Tuning

[1470] The designer checks the content generated by the server and makes any final adjustments.

[1471] Example: A designer reviews the generated images and text and adjusts color, font, placement, etc.

[1472] 6. Legal Brand Check

[1473] The server uses AI to automatically detect legal risks and compliance with brand guidelines for content and presents them to the legal department.

[1474] Example: AI detects legal risks in ad copy and checks whether appropriate contact information is included. The results are reported to the legal department.

[1475] Terminal side

[1476] 7. Execution of distribution

[1477] The terminal delivers content to target users based on the distribution scenario and content received from the server and conducts AB testing.

[1478] Example: The device delivers a "quick health" version and a "post-sports recovery" version to different target groups (office workers and sports enthusiasts), and measures the effectiveness for each group.

[1479] 8. Effectiveness Measurement

[1480] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time.

[1481] Example: The server collects data after delivery, analyzes and displays the click rate and conversion rate for each target group.

[1482] Server side

[1483] 9. Analysis and improvement of results

[1484] The server uses AI to analyze the distribution results, analyze the difference between the predicted effect and the actual results, identify the cause, and automatically generate improvement measures.

[1485] Example: AI identifies that the visuals are the cause of low click-through rates on ads for office workers and suggests new images and text.

[1486] User side

[1487] 10. Final tuning

[1488] Users (especially marketers and designers) review the AI's suggestions and adjust the actual content and distribution scenarios.

[1489] Example: Marketers review suggested improvements and make manual adjustments as needed.

[1490] This invention makes it possible to efficiently carry out digital marketing even without specialized knowledge. This system automates the entire process, from product concept to distribution, evaluation, and improvement, thereby saving costs and time.

[1491] The processing flow will be explained below.

[1492] Step 1:

[1493] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1494] Step 2:

[1495] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1496] Step 3:

[1497] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[1498] Step 4:

[1499] AI automatically generates optimal delivery scenarios for the extracted targets. Scenarios include the message, delivery channel, delivery timing, etc. Specific actions that can be generated include "delivering social media ads to office workers on weekday mornings" and "delivering email ads on weekends to sports enthusiasts."

[1500] Step 5:

[1501] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Get healthy easily" and an image of an office worker holding a health drink.

[1502] Step 6:

[1503] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and fine-tunes the color tone, font, placement, etc.

[1504] Step 7:

[1505] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1506] Step 8:

[1507] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[1508] Step 9:

[1509] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[1510] Step 10:

[1511] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[1512] Step 11:

[1513] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1514] Step 12:

[1515] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[1516] Example 1

[1517] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1518] In traditional digital marketing, the process from entering product concepts to distributing advertising content, measuring effectiveness, and making improvements is often done manually, which not only takes a great deal of time and effort but also requires specialized knowledge, resulting in problems of inefficiency.In addition, checking whether the generated advertising content complies with legal risks and brand guidelines is often done manually, which poses challenges in terms of the time and human resources required for the checking process to avoid legal risks.

[1519] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1520] In this invention, the server includes means for receiving a product concept from a user, means for automatically generating a distribution scenario based on the received product concept using a generative AI model, and means for generating advertising content based on the distribution scenario automatically generated using the generative AI model. This makes it possible to provide an environment in which a user simply inputs a product concept, and the AI ​​automatically generates a distribution scenario and advertising content, enabling a series of digital marketing processes to be executed quickly and efficiently.

[1521] A "product concept" is an idea or strategy that includes the basic purpose and characteristics of a product or service, target market, competitive analysis, etc.

[1522] "Means for receiving" refers to a function or process for acquiring data input by a user.

[1523] A "generative AI model" refers to artificial intelligence technology and algorithms that automatically generate scenarios and content based on input information from users.

[1524] A "distribution scenario" is a plan that defines what advertising content will be distributed to a specific target, at what timing, and through which channel.

[1525] "Advertising content" refers to promotional materials such as text, images, and videos created based on a distribution scenario.

[1526] A "creator" is a professional who is responsible for the final design and adjustment of advertising content.

[1527] "Legal risk" refers to the possibility that advertising content may violate laws or regulations.

[1528] "Brand guidelines" are rules regarding design and messaging established to maintain a company's brand image.

[1529] A "legal department" is a department within a company or organization that manages and deals with legal issues and risks.

[1530] "Target users" refers to the customer demographic that is anticipated when delivering advertisements, specifically the recipients of the advertisements.

[1531] "AB testing" is a method of comparing two or more versions of an advertisement or piece of content to determine which is more effective.

[1532] "Analysis tools" refer to software and platforms for collecting and analyzing data and visualizing the results.

[1533] "Click-through rate" refers to the percentage of clicks on an ad compared to the number of times it is displayed.

[1534] "Conversion rate" is the percentage of ads that result in a targeted action (such as a purchase or registration).

[1535] "Return on investment" is an indicator that evaluates how much profit is gained from the resources invested in advertising and marketing activities.

[1536] "Evaluation results" refer to various indicators (click-through rate, conversion rate, return on investment, etc.) obtained using analysis tools after advertising is delivered.

[1537] "Root cause analysis" is the process of identifying the causes of problems or lack of effectiveness with advertising or content.

[1538] "Improvement measures" are specific action plans to address identified problems and causes.

[1539] A "marketer" is a professional who is responsible for marketing activities in a company or organization.

[1540] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. The main elements that make up the system are users, devices, and servers, each of which plays a specific role.

[1541] First, the user uses a terminal to input the product concept, insights (consumer insights), benefits, and competitive comparison information. For example, for a new health drink, the user can input insights and benefits such as "maintaining health in a busy life" and "easily achieving health," as well as "comparison data with similar competitive products." This information is sent to the server via the terminal.

[1542] The server compares the received product concept data with its internal database and external data (market data, trend data) and performs an analysis. This analysis uses an AI model (e.g., machine learning algorithms, data analysis tools, etc.). Specifically, the server uses AI to analyze trend data on the health drink market and other advertising data, and selects "health-conscious working generation" and "sports enthusiasts" as target users.

[1543] Next, the server automatically generates a distribution scenario based on the selected targets using a generative AI model (e.g., natural language processing model). For example, the AI ​​could generate a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts," and select the optimal distribution channel (e.g., social media, email) for each target.

[1544] The server then uses a generative AI model to automatically generate advertising content such as text, images, and videos based on the distribution scenario. This process uses tools such as DeepArt for image generation and Synthesia for video generation. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[1545] The generated content and distribution scenarios are then checked by a designer, who makes final adjustments using design tools such as Adobe Creative Cloud to adjust color tones, fonts, and image placement.

[1546] The server then uses AI to detect legal risks and compliance with brand guidelines in the ad content. For example, it uses Compliance AI tools to check for potential legal risks in the ad copy, checks for violations of guidelines, and reports the results to the legal department.

[1547] The device then delivers content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the device delivers advertisements for "easy health" and "recovery after sports" to different target groups (office workers and sports enthusiasts) and measures the effectiveness of each.

[1548] Finally, the server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time and analyze the results. Based on this evaluation, the AI ​​analyzes the cause and presents improvement measures, and marketers and designers make final adjustments.

[1549] An example prompt is:

[1550] Please enter your product concept for a "new healthy drink." Please include specific consumer insights, benefits, and competitive comparison information.

[1551] example:

[1552] Insight: "Staying healthy in a busy life"

[1553] Benefit: "Easy to get healthy"

[1554] Competitive comparison: "Comparative data with similar competing products"

[1555] As a result, this system automates the entire process from product concept to distribution, evaluation, and improvement, resulting in significant cost and time savings.

[1556] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1557] Step 1:

[1558] The user uses a terminal to input and submit a product concept. Specifically, the user enters the concept of a "new health drink," along with insights (e.g., "Maintaining health in a busy life"), benefits (e.g., "Easily achieve health"), and competitive comparison information into the form, and clicks the submit button. The input information is sent from the terminal to the server.

[1559] Input: Product concept, insights, benefits, competitive comparison information

[1560] Output: Product concept data sent to the server

[1561] Step 2:

[1562] The server analyzes the product concept data received from the user by comparing it with the internal database and external data (market data, trend data). Specifically, the server analyzes the user's input data using past sales data and consumer reviews from the internal database, as well as market trend data obtained through external APIs. An AI model is used in this analysis to select the optimal target users.

[1563] Input: Product concept data, internal database, external data

[1564] Output: Analysis results (e.g., "health-conscious working generation" and "sports enthusiasts")

[1565] Step 3:

[1566] The server automatically generates a distribution scenario based on the selected target using a generative AI model. Specifically, it uses a generative AI model (e.g., a natural language processing model) to create scenarios for a "healthy drink advertisement for office workers" and a "recovery drink advertisement for sports enthusiasts." It also selects the optimal distribution channel (e.g., social media, email, etc.) for each target.

[1567] Input: Analysis results, generated AI model

[1568] Output: Delivery scenario

[1569] Step 4:

[1570] The server uses the generative AI model to automatically generate advertising content based on the generated distribution scenario. Specific operations include using a natural language generation model to generate text, an image generation tool (e.g., DeepArt) to generate images, and a video generation tool (e.g., Synthesia) to generate videos. For example, the AI ​​generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[1571] Input: Delivery scenario, generative AI model

[1572] Output: Ad content (text, images, videos)

[1573] Step 5:

[1574] Creators adjust the content and distribution scenarios generated by the server. Specifically, creators use design tools (e.g., Adobe Creative Cloud) to adjust the color tone, font, and placement of generated images and text.

[1575] Input: Ad content, distribution scenario

[1576] Output: Adjusted advertising content, distribution scenario

[1577] Step 6:

[1578] The server uses AI to detect legal risks and compliance with brand guidelines in advertising content and presents the results to the legal department. Specifically, it uses legal risk detection tools (e.g., Compliance AI) to analyze content and checks compliance with guidelines.

[1579] Input: Tailored ad content

[1580] Output: Legal risk and brand guideline compliance detection results

[1581] Step 7:

[1582] The device delivers content to target users based on the delivery scenario and content received from the server, and performs AB testing. Specifically, an ad management tool (e.g., Facebook Ads Manager) is used for delivery, and different versions of ads are delivered to different target groups.

[1583] Input: Distribution scenario, advertising content

[1584] Output: Advertisements delivered to target users, AB test results

[1585] Step 8:

[1586] The server uses analytical tools (e.g., Tableau, Power BI) to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered content in real time. Specifically, it collects and visualizes user data after ad delivery and analyzes the effectiveness indicators for each target group.

[1587] Input: AB test results, target user data

[1588] Output: Effectiveness measurement results (CTR, CVR, ROI)

[1589] Step 9:

[1590] The server uses AI to analyze the results of effectiveness measurements, analyzes the difference between predicted and actual results to identify the cause, and automatically generates improvement measures.Specifically, it uses an AI model (e.g., machine learning algorithm) to generate new suggestions for identified problems.For example, it may identify that the cause of a low click-through rate is visual and suggest new images and text.

[1591] Input: Effectiveness measurement results

[1592] Output: Cause analysis, improvement suggestions

[1593] Step 10:

[1594] Users (especially marketers and creators) review the AI's suggestions and make final adjustments to the actual content and distribution scenario. Specifically, marketers adjust distribution schedules and targeting based on the suggestions, and creators make suggested design improvements.

[1595] Input: Improvement suggestion

[1596] Output: Final adjusted ad content and distribution scenario

[1597] (Application example 1)

[1598] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1599] In the field of digital marketing, there is a demand for automation of the creation, distribution, effectiveness measurement, and improvement of effective advertising campaigns. Conventional methods require marketers to expend a lot of time and effort and specialized knowledge, resulting in inefficiency and high costs. In addition, it is difficult to measure the effectiveness of ads in real time or make quick improvements after they are delivered. This poses a challenge in maximizing the effectiveness of advertising investments.

[1600] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1601] In this invention, the server includes: means for receiving a product concept from a user; means for automatically generating a distribution scenario using AI based on the received product concept; means for automatically generating advertising content using AI based on the automatically generated distribution scenario; means for a designer to adjust the generated content and distribution scenario; means for detecting legal risks of the advertising content and compliance with brand guidelines using AI and presenting the results to the legal department; means for delivering the generated advertising content to target users via their smart devices and performing A / B testing; means for evaluating real-time data collected from the smart devices using a BI tool and measuring CTR, CVR, and ROI; and means for analyzing the evaluation results using AI and automatically improving the advertising content and distribution scenario. This enables the automation of effective advertising campaigns.

[1602] "Product concept" refers to detailed information about a product or service, such as its features, benefits, and target users.

[1603] "User" means a person or entity that utilizes the System to enter product concepts and manage advertising campaigns.

[1604] A "distribution scenario" refers to a plan for distributing content to specific target users through what channels and at what timing.

[1605] "AI" refers to artificial intelligence technology, which includes algorithms and models for automatically solving specific problems.

[1606] "Advertising Content" refers to materials such as text, images, and video created for advertising purposes.

[1607] "Designer" refers to the person who makes the final adjustments to the generated advertising content and visually optimizes it.

[1608] "Legal risk" refers to the risk that advertising content may violate the law.

[1609] "Brand guidelines" refer to standards for design and messaging established to maintain brand consistency.

[1610] "Legal Department" means the department within an organization that considers and resolves legal matters.

[1611] "Target users" refers to the group of users who are intended to receive a particular message of an advertising campaign.

[1612] "Smart devices" refers to advanced electronic devices with internet connectivity, such as smartphones, tablets, and smart glasses.

[1613] "AB testing" refers to a testing method in which different versions of advertising content are simultaneously delivered to target users and their effectiveness is compared.

[1614] "BI tool" stands for business intelligence tool and refers to software that analyzes data to support business decision-making.

[1615] "CTR" stands for click-through rate and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[1616] "CVR" stands for conversion rate and refers to the percentage of times a specific action (purchase, registration, etc.) is performed.

[1617] "ROI" stands for return on investment and refers to an indicator that financially evaluates the effectiveness of the money invested in an advertising campaign.

[1618] "Real-time data" refers to data that is collected continuously from the moment an ad is delivered.

[1619] This invention is a system that automatically executes digital marketing by inputting product concepts into AI. This system is divided into a user side and a server side.

[1620] User side

[1621] Entering product concepts

[1622] Users use a smartphone app to input product concepts, insights, benefits, and competitive analysis information. For example, for a "new health drink," users can input "staying healthy in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1623] Server side

[1624] Data reception and analysis

[1625] The server analyzes the product concept data received from users by comparing it with internal and external data. This analysis uses artificial intelligence (AI) models such as TensorFlow. The optimal target users are selected based on market and trend data. As a specific example, trend data from the health drink market is analyzed to select "health-conscious working people" and "sports enthusiasts" as targets.

[1626] Generating a distribution scenario

[1627] The server automatically generates distribution scenarios using AI based on the selected target users. For example, the AI ​​generates "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and selects the optimal distribution channel (SNS, email, etc.) for each target.

[1628] Content Generation

[1629] The server uses AI to generate advertising content such as text, images, and videos based on a distribution scenario. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink.

[1630] Legal Brand Check

[1631] AI is used to detect legal risks and compliance with brand guidelines in generated advertising content, and presents the results to the legal department. For example, AI can detect legal risks in advertising copy and check whether appropriate contact information is included.

[1632] Terminal side

[1633] Executing the distribution

[1634] The smartphone app delivers advertising content to target users based on the delivery scenario and content received from the server, and conducts A / B testing. For example, the app delivers two versions, "Easy Health" and "Post-Sports Recovery," to different target groups (office workers and sports enthusiasts), and measures the effectiveness of each.

[1635] Effectiveness measurement

[1636] The server uses BI (business intelligence) tools to measure the click-through rate (CTR), conversion rate (CVR), return on investment (ROI), etc. of the delivered advertising content in real time. For example, the server collects data after delivery and analyzes and displays the click-through rate and conversion rate of each target group. For this purpose, BI tools such as Tableau are used.

[1637] Results analysis and improvement

[1638] The server uses AI to analyze the results of distribution, analyze the difference between the predicted effect and the actual result, identify the cause, and automatically generate improvement measures. For example, the AI ​​may identify that the visuals are the cause of the low click-through rate of ads aimed at office workers, and suggest new images and text.

[1639] User side

[1640] Final Tuning

[1641] Users, especially marketers and designers, review the AI ​​suggestions and adjust the actual content and distribution scenarios. For example, marketers review the suggested improvements and make manual adjustments as necessary.

[1642] Prompt Sentence Examples

[1643] Product concept: A new health drink

[1644] Consumer Insights: Busy lifestyles and the need to stay healthy

[1645] Benefit: Easy health

[1646] Competitive comparison: Comparison data with similar competing products

[1647] In this way, effective advertising campaigns can be automated and efficiently executed.

[1648] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1649] Step 1:

[1650] Users use a smartphone app to input product concepts, consumer insights, profits, and competitive analysis information.

[1651] For example, the user inputs "new healthy drink" along with consumer insights and comparison data with competing products. The device then sends this data to the server.

[1652] Step 2:

[1653] The server analyzes the product concept data received from the user by comparing it with internal data and external data.

[1654] This analysis uses AI models such as TensorFlow. The server selects the optimal target users based on market and trend data. The output is a list of target users (e.g., "health-conscious working generation" or "sports enthusiasts").

[1655] Step 3:

[1656] The server automatically generates a distribution scenario using AI based on the target users.

[1657] For example, AI can generate "healthy drink ads for office workers" and "recovery drink ads for sports enthusiasts," and select the optimal distribution channel (e.g., social media or email) for each target. Specific distribution scenarios are generated as an output.

[1658] Step 4:

[1659] The server automatically generates advertising content using AI based on the generated distribution scenario.

[1660] Specifically, it generates advertising materials such as text, images, and videos. For example, it generates a tagline such as "Easy Health" and an image of an office worker drinking a drink. The output is the completed advertising content.

[1661] Step 5:

[1662] Use AI to detect legal risks and compliance with brand guidelines before presenting server-generated ad content to the legal department.

[1663] For example, AI can detect legal risks and brand guideline violations in ad copy and report the results to the legal department. The output is a check result for legal risk and brand suitability.

[1664] Step 6:

[1665] The device delivers advertising content to target users based on the delivery scenario and content received from the server, and performs AB testing.

[1666] For example, we deliver two versions of the AB test, one for "easy health" and the other for "recovery after sports" to different target groups (office workers and sports enthusiasts), and measure their effectiveness. The input is the delivery scenario and content from the server, and the output is the results of the AB test.

[1667] Step 7:

[1668] The server uses a BI tool (e.g., Tableau) to measure the effectiveness of advertising content in real time.

[1669] It calculates and analyzes metrics such as click-through rate (CTR), conversion rate (CVR), and return on investment (ROI). The input is user response data to delivered advertising content, and the output is the real-time measurement results of these metrics.

[1670] Step 8:

[1671] The server uses AI to analyze the distribution results and analyze the difference between the predicted effect and the actual results.

[1672] For example, AI can identify that the low click-through rate of ads for office workers is due to visuals and suggest new images and text. The input is effectiveness measurement data, and the output is the results of an analysis of the causes and suggestions for improvement.

[1673] Step 9:

[1674] The user reviews the AI's suggestions and makes manual adjustments if necessary.

[1675] Marketers and designers review the proposed improvements and make final adjustments to the content and distribution scenario. The input is the improvement suggestions from the AI, and the output is the final adjusted advertising content and distribution scenario.

[1676] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1677] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[1678] Program processing

[1679] User side

[1680] 1. Enter the product concept

[1681] The user uses the terminal to input the product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into the form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1682] Server side

[1683] 2. Data Reception and Analysis

[1684] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1685] 3. Emotion Data Analysis

[1686] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[1687] 4. Generating a distribution scenario

[1688] The server extracts targets based on the emotional data and automatically generates optimal distribution scenarios using AI. Specifically, the emotion engine sets targets such as "office workers with positive emotions" or "sports enthusiasts feeling tired" and generates distribution scenarios based on them.

[1689] 5. Content Generation

[1690] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[1691] 6. Content Selection and Tuning

[1692] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color, font, and placement.

[1693] 7. Legal Brand Check

[1694] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1695] Terminal side

[1696] 8. Execution of distribution

[1697] The device distributes content to target users based on the distribution scenario and content received from the server, and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[1698] 9. Measurement

[1699] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[1700] Server side

[1701] 10. Analysis and improvement of results

[1702] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1703] User side

[1704] 11. Final tuning

[1705] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[1706] This invention enables efficient digital marketing even without specialized knowledge. Furthermore, by combining it with an emotion engine, distribution scenarios and advertising content can be optimized to match user emotions, resulting in more effective digital marketing. This system automates the entire process, from product conception through distribution, evaluation, and improvement, thereby saving time and money.

[1707] The processing flow will be explained below.

[1708] Step 1:

[1709] The user uses a terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user enters information about a "new health drink" into a form, such as "maintaining health in a busy life," "getting healthy easily," and "comparison data with similar competing products."

[1710] Step 2:

[1711] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1712] Step 3:

[1713] The server launches an AI engine to analyze internal and external data and extracts the optimal target users based on the product concept. Specifically, the server extracts two target segments: "health-conscious office workers" and "sports enthusiasts."

[1714] Step 4:

[1715] The server uses the emotion engine to extract emotion data from user input data and user interactions. Specifically, it analyzes the user's emotional state (e.g., positive, negative) from the tone and expression of the text entered by the user.

[1716] Step 5:

[1717] Based on the extracted target and emotional data, AI automatically generates optimal distribution scenarios. The scenarios include the message, distribution channel, and distribution timing. Specific actions generated include "delivering morning social media ads to office workers with positive emotions" and "delivering weekend email ads to sports enthusiasts feeling tired."

[1718] Step 6:

[1719] The server uses AI to automatically generate content such as text, images, and videos based on a distribution scenario. Specifically, the AI ​​generates a catchphrase such as "Easily get healthy" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals that match the user's emotions.

[1720] Step 7:

[1721] The server sends the generated content to the designer, who makes the final adjustments. Specifically, the designer checks the generated images and text and adjusts the color tone, font, and placement.

[1722] Step 8:

[1723] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​detects legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1724] Step 9:

[1725] The server presents the results of the legal and brand check to the legal department, who then performs a final check. Specifically, the legal department checks the presented report and returns feedback to the server if there are any problems.

[1726] Step 10:

[1727] The server sends the distribution scenario and content to the device, which then distributes the content to the target users and conducts AB testing.Specifically, the device distributes the "Easy Health" version and the "Post-Sports Recovery" version to different target groups.

[1728] Step 11:

[1729] The server uses a BI tool to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Specifically, the server collects data after delivery and analyzes the evaluation indicators for each target group.

[1730] Step 12:

[1731] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1732] Step 13:

[1733] Users (especially marketers and designers) review the AI's suggestions and adjust the final content and distribution scenarios. Specifically, marketers review the suggested improvements and make manual adjustments as necessary.

[1734] Example 2

[1735] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1736] Modern digital marketing requires efficient and effective delivery of advertising content, but traditional methods have the following problems:

[1737] 1. The process from entering product concepts to generating distribution scenarios is done manually, which is time-consuming and costly.

[1738] 2. Delivery scenarios and advertising content are created uniformly and do not respond to the emotions and needs of target users.

[1739] 3. Because effectiveness measurement and analysis are done manually, improvement measures are delayed. Also, because A / B testing and its effectiveness measurement cannot be carried out efficiently, it is difficult to optimize advertising.

[1740] The present invention aims to solve these problems and provide a system that realizes efficient and effective digital marketing.

[1741] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1742] In this invention, the server includes: means for receiving a product concept from a user; means for comparing and analyzing the received product concept with internal data and external data; means for extracting emotional data from user interactions; means for extracting targets based on the emotional data and automatically generating an optimal distribution scenario using AI; means for automatically generating advertising content using a generative AI model; means for a designer to adjust the generated content and distribution scenario; means for using AI to detect legal risks and compliance with brand guidelines of the advertising content and present it to the legal department; means for delivering the generated advertising content to target users and performing A / B testing; means for evaluating the delivery results using a BI tool and measuring CTR, CVR, and ROI; means for analyzing the evaluation results using AI and improving the distribution scenario and content; and means for marketers and designers to make final adjustments based on the AI's improvement suggestions. This enables efficient and effective digital marketing.

[1743] "Product Concept" refers to the main idea or features of the product or service you offer.

[1744] "Internal data" refers to information generated or collected within a company that is used for analysis or application within a system.

[1745] "External data" refers to information obtained from outside the company, such as data on trends and markets, that is used in analysis in combination with internal data.

[1746] "Emotional data" refers to emotional states (e.g., positive, negative) extracted from user input and interactions.

[1747] "Target" refers to a group of users to whom marketing is directed based on specific conditions or attributes.

[1748] A "distribution scenario" refers to a plan or strategy for how to deliver advertisements to a target audience.

[1749] A "generative AI model" refers to an artificial intelligence model that automatically generates content such as text, images, and videos based on pre-trained algorithms.

[1750] "Designer" refers to a professional who makes final adjustments to generated content, modifying it to meet visual satisfaction and brand guidelines.

[1751] "Legal risk" refers to potential problems that may arise from advertising content violating laws or regulations.

[1752] "Brand guidelines" refer to regulations regarding design and expression that are intended to maintain consistency in a company or product brand.

[1753] "Influential target users" refers to a specific user group for whom advertising content may have a high influence or potential effect.

[1754] "AB testing" refers to a method of comparing two or more versions of advertising content and measuring their effectiveness.

[1755] "BI tools" refers to software used for business intelligence, tools that support data analysis and report creation.

[1756] "CTR" stands for Click Through Rate, and refers to the ratio of the number of times an ad is clicked to the number of times it is displayed.

[1757] "CVR" stands for conversion rate, and refers to the ratio of the number of times users who clicked on an ad actually took the target action, such as purchasing or registering.

[1758] "ROI" stands for Return on Investment and refers to the ratio of return on investment for advertising and marketing initiatives.

[1759] "Final adjustment" refers to the process in which human experts make final corrections and fine-tuning to AI suggestions and automatically generated content.

[1760] This invention is a system that automatically executes digital marketing by inputting product concepts into AI, and further combines it with an emotion engine to recognize user emotions and optimize distribution scenarios and advertising content based on those emotions. This system includes the following processes: inputting product concepts, formulating distribution scenarios, recognizing emotion data, creating advertising content, legal and brand checks, delivering content to targets, measuring effectiveness, and making improvements based on the results.

[1761] Hardware and software used

[1762] Hardware: Servers, terminals, user input devices (e.g., PCs, tablets, smartphones)

[1763] Software: Generative AI models, emotion engines, BI tools

[1764] Explanation of the program's processing steps

[1765] 1. User side

[1766] The user uses the terminal to input product concept, insights, benefits, and competitive comparison information. Specifically, the user inputs the following information about a "new health drink."

[1767] Product concept: A new health drink

[1768] Insight: Staying healthy in a busy life

[1769] Benefit: Easy health

[1770] Competitive comparison information: Comparison data with similar competing products

[1771] 2. Server side

[1772] The server stores the product concept data received from the user in an internal database and simultaneously acquires related external data (market data, trend data). Specifically, it collects market trends and past advertising data and stores them in the database.

[1773] 3. Emotion Data Analysis

[1774] The server uses an emotion engine to extract emotion data from user input and user interactions. Specifically, it analyzes the tone and expression of the text entered by the user to determine the user's emotional state (e.g., positive, negative).

[1775] 4. Generating a distribution scenario

[1776] The server extracts targets based on emotional data and automatically generates optimal distribution scenarios using AI. Targets such as "office workers with positive emotions" and "sports enthusiasts feeling tired" are set using an emotion engine, and distribution scenarios are generated based on these targets.

[1777] 5. Content Generation

[1778] The server uses a generative AI model to automatically generate advertising content such as text, images, and videos based on a distribution scenario. For example, the AI ​​generates a catchy slogan such as "Get healthy easily" and an image of an office worker drinking a drink. It also uses an emotion engine to optimize messages and visuals to match the user's emotions.

[1779] 6. Content Selection and Tuning

[1780] The server sends the generated content to the designer, who then makes the final adjustments. Specifically, the designer reviews the generated images and text and adjusts the color tone, font, and placement.

[1781] 7. Legal Brand Check

[1782] The server uses AI to automatically detect legal risks and brand guideline compliance in the generated content. Specifically, the AI ​​identifies legal risk areas in the ad copy and checks whether appropriate contact information is included.

[1783] 8. Execution of distribution

[1784] The device delivers content to target users based on the delivery scenario and advertising content received from the server, and conducts AB testing.Specifically, the device delivers a "Easy Health" version and a "Post-Sports Recovery" version to different target groups, and measures the effectiveness for each group.

[1785] 9. Measurement

[1786] The server uses BI tools to measure the CTR (click-through rate), CVR (conversion rate), ROI (return on investment), etc. of the delivered content in real time. Post-delivery data is collected and the evaluation indicators for each target group are analyzed.

[1787] 10. Analysis and improvement of results

[1788] Based on the analysis results of the BI tool, the server uses AI to analyze the difference between the predicted effect and the actual result, identifies the cause, and automatically generates improvement measures. Specifically, the AI ​​identifies that there is a problem with the visuals in the advertisements for office workers and suggests new images and text.

[1789] 11. Final tuning

[1790] Users (especially marketers and designers) review the AI's suggestions and adjust the final ad content and delivery scenario. Specifically, marketers review the proposed improvements and make manual adjustments as necessary.

[1791] Examples of prompt statements

[1792] For example, a possible prompt for an AI model might be:

[1793] Create a marketing campaign for a new health drink. The product concept should be "Staying healthy in a busy life," the benefit should be "Getting healthy easily," and include comparative information about competing products. Target office workers and sports enthusiasts.

[1794] This system makes it possible to carry out digital marketing efficiently even without specialized knowledge. In addition, by combining it with an emotion engine, it is possible to optimize delive...

Claims

1. means for receiving a product concept from a user; A method to automatically generate a distribution scenario using AI based on the received product concept, A method for automatically generating advertising content using AI based on automatically generated distribution scenarios, and A means for designers to adjust the generated content and delivery scenarios; A method to use AI to detect legal risks and brand guideline compliance of advertising content and provide it to the legal department. A means for distributing generated advertising content to influential target users and conducting A / B testing; A way to evaluate delivery results using a BI tool and measure CTR, CVR, and ROI. A method for analyzing evaluation results using AI and improving distribution scenarios and content; A system including:

2. 2. The system according to claim 1, further comprising means for analyzing the received product concept by comparing it with internal data and external data, and generating a distribution scenario.

3. The system of claim 1 includes a means for AI to analyze causes and propose improvement measures based on the results of effectiveness measurements of delivered advertising content, allowing marketers and designers to make final adjustments.

Images